12M version with time_horizon=64

SoccerTwos.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16825e49773930dfe00693924997c7d2591ff44cf5e0983393ec726da66bf3b4
+oid sha256:918a2c27c5d62c9a53f8f4b811c76ee093491b3b203872164693c40766d62298
 size 1768747

SoccerTwos/SoccerTwos-12000026.onnx

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:16825e49773930dfe00693924997c7d2591ff44cf5e0983393ec726da66bf3b4
-size 1768747

SoccerTwos/SoccerTwos-12000026.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:0a6df846e156dc0cc37bc095d5576cb688ae6509b1c0320a89411fe666bb60dd
-size 28430025

SoccerTwos/{SoccerTwos-10999986.onnx → SoccerTwos-13499954.onnx}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3cb5347464566f8634e92daa79ec3911ca3b8cc45aaaeb275cd72b2ede1bad1c
+oid sha256:1b2052f8d86a5946f896dc520e5cea30aa0e31c6aa366d0d85c40c7cb225809a
 size 1768747

SoccerTwos/{SoccerTwos-11499948.pt → SoccerTwos-13499954.pt}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5fb9e8bd4b28fdb0d4eeb53baf8ff676a5085d2073e5531cab48559d2ae7b7eb
+oid sha256:a6a78dcab2d163e9b6354df76444f03935183478fb6db54dd7f86ce609799a1d
 size 28430025

SoccerTwos/{SoccerTwos-11499948.onnx → SoccerTwos-13999958.onnx}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e0b93e15c92d66fb38d71606eeb5c3c7a2dc5aedca6268285cba8bc626ea5258
+oid sha256:31e8b72917ae89b8906712f0dd49d9f761e4b4fa0b4032bf735931bf6a8dc5b4
 size 1768747

SoccerTwos/{SoccerTwos-10999986.pt → SoccerTwos-13999958.pt}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48c77d01d9ad7199dcc8cdf2a6b7b35fe77d4de14f770c3668da1440df8dad4a
+oid sha256:a4e8b7db79f8c24cd380c5cdc0e1b5be580fc41113717d60c21326039bb68ac0
 size 28430025

SoccerTwos/{SoccerTwos-11000064.onnx → SoccerTwos-14499976.onnx}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3cb5347464566f8634e92daa79ec3911ca3b8cc45aaaeb275cd72b2ede1bad1c
+oid sha256:e44e49d2b1e7b39ff6bb77172c338be2ff0c50c9e654f5856d886ffc6ac2e7df
 size 1768747

SoccerTwos/{SoccerTwos-11999998.pt → SoccerTwos-14499976.pt}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:552542b772789aad4c776676777b5a8d4ee71deec851516c50e209574ca9911e
+oid sha256:80fca7ff1ed92b06440b1238f36cb1a8da363c7d3a6a8d5526d75a94c83f900a
 size 28430025

SoccerTwos/{SoccerTwos-11999998.onnx → SoccerTwos-14999986.onnx}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16825e49773930dfe00693924997c7d2591ff44cf5e0983393ec726da66bf3b4
+oid sha256:918a2c27c5d62c9a53f8f4b811c76ee093491b3b203872164693c40766d62298
 size 1768747

SoccerTwos/{SoccerTwos-11000064.pt → SoccerTwos-14999986.pt}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16f493a665da1c00fedc02c91c7e2e6a6342a3aef25ba6395d27f7f89308e842
+oid sha256:f9454a01e8603f43a41818e57c01286ea5aac21edd5c6dfe95d09179ff912aa2
 size 28430025

SoccerTwos/SoccerTwos-15000040.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:918a2c27c5d62c9a53f8f4b811c76ee093491b3b203872164693c40766d62298
+size 1768747

SoccerTwos/SoccerTwos-15000040.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6bf8495605ed9303280307d317e2c0f40ea5f1d252475e96458c3da61b90253a
+size 28430025

