Second train of SnowballTarget

SnowballTarget.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ceb15ce328c4611d0551260d3c357558385e0db3275a82c15ddcda821e7ea5b1
-size 908634
+oid sha256:d781eedf292764ed50c847df775e1070a8eba82fbeb44da3a91a549ffedfa878
+size 1693434

SnowballTarget/SnowballTarget-149984.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a5d7295aa5f3073955dd617162e3bee3abd6ebf30fe2ecb41d8dc69ff9b3af30
-size 908634
+oid sha256:5efbb9e00ec26a4b05fa1dc0772e35a6e235c99429c9f86edb39e35c9ba2d671
+size 1693434

SnowballTarget/SnowballTarget-149984.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:03870315e891d42024c170bb1c2edb5c4c82baf2674bd0d8f151969ed87ca973
-size 5428853
+oid sha256:6df381b2231c390de5bf79159c936ba1cd9a40bb0ce3183a65c1c3fd10106b4f
+size 10126706

SnowballTarget/SnowballTarget-199984.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ceb15ce328c4611d0551260d3c357558385e0db3275a82c15ddcda821e7ea5b1
-size 908634
+oid sha256:eaeb514ee7620320b1a5973b4b93321e9eb46ad00c93fe0bd7e9ff1c6ccfb826
+size 1693434

SnowballTarget/SnowballTarget-199984.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe13e91df9e5c36d85fdc5ad4089252c9357f999fa5b84c82a456d083b7ff2fa
-size 5428853
+oid sha256:64be63bdefe4f5e49be6c416fe67c1845e62e55e43181bcb817cea89e9b64b4d
+size 10126706

SnowballTarget/{SnowballTarget-200112.onnx → SnowballTarget-249944.onnx}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ceb15ce328c4611d0551260d3c357558385e0db3275a82c15ddcda821e7ea5b1
-size 908634
+oid sha256:c8e263e5a6dd7a3fcabf3aa5616976fceb6591aba7e597d668541db8ebc93020
+size 1693434

SnowballTarget/SnowballTarget-249944.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b24e67ef04ef94eba7e633730e6f269f3f739952ab3fe65207e25c6bfad29d10
+size 10126706

SnowballTarget/{SnowballTarget-200112.pt → SnowballTarget-299968.onnx}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:42b8393fe74e16e42f0fcdf81a385e87ea256436821d2477f02ddc39c4cc7f91
-size 5428853
+oid sha256:a45c195cdff773391ac5d577817f611badc802dd4304f35b3d10b07a7d64be50
+size 1693434

SnowballTarget/SnowballTarget-299968.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b6f85dd1af5c7440f1789d7db7e5617f311983fdef3c8ce8e8769fb3afa1f6d
+size 10126706

SnowballTarget/SnowballTarget-349992.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b970edc65ffb4e58947b5d81b7d9bdaea7c818cf029b09fddfd6fa9f2624651e
+size 1693434

SnowballTarget/SnowballTarget-349992.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a7b2b19afed3ba1154c6b4dc0a89b104dc3d207987e695861e3e318b3c3aba2
+size 10126706

SnowballTarget/SnowballTarget-399992.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d781eedf292764ed50c847df775e1070a8eba82fbeb44da3a91a549ffedfa878
+size 1693434

SnowballTarget/SnowballTarget-399992.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9400920e1b0959a440d95ebf9f4230e2dbdaee79f542d72c3976cc544709424
+size 10126706

SnowballTarget/SnowballTarget-400312.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d781eedf292764ed50c847df775e1070a8eba82fbeb44da3a91a549ffedfa878
+size 1693434

SnowballTarget/SnowballTarget-400312.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:620e7ed9f4ca0d63a6ade35b8f500f69bdad73d743a6cc9d020ab48018b90342
+size 10126706

SnowballTarget/SnowballTarget-49936.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5127eed5dcaeb14b9b9a31366c9d146c0fd3d30bb043f0937e1fa802c147ffab
-size 908634
+oid sha256:e5e2f6131a0a9a03773b92aff75787fc4d2ea3b6a025c3bf9ae4e10bac275d43
+size 1693434

