Hugging Face's logo

figurek1m
/
ppo-SnowballTarget

Reinforcement Learning
ml-agents
TensorBoard
ONNX
SnowballTarget
deep-reinforcement-learning
ML-Agents-SnowballTarget
Model card Files Metrics Community
figurek1m commited on
Commit
cf141df
·
verified ·
1 Parent(s): 874c5ef

First Push

Browse files
Files changed (10) hide show
  1. SnowballTarget.onnx +2 -2
  2. SnowballTarget/SnowballTarget-7304.onnx +3 -0
  3. SnowballTarget/SnowballTarget-7304.pt +3 -0
  4. SnowballTarget/checkpoint.pt +2 -2
  5. SnowballTarget/events.out.tfevents.1741746368.8bba9a8a1fb9.5814.0 +3 -0
  6. config.json +1 -1
  7. configuration.yaml +3 -3
  8. run_logs/Player-0.log +15 -18
  9. run_logs/timers.json +69 -234
  10. run_logs/training_status.json +10 -46
SnowballTarget.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e29c4374cef7edfdfa62b22bd8930f5ed16cb463b529c11d57701d630a13987a
3
- size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d3c1b10eea4f24ec233406ea91ee17e5a784a40eb1dd366d5ec187df18e0026
3
+ size 649740
SnowballTarget/SnowballTarget-7304.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d3c1b10eea4f24ec233406ea91ee17e5a784a40eb1dd366d5ec187df18e0026
3
+ size 649740
SnowballTarget/SnowballTarget-7304.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:12a7e9c4e93fd988e42c836a891e19200c0a9086afe2b7b06bf7b9fe5556729a
3
+ size 1286229
SnowballTarget/checkpoint.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:247f85612b7d45447d71edcb9d117a8c8428d8bb87df52a0566c8537be314aef
3
- size 3849250
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be48abe216ba90c24f20e121d4289c002597de12a869898730986c98715e81bc
3
+ size 1285986
SnowballTarget/events.out.tfevents.1741746368.8bba9a8a1fb9.5814.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7083d7f6e8abb86b12624cd89059479c2a9fb91e285579af0c52109904d3066d
3
+ size 1116
config.json CHANGED
@@ -1 +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, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 50000, "network_settings": {"normalize": false, "hidden_units": 256, "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": 10, "even_checkpoints": false, "max_steps": 200000, "time_horizon": 64, "summary_freq": 10000, "threaded": false, "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, "timeout_wait": 60, "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, "no_graphics_monitor": false}, "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}
 
1
+ {"default_settings": null, "behaviors": {"SnowballTarget": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 512, "buffer_size": 10240, "learning_rate": 0.0003, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 50000, "network_settings": {"normalize": false, "hidden_units": 256, "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": 10, "even_checkpoints": false, "max_steps": 200000, "time_horizon": 64, "summary_freq": 10000, "threaded": false, "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, "timeout_wait": 60, "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, "no_graphics_monitor": false}, "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 CHANGED
@@ -3,8 +3,8 @@ behaviors:
3
  SnowballTarget:
4
  trainer_type: ppo
5
  hyperparameters:
6
- batch_size: 128
7
- buffer_size: 2048
8
  learning_rate: 0.0003
9
  beta: 0.005
10
  epsilon: 0.2
@@ -66,7 +66,7 @@ engine_settings:
66
  no_graphics_monitor: false
67
  environment_parameters: null
68
  checkpoint_settings:
69
- run_id: SnowballTarget1
70
  initialize_from: null
71
  load_model: false
72
  resume: false
 
3
  SnowballTarget:
4
  trainer_type: ppo
5
  hyperparameters:
6
+ batch_size: 512
7
+ buffer_size: 10240
8
  learning_rate: 0.0003
9
  beta: 0.005
10
  epsilon: 0.2
 