SoccerTwos/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b727e843bdd5262b2a3bf11c996b8e174c51e738d7c132f954844163056569f
+oid sha256:0feb690952e6ec2331100bc22acb8a6ef55f4486c1299daf9a4ec88e68cafb51
 size 28428927

SoccerTwos/events.out.tfevents.1677779569.zippy.44044.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d52e6bf883d27c81e780ccbfd8f60e9a74377d81605ecfb3d06f0fba002a9cd
+size 1017775

SoccerTwos/events.out.tfevents.1678072392.zippy.56040.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa8b186cd0aa9d9371bf25f6f1f9b2f76796bd9c825a655885e24bd6f83a5605
+size 2034657

config.json

@@ -1 +1 @@
-{"default_settings": null, "behaviors": {"SoccerTwos": {"trainer_type": "poca", "hyperparameters": {"batch_size": 2048, "buffer_size": 20480, "learning_rate": 0.0001, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 5, "learning_rate_schedule": "constant", "beta_schedule": "constant", "epsilon_schedule": "constant"}, "checkpoint_interval": 500000, "network_settings": {"normalize": false, "hidden_units": 512, "num_layers": 2, "vis_encode_type": "simple", "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": 5, "even_checkpoints": false, "max_steps": 12000000, "time_horizon": 64, "summary_freq": 10000, "threaded": false, "self_play": {"save_steps": 50000, "team_change": 200000, "swap_steps": 2000, "window": 10, "play_against_latest_model_ratio": 0.5, "initial_elo": 1200.0}, "behavioral_cloning": null}}, "env_settings": {"env_path": "training-envs-executables\\SoccerTwos\\SoccerTwos.exe", "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": "SoccerTwos", "initialize_from": null, "load_model": false, "resume": true, "force": true, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
+{"default_settings": null, "behaviors": {"SoccerTwos": {"trainer_type": "poca", "hyperparameters": {"batch_size": 4096, "buffer_size": 60480, "learning_rate": 0.0001, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 5, "learning_rate_schedule": "constant", "beta_schedule": "constant", "epsilon_schedule": "constant"}, "checkpoint_interval": 500000, "network_settings": {"normalize": false, "hidden_units": 512, "num_layers": 2, "vis_encode_type": "simple", "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": 5, "even_checkpoints": false, "max_steps": 15000000, "time_horizon": 64, "summary_freq": 10000, "threaded": false, "self_play": {"save_steps": 50000, "team_change": 200000, "swap_steps": 2000, "window": 10, "play_against_latest_model_ratio": 0.5, "initial_elo": 1200.0}, "behavioral_cloning": null}}, "env_settings": {"env_path": "training-envs-executables\\SoccerTwos\\SoccerTwos.exe", "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": "SoccerTwos", "initialize_from": null, "load_model": false, "resume": true, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}

configuration.yaml

@@ -3,8 +3,8 @@ behaviors:
   SoccerTwos:
     trainer_type: poca
     hyperparameters:
-      batch_size: 2048
-      buffer_size: 20480
+      batch_size: 4096
+      buffer_size: 60480
       learning_rate: 0.0001
       beta: 0.005
       epsilon: 0.2
@@ -37,7 +37,7 @@ behaviors:
     init_path: null
     keep_checkpoints: 5
     even_checkpoints: false
-    max_steps: 12000000
+    max_steps: 15000000
     time_horizon: 64
     summary_freq: 10000
     threaded: false
@@ -73,7 +73,7 @@ checkpoint_settings:
   initialize_from: null
   load_model: false
   resume: true
-  force: true
+  force: false
   train_model: false
   inference: false
   results_dir: results