SnowballTarget/SnowballTarget-49936.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bfec2313f555eb450dcc648fb75a76f76be0a5a7ea23f0f42ea8617ac77cf4b3
-size 5428853
+oid sha256:84c131e54d3f5b3b6a3f7bc243626ea533610540a0069042a6d777cf0baabf24
+size 10126706

SnowballTarget/SnowballTarget-99960.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a740f1c203ae75c8df62f5495a3aeb7957a7f47ae2837c1c896659fd53a2ad8
-size 908634
+oid sha256:0b040b13b8a1a7fd95ee7c9165690481f02a7d6383e21fe1654ef9e50b4e4e16
+size 1693434

SnowballTarget/SnowballTarget-99960.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:222054e97f64d33d200c539db9cd8e759bd1645b30f95f67d90faac2113ec69e
-size 5428853
+oid sha256:84c67e6721eefa5e6c6affe37f963f3aac7a1ebc179d6b3593230198d734e3b5
+size 10126706

SnowballTarget/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:42b8393fe74e16e42f0fcdf81a385e87ea256436821d2477f02ddc39c4cc7f91
-size 5428853
+oid sha256:620e7ed9f4ca0d63a6ade35b8f500f69bdad73d743a6cc9d020ab48018b90342
+size 10126706

SnowballTarget/{events.out.tfevents.1677349265.055aa07f3599.2446.0 → events.out.tfevents.1677350869.055aa07f3599.9503.0}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d11e9c25e5bf912f30e13de9788cf672c519f7a25f220d5b12f73639510c64b
-size 18668
+oid sha256:7a8aaf3636192a2156dd6a6dfb840eed96eaa3e168c7320b9df1ff282b0a9d5e
+size 49627

config.json

@@ -1 +1 @@
-{"default_settings": null, "behaviors": {"SnowballTarget": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "learning_rate": 0.0003, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "network_settings": {"normalize": false, "hidden_units": 256, "num_layers": 3, "vis_encode_type": "resnet", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}}, "init_path": null, "keep_checkpoints": 10, "checkpoint_interval": 50000, "max_steps": 200000, "time_horizon": 64, "summary_freq": 10000, "threaded": true, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/SnowballTarget/SnowballTarget", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SnowballTarget1", "initialize_from": null, "load_model": false, "resume": false, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
+{"default_settings": null, "behaviors": {"SnowballTarget": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 256, "buffer_size": 4096, "learning_rate": 0.0003, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "network_settings": {"normalize": false, "hidden_units": 376, "num_layers": 3, "vis_encode_type": "resnet", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}}, "init_path": null, "keep_checkpoints": 10, "checkpoint_interval": 50000, "max_steps": 400000, "time_horizon": 64, "summary_freq": 10000, "threaded": true, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/SnowballTarget/SnowballTarget", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SnowballTarget2", "initialize_from": null, "load_model": false, "resume": false, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}

configuration.yaml

@@ -3,8 +3,8 @@ behaviors:
   SnowballTarget:
     trainer_type: ppo
     hyperparameters:
-      batch_size: 128
-      buffer_size: 2048
+      batch_size: 256
+      buffer_size: 4096
       learning_rate: 0.0003
       beta: 0.005
       epsilon: 0.2
@@ -15,7 +15,7 @@ behaviors:
       epsilon_schedule: linear
     network_settings:
       normalize: false
-      hidden_units: 256
+      hidden_units: 376
       num_layers: 3
       vis_encode_type: resnet
       memory: null
@@ -36,7 +36,7 @@ behaviors:
     init_path: null
     keep_checkpoints: 10
     checkpoint_interval: 50000
-    max_steps: 200000
+    max_steps: 400000
     time_horizon: 64
     summary_freq: 10000
     threaded: true
@@ -62,7 +62,7 @@ engine_settings:
   no_graphics: true
 environment_parameters: null
 checkpoint_settings:
-  run_id: SnowballTarget1
+  run_id: SnowballTarget2
   initialize_from: null
   load_model: false
   resume: false