66
  no_graphics_monitor: false
67
  environment_parameters: null
68
  checkpoint_settings:
69
+ run_id: SnowballTarget2
70
  initialize_from: null
71
  load_model: false
72
  resume: false
run_logs/Player-0.log CHANGED
@@ -2,9 +2,6 @@ Mono path[0] = '/content/ml-agents/training-envs-executables/linux/SnowballTarge
2
  Mono config path = '/content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/MonoBleedingEdge/etc'
3
  Preloaded 'lib_burst_generated.so'
4
  Preloaded 'libgrpc_csharp_ext.x64.so'
5
- PlayerPrefs - Creating folder: /root/.config/unity3d/Hugging Face
6
- PlayerPrefs - Creating folder: /root/.config/unity3d/Hugging Face/SnowballTarget
7
- Unable to load player prefs
8
  Initialize engine version: 2021.3.14f1 (eee1884e7226)
9
  [Subsystems] Discovering subsystems at path /content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/UnitySubsystems
10
  Forcing GfxDevice: Null
@@ -34,7 +31,7 @@ ALSA lib pcm.c:2664:(snd_pcm_open_noupdate) Unknown PCM default
34
  FMOD failed to initialize the output device.: "Error initializing output device. " (60)
35
  FMOD initialized on nosound output
36
  Begin MonoManager ReloadAssembly
37
- - Completed reload, in 0.157 seconds
38
  ERROR: Shader Sprites/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
39
  ERROR: Shader Sprites/Mask shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
40
  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
45
  WARNING: Shader Unsupported: 'Standard' - All subshaders removed
46
  WARNING: Shader Did you use #pragma only_renderers and omit this platform?
47
  WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
48
- UnloadTime: 1.392721 ms
49
  ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
50
  requesting resize 84 x 84
51
  Setting up 1 worker threads for Enlighten.
@@ -53,7 +50,7 @@ Memory Statistics:
53
  [ALLOC_TEMP_TLS] TLS Allocator
54
  StackAllocators :
55
  [ALLOC_TEMP_MAIN]
56
- Peak usage frame count: [8.0 KB-16.0 KB]: 5367 frames, [16.0 KB-32.0 KB]: 90 frames, [2.0 MB-4.0 MB]: 1 frames
57
  Initial Block Size 4.0 MB
58
  Current Block Size 4.0 MB
59
  Peak Allocated Bytes 2.0 MB
@@ -169,22 +166,22 @@ Memory Statistics:
169
  Peak Allocated Bytes 0 B
170
  Overflow Count 0
171
  [ALLOC_DEFAULT] Dual Thread Allocator
172
- Peak main deferred allocation count 40
173
  [ALLOC_BUCKET]
174
  Large Block size 4.0 MB
175
  Used Block count 1
176
  Peak Allocated bytes 1.0 MB
177
  [ALLOC_DEFAULT_MAIN]
178
- Peak usage frame count: [4.0 MB-8.0 MB]: 5458 frames
179
  Requested Block Size 16.0 MB
180
  Peak Block count 1
181
- Peak Allocated memory 6.7 MB
182
  Peak Large allocation bytes 0 B
183
  [ALLOC_DEFAULT_THREAD]
184
- Peak usage frame count: [16.0 MB-32.0 MB]: 5458 frames
185
  Requested Block Size 16.0 MB
186
  Peak Block count 1
187
- Peak Allocated memory 17.7 MB
188
  Peak Large allocation bytes 16.0 MB
189
  [ALLOC_TEMP_JOB_1_FRAME]
190
  Initial Block Size 2.0 MB
@@ -213,13 +210,13 @@ Memory Statistics:
213
  Used Block count 1
214
  Peak Allocated bytes 1.0 MB
215
  [ALLOC_GFX_MAIN]
216
- Peak usage frame count: [32.0 KB-64.0 KB]: 4995 frames, [64.0 KB-128.0 KB]: 463 frames
217
  Requested Block Size 16.0 MB
218
  Peak Block count 1
219
- Peak Allocated memory 66.0 KB
220
  Peak Large allocation bytes 0 B
221
  [ALLOC_GFX_THREAD]
222
- Peak usage frame count: [32.0 KB-64.0 KB]: 5458 frames
223
  Requested Block Size 16.0 MB
224
  Peak Block count 1
225
  Peak Allocated memory 39.6 KB
@@ -231,13 +228,13 @@ Memory Statistics:
231
  Used Block count 1
232
  Peak Allocated bytes 1.0 MB
233
  [ALLOC_CACHEOBJECTS_MAIN]
234
- Peak usage frame count: [0.5 MB-1.0 MB]: 5458 frames
235
  Requested Block Size 4.0 MB
236
  Peak Block count 1
237
  Peak Allocated memory 0.6 MB
238
  Peak Large allocation bytes 0 B
239
  [ALLOC_CACHEOBJECTS_THREAD]
240
- Peak usage frame count: [0.5 MB-1.0 MB]: 5457 frames, [2.0 MB-4.0 MB]: 1 frames
241
  Requested Block Size 4.0 MB
242
  Peak Block count 1
243
  Peak Allocated memory 2.2 MB
@@ -249,13 +246,13 @@ Memory Statistics:
249
  Used Block count 1
250
  Peak Allocated bytes 1.0 MB
251
  [ALLOC_TYPETREE_MAIN]
252
- Peak usage frame count: [0-1.0 KB]: 5458 frames
253
  Requested Block Size 2.0 MB
254
  Peak Block count 1
255
  Peak Allocated memory 1.0 KB
256
  Peak Large allocation bytes 0 B
257
  [ALLOC_TYPETREE_THREAD]
258
- Peak usage frame count: [1.0 KB-2.0 KB]: 5458 frames
259
  Requested Block Size 2.0 MB
260
  Peak Block count 1
261
  Peak Allocated memory 1.7 KB
 