run_logs/Player-0.log

@@ -9,7 +9,7 @@ NullGfxDevice:
     Renderer: Null Device
     Vendor:   Unity Technologies
 Begin MonoManager ReloadAssembly
-- Completed reload, in  0.098 seconds
+- Completed reload, in  0.096 seconds
 ERROR: Shader Sprites/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 Microsoft Media Foundation video decoding to texture disabled: graphics device is Null, only Direct3D 11 and Direct3D 12 (only on desktop) are supported for hardware-accelerated video decoding.
 ERROR: Shader Sprites/Mask shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
@@ -35,7 +35,7 @@ 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: 0.634836 ms
+UnloadTime: 0.663212 ms
 Registered Communicator in Agent.
 ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 Setting up 4 worker threads for Enlighten.
@@ -43,7 +43,7 @@ Memory Statistics:
 [ALLOC_TEMP_TLS] TLS Allocator
   StackAllocators : 
     [ALLOC_TEMP_MAIN]
-      Peak usage frame count: [8.0 KB-16.0 KB]: 18783 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [8.0 KB-16.0 KB]: 37573 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
@@ -71,7 +71,7 @@ Memory Statistics:
     [ALLOC_TEMP_Job.Worker 0]
       Initial Block Size 256.0 KB
       Current Block Size 256.0 KB
-      Peak Allocated Bytes 488 B
+      Peak Allocated Bytes 0 B
       Overflow Count 0
     [ALLOC_TEMP_Background Job.Worker 10]
       Initial Block Size 32.0 KB
@@ -161,7 +161,7 @@ Memory Statistics:
     [ALLOC_TEMP_Job.Worker 2]
       Initial Block Size 256.0 KB
       Current Block Size 256.0 KB
-      Peak Allocated Bytes 0 B
+      Peak Allocated Bytes 488 B
       Overflow Count 0
     [ALLOC_TEMP_Background Job.Worker 3]
       Initial Block Size 32.0 KB
@@ -189,22 +189,22 @@ Memory Statistics:
       Peak Allocated Bytes 54 B
       Overflow Count 0
 [ALLOC_DEFAULT] Dual Thread Allocator
-  Peak main deferred allocation count 3
+  Peak main deferred allocation count 4
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
       Peak Allocated bytes 0.9 MB
     [ALLOC_DEFAULT_MAIN]
-      Peak usage frame count: [4.0 MB-8.0 MB]: 18784 frames
+      Peak usage frame count: [4.0 MB-8.0 MB]: 37574 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 4.9 MB
+      Peak Allocated memory 5.0 MB
       Peak Large allocation bytes 0 B
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 18784 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 37574 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 17.5 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
@@ -233,13 +233,13 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 0.9 MB
     [ALLOC_GFX_MAIN]
-      Peak usage frame count: [32.0 KB-64.0 KB]: 18783 frames, [64.0 KB-128.0 KB]: 1 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 37573 frames, [64.0 KB-128.0 KB]: 1 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 65.6 KB
       Peak Large allocation bytes 0 B
     [ALLOC_GFX_THREAD]
-      Peak usage frame count: [128.0 KB-256.0 KB]: 18784 frames
+      Peak usage frame count: [128.0 KB-256.0 KB]: 37574 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 173.6 KB
@@ -251,13 +251,13 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 0.9 MB
     [ALLOC_CACHEOBJECTS_MAIN]
-      Peak usage frame count: [0.5 MB-1.0 MB]: 18784 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 37574 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]: 18783 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 37573 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
@@ -269,13 +269,13 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 0.9 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 18784 frames
+      Peak usage frame count: [0-1.0 KB]: 37574 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]: 18783 frames, [2.0 KB-4.0 KB]: 1 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 37573 frames, [2.0 KB-4.0 KB]: 1 frames
       Requested Block Size 2.0 MB
       Peak Block count 1
       Peak Allocated memory 2.2 KB