run_logs/Player-0.log

@@ -2,9 +2,6 @@ Mono path[0] = '/content/ml-agents/training-envs-executables/linux/SnowballTarge
 Mono config path = '/content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/MonoBleedingEdge/etc'
 Preloaded 'lib_burst_generated.so'
 Preloaded 'libgrpc_csharp_ext.x64.so'
-PlayerPrefs - Creating folder: /root/.config/unity3d/Hugging Face
-PlayerPrefs - Creating folder: /root/.config/unity3d/Hugging Face/SnowballTarget
-Unable to load player prefs
 Initialize engine version: 2021.3.14f1 (eee1884e7226)
 [Subsystems] Discovering subsystems at path /content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/UnitySubsystems
 Forcing GfxDevice: Null
@@ -34,7 +31,7 @@ ALSA lib pcm.c:2642:(snd_pcm_open_noupdate) Unknown PCM default
 FMOD failed to initialize the output device.: "Error initializing output device. " (60)
 FMOD initialized on nosound output
 Begin MonoManager ReloadAssembly
-- Completed reload, in  0.117 seconds
+- Completed reload, in  0.083 seconds
 ERROR: Shader Sprites/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 ERROR: Shader Sprites/Mask shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 ERROR: Shader Legacy Shaders/VertexLit shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
@@ -45,7 +42,7 @@ ERROR: Shader Standard shader is not supported on this GPU (none of subshaders/f
 WARNING: Shader Unsupported: 'Standard' - All subshaders removed
 WARNING: Shader Did you use #pragma only_renderers and omit this platform?
 WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
-UnloadTime: 0.828512 ms
+UnloadTime: 0.677755 ms
 ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 requesting resize 84 x 84
 Setting up 1 worker threads for Enlighten.
@@ -53,7 +50,7 @@ Memory Statistics:
 [ALLOC_TEMP_TLS] TLS Allocator
   StackAllocators : 
     [ALLOC_TEMP_MAIN]
-      Peak usage frame count: [8.0 KB-16.0 KB]: 5369 frames, [16.0 KB-32.0 KB]: 91 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [8.0 KB-16.0 KB]: 10742 frames, [16.0 KB-32.0 KB]: 182 frames, [2.0 MB-4.0 MB]: 1 frames
       Initial Block Size 4.0 MB
       Current Block Size 4.0 MB
       Peak Allocated Bytes 2.0 MB
@@ -169,22 +166,22 @@ Memory Statistics:
       Peak Allocated Bytes 0 B
       Overflow Count 0
 [ALLOC_DEFAULT] Dual Thread Allocator
-  Peak main deferred allocation count 45
+  Peak main deferred allocation count 41
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
       Peak Allocated bytes 1.0 MB
     [ALLOC_DEFAULT_MAIN]
-      Peak usage frame count: [4.0 MB-8.0 MB]: 5461 frames
+      Peak usage frame count: [4.0 MB-8.0 MB]: 10924 frames, [8.0 MB-16.0 MB]: 1 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 6.7 MB
+      Peak Allocated memory 9.0 MB
       Peak Large allocation bytes 0 B
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 5461 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 10925 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 17.8 MB
+      Peak Allocated memory 17.6 MB
       Peak Large allocation bytes 16.0 MB
 [ALLOC_TEMP_JOB_1_FRAME]
   Initial Block Size 2.0 MB
@@ -213,13 +210,13 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.0 MB
     [ALLOC_GFX_MAIN]
-      Peak usage frame count: [32.0 KB-64.0 KB]: 4419 frames, [64.0 KB-128.0 KB]: 1042 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 9981 frames, [64.0 KB-128.0 KB]: 944 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 67.7 KB
+      Peak Allocated memory 66.8 KB
       Peak Large allocation bytes 0 B
     [ALLOC_GFX_THREAD]
-      Peak usage frame count: [32.0 KB-64.0 KB]: 5461 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 10925 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 39.6 KB
@@ -231,13 +228,13 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.0 MB
     [ALLOC_CACHEOBJECTS_MAIN]
-      Peak usage frame count: [0.5 MB-1.0 MB]: 5461 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 10925 frames
       Requested Block Size 4.0 MB
       Peak Block count 1
       Peak Allocated memory 0.6 MB
       Peak Large allocation bytes 0 B
     [ALLOC_CACHEOBJECTS_THREAD]
-      Peak usage frame count: [0.5 MB-1.0 MB]: 5460 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 10924 frames, [2.0 MB-4.0 MB]: 1 frames
       Requested Block Size 4.0 MB
       Peak Block count 1
       Peak Allocated memory 2.2 MB
@@ -249,13 +246,13 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.0 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 5461 frames
+      Peak usage frame count: [0-1.0 KB]: 10925 frames
       Requested Block Size 2.0 MB
       Peak Block count 1
       Peak Allocated memory 1.0 KB
       Peak Large allocation bytes 0 B
     [ALLOC_TYPETREE_THREAD]
-      Peak usage frame count: [1.0 KB-2.0 KB]: 5461 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 10925 frames
       Requested Block Size 2.0 MB
       Peak Block count 1
       Peak Allocated memory 1.7 KB