2
  Mono config path = '/content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/MonoBleedingEdge/etc'
3
  Preloaded 'lib_burst_generated.so'
4
  Preloaded 'libgrpc_csharp_ext.x64.so'
 
 
 
5
  Initialize engine version: 2021.3.14f1 (eee1884e7226)
6
  [Subsystems] Discovering subsystems at path /content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/UnitySubsystems
7
  Forcing GfxDevice: Null
 
31
  FMOD failed to initialize the output device.: "Error initializing output device. " (60)
32
  FMOD initialized on nosound output
33
  Begin MonoManager ReloadAssembly
34
+ - Completed reload, in 0.092 seconds
35
  ERROR: Shader Sprites/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
36
  ERROR: Shader Sprites/Mask shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
37
  ERROR: Shader Legacy Shaders/VertexLit shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 
42
  WARNING: Shader Unsupported: 'Standard' - All subshaders removed
43
  WARNING: Shader Did you use #pragma only_renderers and omit this platform?
44
  WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
45
+ UnloadTime: 0.759224 ms
46
  ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
47
  requesting resize 84 x 84
48
  Setting up 1 worker threads for Enlighten.
 
50
  [ALLOC_TEMP_TLS] TLS Allocator
51
  StackAllocators :
52
  [ALLOC_TEMP_MAIN]
53
+ Peak usage frame count: [8.0 KB-16.0 KB]: 204 frames, [16.0 KB-32.0 KB]: 3 frames, [2.0 MB-4.0 MB]: 1 frames
54
  Initial Block Size 4.0 MB
55
  Current Block Size 4.0 MB
56
  Peak Allocated Bytes 2.0 MB
 
166
  Peak Allocated Bytes 0 B
167
  Overflow Count 0
168
  [ALLOC_DEFAULT] Dual Thread Allocator
169
+ Peak main deferred allocation count 32
170
  [ALLOC_BUCKET]
171
  Large Block size 4.0 MB
172
  Used Block count 1
173
  Peak Allocated bytes 1.0 MB
174
  [ALLOC_DEFAULT_MAIN]
175
+ Peak usage frame count: [4.0 MB-8.0 MB]: 208 frames
176
  Requested Block Size 16.0 MB
177
  Peak Block count 1
178
+ Peak Allocated memory 5.2 MB
179
  Peak Large allocation bytes 0 B
180
  [ALLOC_DEFAULT_THREAD]
181
+ Peak usage frame count: [16.0 MB-32.0 MB]: 208 frames
182
  Requested Block Size 16.0 MB
183
  Peak Block count 1
184
+ Peak Allocated memory 17.8 MB
185
  Peak Large allocation bytes 16.0 MB
186
  [ALLOC_TEMP_JOB_1_FRAME]
187
  Initial Block Size 2.0 MB
 
210
  Used Block count 1
211
  Peak Allocated bytes 1.0 MB
212
  [ALLOC_GFX_MAIN]
213
+ Peak usage frame count: [32.0 KB-64.0 KB]: 191 frames, [64.0 KB-128.0 KB]: 17 frames
214
  Requested Block Size 16.0 MB
215
  Peak Block count 1
216
+ Peak Allocated memory 65.6 KB
217
  Peak Large allocation bytes 0 B
218
  [ALLOC_GFX_THREAD]
219
+ Peak usage frame count: [32.0 KB-64.0 KB]: 208 frames
220
  Requested Block Size 16.0 MB
221
  Peak Block count 1
222
  Peak Allocated memory 39.6 KB
 