run_logs/timers.json

@@ -2,305 +2,305 @@
     "name": "root",
     "gauges": {
         "SoccerTwos.Policy.Entropy.mean": {
-            "value": 1.3296939134597778,
-            "min": 1.2558366060256958,
-            "max": 1.3638432025909424,
-            "count": 100
+            "value": 1.4042199850082397,
+            "min": 1.293055772781372,
+            "max": 1.4382219314575195,
+            "count": 200
         },
         "SoccerTwos.Policy.Entropy.sum": {
-            "value": 26551.328125,
-            "min": 24682.359375,
-            "max": 28070.38671875,
-            "count": 100
+            "value": 28309.07421875,
+            "min": 25553.92578125,
+            "max": 29271.15234375,
+            "count": 200
         },
         "SoccerTwos.Environment.EpisodeLength.mean": {
-            "value": 65.50666666666666,
-            "min": 40.69747899159664,
-            "max": 76.53225806451613,
-            "count": 100
+            "value": 64.6125,
+            "min": 43.6605504587156,
+            "max": 78.015625,
+            "count": 200
         },
         "SoccerTwos.Environment.EpisodeLength.sum": {
-            "value": 19652.0,
-            "min": 17372.0,
-            "max": 21752.0,
-            "count": 100
+            "value": 20676.0,
+            "min": 17108.0,
+            "max": 21996.0,
+            "count": 200
         },
         "SoccerTwos.Self-play.ELO.mean": {
-            "value": 1666.3319288516852,
-            "min": 1611.3660763682876,
-            "max": 1679.8709732967384,
-            "count": 100
+            "value": 1668.9076514814558,
+            "min": 1636.8585446070267,
+            "max": 1692.9523803989568,
+            "count": 200
         },
         "SoccerTwos.Self-play.ELO.sum": {
-            "value": 249949.78932775278,
-            "min": 204869.3990160037,
-            "max": 394426.6732712473,
-            "count": 100
+            "value": 267025.22423703293,
+            "min": 214323.2614478224,
+            "max": 360276.8555171805,
+            "count": 200
         },
         "SoccerTwos.Step.mean": {
-            "value": 11999998.0,
-            "min": 11009986.0,
-            "max": 11999998.0,
-            "count": 100
+            "value": 14999986.0,
+            "min": 13009988.0,
+            "max": 14999986.0,
+            "count": 200
         },
         "SoccerTwos.Step.sum": {
-            "value": 11999998.0,
-            "min": 11009986.0,
-            "max": 11999998.0,
-            "count": 100
+            "value": 14999986.0,
+            "min": 13009988.0,
+            "max": 14999986.0,
+            "count": 200
         },
         "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
-            "value": 0.03318590298295021,
-            "min": -0.09402157366275787,
-            "max": 0.06818799674510956,
-            "count": 100
+            "value": 0.004000318236649036,
+            "min": -0.08737442642450333,
+            "max": 0.03684547543525696,
+            "count": 200
         },
         "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
-            "value": 7.732315540313721,
-            "min": -23.12930679321289,
-            "max": 17.524314880371094,
-            "count": 100
+            "value": 0.976077675819397,
+            "min": -23.15422248840332,
+            "max": 9.432441711425781,
+            "count": 200
         },
         "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
-            "value": 0.032004907727241516,
-            "min": -0.09568411856889725,
-            "max": 0.06986971199512482,
-            "count": 100
+            "value": 0.004686075262725353,
+            "min": -0.08682207763195038,
+            "max": 0.03757215291261673,
+            "count": 200
         },
         "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
-            "value": 7.457143783569336,
-            "min": -23.538293838500977,
-            "max": 17.95651626586914,
-            "count": 100
+            "value": 1.143402338027954,
+            "min": -23.007850646972656,
+            "max": 9.618471145629883,
+            "count": 200
         },
         "SoccerTwos.Environment.CumulativeReward.mean": {
             "value": 0.0,
             "min": 0.0,
             "max": 0.0,
-            "count": 100
+            "count": 200
         },
         "SoccerTwos.Environment.CumulativeReward.sum": {
             "value": 0.0,
             "min": 0.0,
             "max": 0.0,
-            "count": 100
+            "count": 200
         },
         "SoccerTwos.Policy.ExtrinsicReward.mean": {
-            "value": -0.034629729953972066,
-            "min": -0.3322632901276214,
-            "max": 0.20096383132833115,
-            "count": 100
+            "value": -0.011927046116043187,
+            "min": -0.43548677270374603,
+            "max": 0.21293473682905498,
+            "count": 200
         },
         "SoccerTwos.Policy.ExtrinsicReward.sum": {
-            "value": -5.125200033187866,
-            "min": -53.08120012283325,
-            "max": 37.78120028972626,
-            "count": 100
+            "value": -1.8964003324508667,
+            "min": -82.307000041008,
+            "max": 40.45759999752045,
+            "count": 200
         },
         "SoccerTwos.Environment.GroupCumulativeReward.mean": {
-            "value": -0.034629729953972066,
-            "min": -0.3322632901276214,
-            "max": 0.20096383132833115,
-            "count": 100
+            "value": -0.011927046116043187,
+            "min": -0.43548677270374603,