run_logs/timers.json

@@ -2,220 +2,220 @@
     "name": "root",
     "gauges": {
         "SnowballTarget.Policy.Entropy.mean": {
-            "value": 0.9121044874191284,
-            "min": 0.9121044874191284,
-            "max": 2.854031801223755,
-            "count": 20
+            "value": 0.8241392374038696,
+            "min": 0.8241392374038696,
+            "max": 2.8787403106689453,
+            "count": 40
         },
         "SnowballTarget.Policy.Entropy.sum": {
-            "value": 8708.7734375,
-            "min": 8708.7734375,
-            "max": 29228.140625,
-            "count": 20
+            "value": 8421.87890625,
+            "min": 7984.82763671875,
+            "max": 29797.83984375,
+            "count": 40
         },
         "SnowballTarget.Step.mean": {
-            "value": 199984.0,
+            "value": 399992.0,
             "min": 9952.0,
-            "max": 199984.0,
-            "count": 20
+            "max": 399992.0,
+            "count": 40
         },
         "SnowballTarget.Step.sum": {
-            "value": 199984.0,
+            "value": 399992.0,
             "min": 9952.0,
-            "max": 199984.0,
-            "count": 20
+            "max": 399992.0,
+            "count": 40
         },
         "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
-            "value": 12.57126522064209,
-            "min": 0.3565720319747925,
-            "max": 12.57126522064209,
-            "count": 20
+            "value": 13.510470390319824,
+            "min": 0.09209876507520676,
+            "max": 13.556648254394531,
+            "count": 40
         },
         "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
-            "value": 2451.396728515625,
-            "min": 69.17497253417969,
-            "max": 2550.962890625,
-            "count": 20
+            "value": 2634.541748046875,
+            "min": 17.86716079711914,
+            "max": 2770.59130859375,
+            "count": 40
         },
         "SnowballTarget.Environment.EpisodeLength.mean": {
             "value": 199.0,
             "min": 199.0,
             "max": 199.0,
-            "count": 20
+            "count": 40
         },
         "SnowballTarget.Environment.EpisodeLength.sum": {
             "value": 8756.0,
             "min": 8756.0,
             "max": 10945.0,
-            "count": 20
+            "count": 40
+        },
+        "SnowballTarget.Environment.CumulativeReward.mean": {
+            "value": 26.65909090909091,
+            "min": 2.8863636363636362,
+            "max": 26.88888888888889,
+            "count": 40
+        },
+        "SnowballTarget.Environment.CumulativeReward.sum": {
+            "value": 1173.0,
+            "min": 127.0,
+            "max": 1453.0,
+            "count": 40
+        },
+        "SnowballTarget.Policy.ExtrinsicReward.mean": {
+            "value": 26.65909090909091,
+            "min": 2.8863636363636362,
+            "max": 26.88888888888889,
+            "count": 40
+        },
+        "SnowballTarget.Policy.ExtrinsicReward.sum": {
+            "value": 1173.0,
+            "min": 127.0,
+            "max": 1453.0,
+            "count": 40
         },
         "SnowballTarget.Losses.PolicyLoss.mean": {
-            "value": 0.07862375247578693,
-            "min": 0.0654585087251297,
-            "max": 0.07862375247578693,
-            "count": 20
+            "value": 0.04546067557941355,
+            "min": 0.042070891773387395,
+            "max": 0.05577735437933977,
+            "count": 40
         },
         "SnowballTarget.Losses.PolicyLoss.sum": {
-            "value": 0.3144950099031477,
-            "min": 0.2618340349005188,
-            "max": 0.3737866257390021,
-            "count": 20
+            "value": 0.0909213511588271,
+            "min": 0.08414178354677479,
+            "max": 0.1583393368705669,
+            "count": 40
         },
         "SnowballTarget.Losses.ValueLoss.mean": {
-            "value": 0.1833415846249052,
-            "min": 0.12921473217726337,
-            "max": 0.27536161705559375,
-            "count": 20
+            "value": 0.15301765158188108,
+            "min": 0.09006862982185375,
+            "max": 0.31951044134649575,
+            "count": 40
         },
         "SnowballTarget.Losses.ValueLoss.sum": {
-            "value": 0.7333663384996209,
-            "min": 0.5168589287090535,
-            "max": 1.3768080852779687,
-            "count": 20
+            "value": 0.30603530316376215,
+            "min": 0.1801372596437075,
+            "max": 0.8356520559857874,
+            "count": 40
         },
         "SnowballTarget.Policy.LearningRate.mean": {
-            "value": 8.082097306000005e-06,
-            "min": 8.082097306000005e-06,
-            "max": 0.000291882002706,
-            "count": 20
+            "value": 4.716098428000004e-06,
+            "min": 4.716098428000004e-06,
+            "max": 0.000295116001628,
+            "count": 40
         },
         "SnowballTarget.Policy.LearningRate.sum": {
-            "value": 3.232838922400002e-05,
-            "min": 3.232838922400002e-05,
-            "max": 0.00138516003828,
-            "count": 20
+            "value": 9.432196856000007e-06,
+            "min": 9.432196856000007e-06,
+            "max": 0.000820998026334,
+            "count": 40
         },
         "SnowballTarget.Policy.Epsilon.mean": {
-            "value": 0.10269400000000001,
-            "min": 0.10269400000000001,
-            "max": 0.19729400000000002,
-            "count": 20
+            "value": 0.101572,
+            "min": 0.101572,
+            "max": 0.198372,