228
  Used Block count 1
229
  Peak Allocated bytes 1.0 MB
230
  [ALLOC_CACHEOBJECTS_MAIN]
231
+ Peak usage frame count: [0.5 MB-1.0 MB]: 208 frames
232
  Requested Block Size 4.0 MB
233
  Peak Block count 1
234
  Peak Allocated memory 0.6 MB
235
  Peak Large allocation bytes 0 B
236
  [ALLOC_CACHEOBJECTS_THREAD]
237
+ Peak usage frame count: [0.5 MB-1.0 MB]: 207 frames, [2.0 MB-4.0 MB]: 1 frames
238
  Requested Block Size 4.0 MB
239
  Peak Block count 1
240
  Peak Allocated memory 2.2 MB
 
246
  Used Block count 1
247
  Peak Allocated bytes 1.0 MB
248
  [ALLOC_TYPETREE_MAIN]
249
+ Peak usage frame count: [0-1.0 KB]: 208 frames
250
  Requested Block Size 2.0 MB
251
  Peak Block count 1
252
  Peak Allocated memory 1.0 KB
253
  Peak Large allocation bytes 0 B
254
  [ALLOC_TYPETREE_THREAD]
255
+ Peak usage frame count: [1.0 KB-2.0 KB]: 208 frames
256
  Requested Block Size 2.0 MB
257
  Peak Block count 1
258
  Peak Allocated memory 1.7 KB
run_logs/timers.json CHANGED
@@ -1,214 +1,68 @@
1
  {
2
  "name": "root",
3
- "gauges": {
4
- "SnowballTarget.Policy.Entropy.mean": {
5
- "value": 0.8420787453651428,
6
- "min": 0.8420787453651428,
7
- "max": 2.8625736236572266,
8
- "count": 20
9
- },
10
- "SnowballTarget.Policy.Entropy.sum": {
11
- "value": 8003.1162109375,
12
- "min": 8003.1162109375,
13
- "max": 29221.15234375,
14
- "count": 20
15
- },
16
- "SnowballTarget.Step.mean": {
17
- "value": 199984.0,
18
- "min": 9952.0,
19
- "max": 199984.0,
20
- "count": 20
21
- },
22
- "SnowballTarget.Step.sum": {
23
- "value": 199984.0,
24
- "min": 9952.0,
25
- "max": 199984.0,
26
- "count": 20
27
- },
28
- "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
- "value": 13.228395462036133,
30
- "min": 0.5035557150840759,
31
- "max": 13.228395462036133,
32
- "count": 20
33
- },
34
- "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
- "value": 2579.537109375,
36
- "min": 97.68980407714844,
37
- "max": 2695.68212890625,
38
- "count": 20
39
- },
40
- "SnowballTarget.Losses.PolicyLoss.mean": {
41
- "value": 0.06904638772710528,
42
- "min": 0.06166020506894783,
43
- "max": 0.07373721250926382,
44
- "count": 20
45
- },
46
- "SnowballTarget.Losses.PolicyLoss.sum": {
47
- "value": 0.2761855509084211,
48
- "min": 0.25503849752610275,
49
- "max": 0.3686860625463191,
50
- "count": 20
51
- },
52
- "SnowballTarget.Losses.ValueLoss.mean": {
53
- "value": 0.20142870871167556,
54
- "min": 0.14005450415425003,
55
- "max": 0.28048249564918815,
56
- "count": 20
57
- },
58
- "SnowballTarget.Losses.ValueLoss.sum": {
59
- "value": 0.8057148348467023,
60
- "min": 0.5602180166170001,
61
- "max": 1.4024124782459408,
62
- "count": 20
63
- },
64
- "SnowballTarget.Policy.LearningRate.mean": {
65
- "value": 8.082097306000005e-06,
66
- "min": 8.082097306000005e-06,
67
- "max": 0.000291882002706,
68
- "count": 20
69
- },
70
- "SnowballTarget.Policy.LearningRate.sum": {
71
- "value": 3.232838922400002e-05,
72
- "min": 3.232838922400002e-05,
73
- "max": 0.00138516003828,
74
- "count": 20
75
- },
76
- "SnowballTarget.Policy.Epsilon.mean": {
77
- "value": 0.10269400000000001,
78
- "min": 0.10269400000000001,
79
- "max": 0.19729400000000002,
80
- "count": 20
81
- },
82
- "SnowballTarget.Policy.Epsilon.sum": {
83
- "value": 0.41077600000000003,
84
- "min": 0.41077600000000003,
85
- "max": 0.96172,
86
- "count": 20
87
- },
88
- "SnowballTarget.Policy.Beta.mean": {
89
- "value": 0.0001444306000000001,
90
- "min": 0.0001444306000000001,
91
- "max": 0.0048649706,
92
- "count": 20
93
- },
94
- "SnowballTarget.Policy.Beta.sum": {
95
- "value": 0.0005777224000000004,
96
- "min": 0.0005777224000000004,
97
- "max": 0.023089828,
98
- "count": 20
99
- },
100
- "SnowballTarget.Environment.EpisodeLength.mean": {
101
- "value": 199.0,
102
- "min": 199.0,
103
- "max": 199.0,
104
- "count": 20
105
- },
106
- "SnowballTarget.Environment.EpisodeLength.sum": {
107
- "value": 8756.0,
108
- "min": 8756.0,
109
- "max": 10945.0,
110
- "count": 20
111
- },
112
- "SnowballTarget.Environment.CumulativeReward.mean": {
113
- "value": 26.09090909090909,
114
- "min": 3.977272727272727,
115
- "max": 26.472727272727273,
116
- "count": 20
117
- },
118
- "SnowballTarget.Environment.CumulativeReward.sum": {
119
- "value": 1148.0,
120
- "min": 175.0,
121
- "max": 1456.0,
122
- "count": 20
123
- },
124
- "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
- "value": 26.09090909090909,
126
- "min": 3.977272727272727,
127
- "max": 26.472727272727273,
128
- "count": 20
129
- },
130
- "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
- "value": 1148.0,
132
- "min": 175.0,
133
- "max": 1456.0,
134
- "count": 20
135
- },
136
- "SnowballTarget.IsTraining.mean": {
137
- "value": 1.0,
138
- "min": 1.0,
139
- "max": 1.0,
140
- "count": 20
141
- },
142
- "SnowballTarget.IsTraining.sum": {
143
- "value": 1.0,
144
- "min": 1.0,
145
- "max": 1.0,
146
- "count": 20
147
- }
148
- },
149
  "metadata": {
150
  "timer_format_version": "0.1.0",
151
- "start_time_seconds": "1741745573",
152