+            "max": 0.21293473682905498,
+            "count": 200
         },
         "SoccerTwos.Environment.GroupCumulativeReward.sum": {
-            "value": -5.125200033187866,
-            "min": -53.08120012283325,
-            "max": 37.78120028972626,
-            "count": 100
+            "value": -1.8964003324508667,
+            "min": -82.307000041008,
+            "max": 40.45759999752045,
+            "count": 200
         },
         "SoccerTwos.IsTraining.mean": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 100
+            "count": 200
         },
         "SoccerTwos.IsTraining.sum": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 100
+            "count": 200
         },
         "SoccerTwos.Losses.PolicyLoss.mean": {
-            "value": 0.015466055430006237,
-            "min": 0.013723419256857597,
-            "max": 0.02158118949351774,
-            "count": 48
+            "value": 0.012564142516514819,
+            "min": 0.010396268464994916,
+            "max": 0.016108207605014156,
+            "count": 33
         },
         "SoccerTwos.Losses.PolicyLoss.sum": {
-            "value": 0.015466055430006237,
-            "min": 0.013723419256857597,
-            "max": 0.02158118949351774,
-            "count": 48
+            "value": 0.012564142516514819,
+            "min": 0.010396268464994916,
+            "max": 0.016108207605014156,
+            "count": 33
         },
         "SoccerTwos.Losses.ValueLoss.mean": {
-            "value": 0.09763547152280808,
-            "min": 0.08508114889264107,
-            "max": 0.11397679463028908,
-            "count": 48
+            "value": 0.10362269473927362,
+            "min": 0.09285751815353122,
+            "max": 0.10667744055390357,
+            "count": 33
         },
         "SoccerTwos.Losses.ValueLoss.sum": {
-            "value": 0.09763547152280808,
-            "min": 0.08508114889264107,
-            "max": 0.11397679463028908,
-            "count": 48
+            "value": 0.10362269473927362,
+            "min": 0.09285751815353122,
+            "max": 0.10667744055390357,
+            "count": 33
         },
         "SoccerTwos.Losses.BaselineLoss.mean": {
-            "value": 0.09956647798419,
-            "min": 0.0870664346218109,
-            "max": 0.11500901088118554,
-            "count": 48
+            "value": 0.10464463659695217,
+            "min": 0.09364987217954227,
+            "max": 0.10800226320113454,
+            "count": 33
         },
         "SoccerTwos.Losses.BaselineLoss.sum": {
-            "value": 0.09956647798419,
-            "min": 0.0870664346218109,
-            "max": 0.11500901088118554,
-            "count": 48
+            "value": 0.10464463659695217,
+            "min": 0.09364987217954227,
+            "max": 0.10800226320113454,
+            "count": 33
         },
         "SoccerTwos.Policy.LearningRate.mean": {
-            "value": 0.00010000000000000002,
-            "min": 0.00010000000000000002,
-            "max": 0.00010000000000000002,
-            "count": 48
+            "value": 0.00010000000000000005,
+            "min": 0.00010000000000000005,
+            "max": 0.00010000000000000005,
+            "count": 33
         },
         "SoccerTwos.Policy.LearningRate.sum": {
-            "value": 0.00010000000000000002,
-            "min": 0.00010000000000000002,
-            "max": 0.00010000000000000002,
-            "count": 48
+            "value": 0.00010000000000000005,
+            "min": 0.00010000000000000005,
+            "max": 0.00010000000000000005,
+            "count": 33
         },
         "SoccerTwos.Policy.Epsilon.mean": {
-            "value": 0.19999999999999996,
-            "min": 0.19999999999999996,
-            "max": 0.19999999999999996,
-            "count": 48
+            "value": 0.19999999999999993,
+            "min": 0.19999999999999993,
+            "max": 0.19999999999999993,
+            "count": 33
         },
         "SoccerTwos.Policy.Epsilon.sum": {
-            "value": 0.19999999999999996,
-            "min": 0.19999999999999996,
-            "max": 0.19999999999999996,
-            "count": 48
+            "value": 0.19999999999999993,
+            "min": 0.19999999999999993,
+            "max": 0.19999999999999993,
+            "count": 33
         },
         "SoccerTwos.Policy.Beta.mean": {
             "value": 0.005,
             "min": 0.005,
             "max": 0.005,
-            "count": 48
+            "count": 33
         },
         "SoccerTwos.Policy.Beta.sum": {
             "value": 0.005,
             "min": 0.005,
             "max": 0.005,
-            "count": 48
+            "count": 33
         }
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1677773145",
+        "start_time_seconds": "1678072388",
         "python_version": "3.8.16 (default, Jan 17 2023, 22:25:28) [MSC v.1916 64 bit (AMD64)]",
-        "command_line_arguments": "C:\\Users\\Alex\\.conda\\envs\\rl\\Scripts\\mlagents-learn config\\poca\\SoccerTwos.yaml --env=training-envs-executables\\SoccerTwos\\SoccerTwos.exe --run-id SoccerTwos --no-graphics --resume --force",
+        "command_line_arguments": "C:\\Users\\Alex\\.conda\\envs\\rl\\Scripts\\mlagents-learn config\\poca\\SoccerTwos-v4.yaml --env=training-envs-executables\\SoccerTwos\\SoccerTwos.exe --run-id SoccerTwos --no-graphics --resume",
         "mlagents_version": "0.31.0.dev0",
         "mlagents_envs_version": "0.31.0.dev0",
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "1.13.1+cpu",
         "numpy_version": "1.21.2",