+            "count": 40
         },
         "SnowballTarget.Policy.Epsilon.sum": {
-            "value": 0.41077600000000003,
-            "min": 0.41077600000000003,
-            "max": 0.96172,
-            "count": 20
+            "value": 0.203144,
+            "min": 0.203144,
+            "max": 0.5736660000000001,
+            "count": 40
         },
         "SnowballTarget.Policy.Beta.mean": {
-            "value": 0.0001444306000000001,
-            "min": 0.0001444306000000001,
-            "max": 0.0048649706,
-            "count": 20
+            "value": 8.844280000000006e-05,
+            "min": 8.844280000000006e-05,
+            "max": 0.004918762799999999,
+            "count": 40
         },
         "SnowballTarget.Policy.Beta.sum": {
-            "value": 0.0005777224000000004,
-            "min": 0.0005777224000000004,
-            "max": 0.023089828,
-            "count": 20
-        },
-        "SnowballTarget.Environment.CumulativeReward.mean": {
-            "value": 25.40909090909091,
-            "min": 3.590909090909091,
-            "max": 25.40909090909091,
-            "count": 20
-        },
-        "SnowballTarget.Environment.CumulativeReward.sum": {
-            "value": 1118.0,
-            "min": 158.0,
-            "max": 1359.0,
-            "count": 20
-        },
-        "SnowballTarget.Policy.ExtrinsicReward.mean": {
-            "value": 25.40909090909091,
-            "min": 3.590909090909091,
-            "max": 25.40909090909091,
-            "count": 20
-        },
-        "SnowballTarget.Policy.ExtrinsicReward.sum": {
-            "value": 1118.0,
-            "min": 158.0,
-            "max": 1359.0,
-            "count": 20
+            "value": 0.00017688560000000012,
+            "min": 0.00017688560000000012,
+            "max": 0.013685933400000001,
+            "count": 40
         },
         "SnowballTarget.IsTraining.mean": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 20
+            "count": 40
         },
         "SnowballTarget.IsTraining.sum": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 20
+            "count": 40
         }
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1677349258",
+        "start_time_seconds": "1677350865",
         "python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[GCC 9.4.0]",
-        "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
+        "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget2 --no-graphics",
         "mlagents_version": "0.29.0.dev0",
         "mlagents_envs_version": "0.29.0.dev0",
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "1.8.1+cu102",
         "numpy_version": "1.22.4",
-        "end_time_seconds": "1677349723"
+        "end_time_seconds": "1677351763"
     },
-    "total": 464.670683895,
+    "total": 897.8772009929999,
     "count": 1,
-    "self": 0.43942728299987266,
+    "self": 0.734729729999799,
     "children": {
         "run_training.setup": {
-            "total": 0.1863661580000553,
+            "total": 0.11248506700030703,
             "count": 1,
-            "self": 0.1863661580000553
+            "self": 0.11248506700030703
         },
         "TrainerController.start_learning": {
-            "total": 464.0448904540001,
+            "total": 897.0299861959998,
             "count": 1,
-            "self": 0.5135775730110481,
+            "self": 1.076378736015613,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 9.617906478000009,
+                    "total": 7.147789585999817,
                     "count": 1,
-                    "self": 9.617906478000009
+                    "self": 7.147789585999817
                 },
                 "TrainerController.advance": {
-                    "total": 453.77839211298897,
-                    "count": 18201,
-                    "self": 0.2719364769961885,
+                    "total": 888.565351069984,
+                    "count": 36416,
+                    "self": 0.528692997982489,
                     "children": {
                         "env_step": {
-                            "total": 453.5064556359928,
-                            "count": 18201,
-                            "self": 314.1343340669872,
+                            "total": 888.0366580720015,
+                            "count": 36416,
+                            "self": 620.2295475150513,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 139.10479623700837,
-                                    "count": 18201,
-                                    "self": 1.507592360009994,
+                                    "total": 267.28082236993987,
+                                    "count": 36416,
+                                    "self": 3.1298786848901727,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 137.59720387699838,
-                                            "count": 18201,
-                                            "self": 31.747033853011885,
+                                            "total": 264.1509436850497,
+                                            "count": 36416,
+                                            "self": 56.354647853004735,
                                             "children": {
                                                 "TorchPolicy.sample_actions": {
-                                                    "total": 105.8501700239865,
-                                                    "count": 18201,
-                                                    "self": 105.8501700239865
+                                                    "total": 207.79629583204496,
+                                                    "count": 36416,