  "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
153
- "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
154
  "mlagents_version": "1.2.0.dev0",
155
  "mlagents_envs_version": "1.2.0.dev0",
156
  "communication_protocol_version": "1.5.0",
157
  "pytorch_version": "2.6.0+cu124",
158
  "numpy_version": "1.23.5",
159
- "end_time_seconds": "1741746060"
160
  },
161
- "total": 486.859215643,
162
  "count": 1,
163
- "self": 0.43948498799994695,
164
  "children": {
165
  "run_training.setup": {
166
- "total": 0.0404594100000395,
167
  "count": 1,
168
- "self": 0.0404594100000395
169
  },
170
  "TrainerController.start_learning": {
171
- "total": 486.37927124500004,
172
  "count": 1,
173
- "self": 0.41491404799393194,
174
  "children": {
175
  "TrainerController._reset_env": {
176
- "total": 3.8309041170000455,
177
  "count": 1,
178
- "self": 3.8309041170000455
179
  },
180
  "TrainerController.advance": {
181
- "total": 482.03084730400604,
182
- "count": 18192,
183
- "self": 0.47085410800542604,
184
  "children": {
185
  "env_step": {
186
- "total": 345.7108646989975,
187
- "count": 18192,
188
- "self": 261.47123622300495,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
- "total": 83.98766351599568,
192
- "count": 18192,
193
- "self": 1.473245178999946,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
- "total": 82.51441833699573,
197
- "count": 18192,
198
- "self": 82.51441833699573
199
  }
200
  }
201
  },
202
  "workers": {
203
- "total": 0.25196495999688295,
204
- "count": 18192,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
- "total": 484.6442554669926,
209
- "count": 18192,
210
  "is_parallel": true,
211
- "self": 255.88279191199695,
212
  "children": {
213
  "run_training.setup": {
214
  "total": 0.0,
@@ -217,48 +71,48 @@
217
  "self": 0.0,
218
  "children": {
219
  "steps_from_proto": {
220
- "total": 0.0077747810000232676,
221
  "count": 1,
222
  "is_parallel": true,
223
- "self": 0.005096027000035974,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
- "total": 0.0026787539999872934,
227
  "count": 10,
228
  "is_parallel": true,
229
- "self": 0.0026787539999872934
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
- "total": 0.04313565400002517,
235
  "count": 1,
236
  "is_parallel": true,
237
- "self": 0.0007152120000455398,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
- "total": 0.00046134999996638726,
241
  "count": 1,
242
  "is_parallel": true,
243
- "self": 0.00046134999996638726
244
  },
245
  "communicator.exchange": {
246
- "total": 0.039550735000034365,
247
  "count": 1,
248
  "is_parallel": true,
249
- "self": 0.039550735000034365
250
  },
251
  "steps_from_proto": {
252
- "total": 0.002408356999978878,
253
  "count": 1,
254
  "is_parallel": true,
255
- "self": 0.00045056399989107376,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
- "total": 0.001957793000087804,
259
  "count": 10,
260
  "is_parallel": true,
261
- "self": 0.001957793000087804
262
  }
263
  }
264
  }
@@ -267,34 +121,34 @@
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
- "total": 228.76146355499566,
271
- "count": 18191,
272
  "is_parallel": true,
273
- "self": 11.064770819001865,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
- "total": 6.291202456993233,
277
- "count": 18191,
278
  "is_parallel": true,
279
- "self": 6.291202456993233
280
  },
281
  "communicator.exchange": {
282
- "total": 174.82710657799515,
283
- "count": 18191,
284
  "is_parallel": true,
285
- "self": 174.82710657799515
286
  },
287
  "steps_from_proto": {
288
- "total": 36.57838370100541,
289
- "count": 18191,
290
  "is_parallel": true,
291
- "self": 6.7102560469925265,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
- "total": 29.86812765401288,
295
- "count": 181910,
296
  "is_parallel": true,
297
- "self": 29.86812765401288
298
  }
299
  }
300
  }
@@ -307,52 +161,33 @@
307
  }
308
  },
309
  "trainer_advance": {
310
- "total": 135.8491284970031,
311
- "count": 18192,
312
- "self": 0.5000056670073718,
313
  "children": {
314
  "process_trajectory": {
315
- "total": 30.252582493994623,
316
- "count": 18192,
317
- "self": 29.529683940994573,
318
- "children": {
319
- "RLTrainer._checkpoint": {
320
- "total": 0.72289855300005,
321
- "count": 4,
322
- "self": 0.72289855300005
323
- }
324
- }
325
- },
326
- "_update_policy": {
327
- "total": 105.09654033600111,
328
- "count": 90,
329
- "self": 42.291469808000556,
330
- "children": {
331
- "TorchPPOOptimizer.update": {
332
- "total": 62.805070528000556,
333
- "count": 4587,
334
- "self": 62.805070528000556
335
- }
336
- }
337
  }
338
  }
339
  }
340
  }
341
  },
342
  "trainer_threads": {
343
- "total": 1.2210000477352878e-06,
344
  "count": 1,
345
- "self": 1.2210000477352878e-06
346
  },
347
  "TrainerController._save_models": {
348
- "total": 0.10260455499997079,
349
  "count": 1,
350
- "self": 0.0009255879999727767,
351
  "children": {
352
  "RLTrainer._checkpoint": {
353
- "total": 0.10167896699999801,
354
  "count": 1,
355
- "self": 0.10167896699999801
356
  }
357
  }
358
  }
 