-        "end_time_seconds": "1677777955"
+        "end_time_seconds": "1678081434"
     },
-    "total": 4810.345773465,
+    "total": 9046.199773536,
     "count": 1,
-    "self": 1.0880586809998931,
+    "self": 0.9137066639996192,
     "children": {
         "run_training.setup": {
-            "total": 0.19250748500000014,
+            "total": 0.19324344800000004,
             "count": 1,
-            "self": 0.19250748500000014
+            "self": 0.19324344800000004
         },
         "TrainerController.start_learning": {
-            "total": 4809.065207299001,
+            "total": 9045.092823424,
             "count": 1,
-            "self": 1.9539889190127724,
+            "self": 3.7986713958616747,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 4.351995644000391,
-                    "count": 6,
-                    "self": 4.351995644000391
+                    "total": 4.305402356000544,
+                    "count": 11,
+                    "self": 4.305402356000544
                 },
                 "TrainerController.advance": {
-                    "total": 4802.611504250987,
-                    "count": 69580,
-                    "self": 1.7038131230092404,
+                    "total": 9036.85224843614,
+                    "count": 138518,
+                    "self": 3.5654074349095026,
                     "children": {
                         "env_step": {
-                            "total": 1373.0210131730128,
-                            "count": 69580,
-                            "self": 1095.0976368799998,
+                            "total": 2626.656758978248,
+                            "count": 138518,
+                            "self": 2107.992004035367,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 276.7358293300265,
-                                    "count": 69580,
-                                    "self": 9.667499210084316,
+                                    "total": 516.4043758059379,
+                                    "count": 138518,
+                                    "self": 17.642061351648408,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 267.0683301199422,
-                                            "count": 125222,
-                                            "self": 267.0683301199422
+                                            "total": 498.7623144542895,
+                                            "count": 250490,
+                                            "self": 498.7623144542895
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 1.1875469629863824,
-                                    "count": 69580,
+                                    "total": 2.260379136943383,
+                                    "count": 138518,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 4802.093405757969,
-                                            "count": 69580,
+                                            "total": 9035.68225249306,
+                                            "count": 138518,
                                             "is_parallel": true,
-                                            "self": 3936.159652096942,
+                                            "self": 7362.317537728006,
                                             "children": {
                                                 "steps_from_proto": {
-                                                    "total": 0.013614713999716699,
-                                                    "count": 12,
+                                                    "total": 0.023604251000842957,
+                                                    "count": 22,
                                                     "is_parallel": true,
-                                                    "self": 0.0025973019984686374,
+                                                    "self": 0.004707087003883004,
                                                     "children": {
                                                         "_process_rank_one_or_two_observation": {
-                                                            "total": 0.011017412001248061,
-                                                            "count": 48,
+                                                            "total": 0.018897163996959954,
+                                                            "count": 88,
                                                             "is_parallel": true,
-                                                            "self": 0.011017412001248061
+                                                            "self": 0.018897163996959954
                                                         }
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 865.9201389470272,
-                                                    "count": 69580,
+                                                    "total": 1673.3411105140528,
+                                                    "count": 138518,
                                                     "is_parallel": true,
-                                                    "self": 44.27732952806309,
+                                                    "self": 86.05551599335627,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 38.828463008995676,
-                                                            "count": 69580,
+                                                            "total": 77.13198323072854,
+                                                            "count": 138518,