+                                                    "self": 207.79629583204496
                                                 }
                                             }
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 0.2673253319971991,
-                                    "count": 18201,
+                                    "total": 0.5262881870103229,
+                                    "count": 36416,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 462.6330918329977,
-                                            "count": 18201,
+                                            "total": 893.9885211770265,
+                                            "count": 36416,
                                             "is_parallel": true,
-                                            "self": 225.46361571399518,
+                                            "self": 425.1962783910244,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -224,48 +224,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.005653285999983382,
+                                                            "total": 0.0022482740000668855,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.003750213999865082,
+                                                            "self": 0.000785426001129963,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.0019030720001183,
+                                                                    "total": 0.0014628479989369225,
                                                                     "count": 10,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0019030720001183
+                                                                    "self": 0.0014628479989369225
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.03998361300000397,
+                                                            "total": 0.04437245400004031,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0003392470000562753,
+                                                            "self": 0.0005378729997573828,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.00032996599998114107,
+                                                                    "total": 0.00029277700014063157,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.00032996599998114107
+                                                                    "self": 0.00029277700014063157
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.038121620999959305,
+                                                                    "total": 0.041718575000231795,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.038121620999959305
+                                                                    "self": 0.041718575000231795
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.0011927790000072491,
+                                                                    "total": 0.0018232289999104978,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0002999450000515935,
+                                                                    "self": 0.0004162840004937607,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.0008928339999556556,
+                                                                            "total": 0.0014069449994167371,
                                                                             "count": 10,
                                                                             "is_parallel": true,
-                                                                            "self": 0.0008928339999556556
+                                                                            "self": 0.0014069449994167371
                                                                         }
                                                                     }
                                                                 }
@@ -274,34 +274,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 237.16947611900252,
-                                                    "count": 18200,
+                                                    "total": 468.79224278600213,
+                                                    "count": 36415,
                                                     "is_parallel": true,
-                                                    "self": 9.670628843984105,
+                                                    "self": 18.68105090993322,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 5.257173482006124,
-                                                            "count": 18200,
+                                                            "total": 10.327643597010137,
+                                                            "count": 36415,
                                                             "is_parallel": true,
-                                                            "self": 5.257173482006124
+                                                            "self": 10.327643597010137
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 191.08419032300617,
-                                                            "count": 18200,
+                                                            "total": 378.4170795610071,
+                                                            "count": 36415,
                                                             "is_parallel": true,
-                                                            "self": 191.08419032300617
+                                                            "self": 378.4170795610071
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 31.157483470006127,