1
  {
2
  "name": "root",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3
  "metadata": {
4
  "timer_format_version": "0.1.0",
5
+ "start_time_seconds": "1741746368",
6
  "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
7
+ "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget2 --no-graphics",
8
  "mlagents_version": "1.2.0.dev0",
9
  "mlagents_envs_version": "1.2.0.dev0",
10
  "communication_protocol_version": "1.5.0",
11
  "pytorch_version": "2.6.0+cu124",
12
  "numpy_version": "1.23.5",
13
+ "end_time_seconds": "1741746387"
14
  },
15
+ "total": 18.975267084000052,
16
  "count": 1,
17
+ "self": 0.4642486770001142,
18
  "children": {
19
  "run_training.setup": {
20
+ "total": 0.027944295999986934,
21
  "count": 1,
22
+ "self": 0.027944295999986934
23
  },
24
  "TrainerController.start_learning": {
25
+ "total": 18.48307411099995,
26
  "count": 1,
27
+ "self": 0.01692610199665978,
28
  "children": {
29
  "TrainerController._reset_env": {
30
+ "total": 2.2062937809998857,
31
  "count": 1,
32
+ "self": 2.2062937809998857
33
  },
34
  "TrainerController.advance": {
35
+ "total": 15.985262898003384,
36
+ "count": 692,
37
+ "self": 0.018765200003826976,
38
  "children": {
39
  "env_step": {
40
+ "total": 14.838615273000869,
41
+ "count": 692,
42
+ "self": 11.12357527100221,
43
  "children": {
44
  "SubprocessEnvManager._take_step": {
45
+ "total": 3.7056855230000565,
46
+ "count": 692,
47
+ "self": 0.06572072400103934,
48
  "children": {
49
  "TorchPolicy.evaluate": {
50
+ "total": 3.639964798999017,
51
+ "count": 692,
52
+ "self": 3.639964798999017
53
  }
54
  }
55
  },
56
  "workers": {
57
+ "total": 0.009354478998602644,
58
+ "count": 691,
59
  "self": 0.0,
60
  "children": {
61
  "worker_root": {
62
+ "total": 18.14547060300015,
63
+ "count": 691,
64
  "is_parallel": true,
65
+ "self": 8.53648198700239,
66
  "children": {
67
  "run_training.setup": {
68
  "total": 0.0,
 