                                                             "is_parallel": true,
-                                                            "self": 38.828463008995676
+                                                            "self": 77.13198323072854
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 617.6617590909752,
-                                                            "count": 69580,
+                                                            "total": 1189.5078526219468,
+                                                            "count": 138518,
                                                             "is_parallel": true,
-                                                            "self": 617.6617590909752
+                                                            "self": 1189.5078526219468
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 165.1525873189933,
-                                                            "count": 139160,
+                                                            "total": 320.64575866802124,
+                                                            "count": 277036,
                                                             "is_parallel": true,
-                                                            "self": 32.38739103698765,
+                                                            "self": 62.269651478218236,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 132.76519628200566,
-                                                                    "count": 556640,
+                                                                    "total": 258.376107189803,
+                                                                    "count": 1108144,
                                                                     "is_parallel": true,
-                                                                    "self": 132.76519628200566
+                                                                    "self": 258.376107189803
                                                                 }
                                                             }
                                                         }
@@ -313,31 +313,31 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 3427.8866779549653,
-                            "count": 69580,
-                            "self": 11.278970307023883,
+                            "total": 6406.6300820229835,
+                            "count": 138518,
+                            "self": 21.63106259284268,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 431.0246229039416,
-                                    "count": 69580,
-                                    "self": 430.6338560709422,
+                                    "total": 773.9861642271401,
+                                    "count": 138518,
+                                    "self": 773.2951902501411,
                                     "children": {
                                         "RLTrainer._checkpoint": {
-                                            "total": 0.3907668329993612,
-                                            "count": 2,
-                                            "self": 0.3907668329993612
+                                            "total": 0.6909739769989756,
+                                            "count": 4,
+                                            "self": 0.6909739769989756
                                         }
                                     }
                                 },
                                 "_update_policy": {
-                                    "total": 2985.5830847439997,
-                                    "count": 48,
-                                    "self": 324.9459118260056,
+                                    "total": 5611.012855203001,
+                                    "count": 33,
+                                    "self": 631.9241372250062,
                                     "children": {
                                         "TorchPOCAOptimizer.update": {
-                                            "total": 2660.637172917994,
-                                            "count": 2400,
-                                            "self": 2660.637172917994
+                                            "total": 4979.088717977995,
+                                            "count": 2310,
+                                            "self": 4979.088717977995
                                         }
                                     }
                                 }
@@ -346,19 +346,19 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 1.207999957841821e-06,
+                    "total": 1.5099994925549254e-06,
                     "count": 1,
-                    "self": 1.207999957841821e-06
+                    "self": 1.5099994925549254e-06
                 },
                 "TrainerController._save_models": {
-                    "total": 0.1477172770000834,
+                    "total": 0.13649972599887406,
                     "count": 1,
-                    "self": 0.0026857530001507257,
+                    "self": 0.0022806409979239106,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.1450315239999327,
+                            "total": 0.13421908500095014,
                             "count": 1,
-                            "self": 0.1450315239999327
+                            "self": 0.13421908500095014
                         }
                     }
                 }