-                                                            "count": 18200,
+                                                            "total": 61.36646871805169,
+                                                            "count": 36415,
                                                             "is_parallel": true,
-                                                            "self": 6.853875980982025,
+                                                            "self": 13.253275974245298,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 24.303607489024103,
-                                                                    "count": 182000,
+                                                                    "total": 48.113192743806394,
+                                                                    "count": 364150,
                                                                     "is_parallel": true,
-                                                                    "self": 24.303607489024103
+                                                                    "self": 48.113192743806394
                                                                 }
                                                             }
                                                         }
@@ -316,9 +316,9 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 0.00011884600007761037,
+                    "total": 0.00021788300000480376,
                     "count": 1,
-                    "self": 0.00011884600007761037,
+                    "self": 0.00021788300000480376,
                     "children": {
                         "thread_root": {
                             "total": 0.0,
@@ -327,36 +327,36 @@
                             "self": 0.0,
                             "children": {
                                 "trainer_advance": {
-                                    "total": 450.46718418102057,
-                                    "count": 406450,
+                                    "total": 879.8872030884322,
+                                    "count": 1007552,
                                     "is_parallel": true,
-                                    "self": 9.851221834996863,
+                                    "self": 24.59325653447786,
                                     "children": {
                                         "process_trajectory": {
-                                            "total": 257.4483959590234,
-                                            "count": 406450,
+                                            "total": 619.7395709079497,
+                                            "count": 1007552,
                                             "is_parallel": true,
-                                            "self": 256.35960615302326,
+                                            "self": 617.4357846219505,
                                             "children": {
                                                 "RLTrainer._checkpoint": {
-                                                    "total": 1.0887898060001362,
-                                                    "count": 4,
+                                                    "total": 2.3037862859991947,
+                                                    "count": 8,
                                                     "is_parallel": true,
-                                                    "self": 1.0887898060001362
+                                                    "self": 2.3037862859991947
                                                 }
                                             }
                                         },
                                         "_update_policy": {
-                                            "total": 183.1675663870003,
+                                            "total": 235.5543756460047,
                                             "count": 90,
                                             "is_parallel": true,
-                                            "self": 62.742893247002826,
+                                            "self": 115.87152756699288,
                                             "children": {
                                                 "TorchPPOOptimizer.update": {
-                                                    "total": 120.42467313999748,
+                                                    "total": 119.68284807901182,
                                                     "count": 4587,
                                                     "is_parallel": true,
-                                                    "self": 120.42467313999748
+                                                    "self": 119.68284807901182
                                                 }
                                             }
                                         }
@@ -367,14 +367,14 @@
                     }
                 },
                 "TrainerController._save_models": {
-                    "total": 0.1348954439999943,
+                    "total": 0.24024892100032957,
                     "count": 1,
-                    "self": 0.0010992370000622032,
+                    "self": 0.0022735880002073827,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.1337962069999321,
+                            "total": 0.2379753330001222,
                             "count": 1,
-                            "self": 0.1337962069999321
+                            "self": 0.2379753330001222
                         }
                     }
                 }

run_logs/training_status.json

@@ -3,57 +3,93 @@
         "checkpoints": [
             {
                 "steps": 49936,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.onnx",
-                "reward": 15.545454545454545,
-                "creation_time": 1677349381.2091355,
+                "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-49936.onnx",
+                "reward": 11.909090909090908,
+                "creation_time": 1677350985.2967446,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.pt"
+                    "results/SnowballTarget2/SnowballTarget/SnowballTarget-49936.pt"
                 ]
             },
             {
                 "steps": 99960,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.onnx",
-                "reward": 22.90909090909091,
-                "creation_time": 1677349497.1158938,
+                "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-99960.onnx",
+                "reward": 17.863636363636363,
+                "creation_time": 1677351096.4081423,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.pt"
+                    "results/SnowballTarget2/SnowballTarget/SnowballTarget-99960.pt"
                 ]
             },
             {
                 "steps": 149984,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.onnx",
-                "reward": 23.90909090909091,
-                "creation_time": 1677349610.0326517,
+                "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-149984.onnx",
+                "reward": 22.545454545454547,
+                "creation_time": 1677351207.7890575,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.pt"
+                    "results/SnowballTarget2/SnowballTarget/SnowballTarget-149984.pt"
                 ]
             },
             {
                 "steps": 199984,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.onnx",
-                "reward": 25.545454545454547,
-                "creation_time": 1677349722.8510551,
+                "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-199984.onnx",
+                "reward": 25.09090909090909,
+                "creation_time": 1677351318.6690974,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.pt"
+                    "results/SnowballTarget2/SnowballTarget/SnowballTarget-199984.pt"
                 ]
             },
             {
-                "steps": 200112,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.onnx",
-                "reward": 25.545454545454547,
-                "creation_time": 1677349723.022575,
+                "steps": 249944,
+                "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-249944.onnx",
+                "reward": 25.863636363636363,
+                "creation_time": 1677351429.8209236,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
+                    "results/SnowballTarget2/SnowballTarget/SnowballTarget-249944.pt"
+                ]
+            },
+            {
+                "steps": 299968,
+                "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-299968.onnx",
+                "reward": 27.181818181818183,
+                "creation_time": 1677351541.7408519,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget2/SnowballTarget/SnowballTarget-299968.pt"
+                ]
+            },
+            {
+                "steps": 349992,
+                "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-349992.onnx",
+                "reward": 26.09090909090909,
+                "creation_time": 1677351652.285872,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget2/SnowballTarget/SnowballTarget-349992.pt"
+                ]
+            },
+            {
+                "steps": 399992,
+                "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-399992.onnx",
+                "reward": 26.545454545454547,
+                "creation_time": 1677351762.2830489,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget2/SnowballTarget/SnowballTarget-399992.pt"
+                ]
+            },
+            {
+                "steps": 400312,
+                "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-400312.onnx",
+                "reward": 26.545454545454547,
+                "creation_time": 1677351762.599819,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget2/SnowballTarget/SnowballTarget-400312.pt"
                 ]
             }
         ],
         "final_checkpoint": {
-            "steps": 200112,
-            "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
-            "reward": 25.545454545454547,
-            "creation_time": 1677349723.022575,
+            "steps": 400312,
+            "file_path": "results/SnowballTarget2/SnowballTarget.onnx",
+            "reward": 26.545454545454547,
+            "creation_time": 1677351762.599819,
             "auxillary_file_paths": [
-                "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
+                "results/SnowballTarget2/SnowballTarget/SnowballTarget-400312.pt"
             ]
         }
     },