run_logs/training_status.json

@@ -2,59 +2,59 @@
     "SoccerTwos": {
         "checkpoints": [
             {
-                "steps": 10999986,
-                "file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-10999986.onnx",
+                "steps": 13499954,
+                "file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-13499954.onnx",
                 "reward": 0.0,
-                "creation_time": 1677772694.0401971,
+                "creation_time": 1678074646.290517,
                 "auxillary_file_paths": [
-                    "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-10999986.pt"
+                    "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-13499954.pt"
                 ]
             },
             {
-                "steps": 11000064,
-                "file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-11000064.onnx",
+                "steps": 13999958,
+                "file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-13999958.onnx",
                 "reward": 0.0,
-                "creation_time": 1677772694.1902058,
+                "creation_time": 1678076862.6602862,
                 "auxillary_file_paths": [
-                    "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-11000064.pt"
+                    "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-13999958.pt"
                 ]
             },
             {
-                "steps": 11499948,
-                "file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-11499948.onnx",
+                "steps": 14499976,
+                "file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-14499976.onnx",
                 "reward": 0.0,
-                "creation_time": 1677775552.383685,
+                "creation_time": 1678079063.1011443,
                 "auxillary_file_paths": [
-                    "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-11499948.pt"
+                    "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-14499976.pt"
                 ]
             },
             {
-                "steps": 11999998,
-                "file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-11999998.onnx",
+                "steps": 14999986,
+                "file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-14999986.onnx",
                 "reward": 0.0,
-                "creation_time": 1677777954.7170906,
+                "creation_time": 1678081433.7117352,
                 "auxillary_file_paths": [
-                    "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-11999998.pt"
+                    "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-14999986.pt"
                 ]
             },
             {
-                "steps": 12000026,
-                "file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-12000026.onnx",
+                "steps": 15000040,
+                "file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-15000040.onnx",
                 "reward": 0.0,
-                "creation_time": 1677777954.8851004,
+                "creation_time": 1678081433.8697443,
                 "auxillary_file_paths": [
-                    "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-12000026.pt"
+                    "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-15000040.pt"
                 ]
             }
         ],
-        "elo": 1661.777301461853,
+        "elo": 1671.9185764472822,
         "final_checkpoint": {
-            "steps": 12000026,
+            "steps": 15000040,
             "file_path": "results\\SoccerTwos\\SoccerTwos.onnx",
             "reward": 0.0,
-            "creation_time": 1677777954.8851004,
+            "creation_time": 1678081433.8697443,
             "auxillary_file_paths": [
-                "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-12000026.pt"
+                "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-15000040.pt"
             ]
         }
     },