71
  "self": 0.0,
72
  "children": {
73
  "steps_from_proto": {
74
+ "total": 0.0031006869999146147,
75
  "count": 1,
76
  "is_parallel": true,
77
+ "self": 0.000860624999859283,
78
  "children": {
79
  "_process_rank_one_or_two_observation": {
80
+ "total": 0.0022400620000553317,
81
  "count": 10,
82
  "is_parallel": true,
83
+ "self": 0.0022400620000553317
84
  }
85
  }
86
  },
87
  "UnityEnvironment.step": {
88
+ "total": 0.046287394000046334,
89
  "count": 1,
90
  "is_parallel": true,
91
+ "self": 0.0006919589998233278,
92
  "children": {
93
  "UnityEnvironment._generate_step_input": {
94
+ "total": 0.00044526500005304115,
95
  "count": 1,
96
  "is_parallel": true,
97
+ "self": 0.00044526500005304115
98
  },
99
  "communicator.exchange": {
100
+ "total": 0.042899765000129264,
101
  "count": 1,
102
  "is_parallel": true,
103
+ "self": 0.042899765000129264
104
  },
105
  "steps_from_proto": {
106
+ "total": 0.0022504050000407005,
107
  "count": 1,
108
  "is_parallel": true,
109
+ "self": 0.0004915099998470396,
110
  "children": {
111
  "_process_rank_one_or_two_observation": {
112
+ "total": 0.001758895000193661,
113
  "count": 10,
114
  "is_parallel": true,
115
+ "self": 0.001758895000193661
116
  }
117
  }
118
  }
 
121
  }
122
  },
123
  "UnityEnvironment.step": {
124
+ "total": 9.60898861599776,
125
+ "count": 690,
126
  "is_parallel": true,
127
+ "self": 0.44187826600000335,
128
  "children": {
129
  "UnityEnvironment._generate_step_input": {
130
+ "total": 0.2308547079987875,
131
+ "count": 690,
132
  "is_parallel": true,
133
+ "self": 0.2308547079987875
134
  },
135
  "communicator.exchange": {
136
+ "total": 7.469084829001758,
137
+ "count": 690,
138
  "is_parallel": true,
139
+ "self": 7.469084829001758
140
  },
141
  "steps_from_proto": {
142
+ "total": 1.4671708129972103,
143
+ "count": 690,
144
  "is_parallel": true,
145
+ "self": 0.27933691499106317,
146
  "children": {
147
  "_process_rank_one_or_two_observation": {
148
+ "total": 1.1878338980061471,
149
+ "count": 6900,
150
  "is_parallel": true,
151
+ "self": 1.1878338980061471
152
  }
153
  }
154
  }
 
161
  }
162
  },
163
  "trainer_advance": {
164
+ "total": 1.1278824249986883,
165
+ "count": 691,
166
+ "self": 0.0195556949956881,
167
  "children": {
168
  "process_trajectory": {
169
+ "total": 1.1083267300030002,
170
+ "count": 691,
171
+ "self": 1.1083267300030002
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
172
  }
173
  }
174
  }
175
  }
176
  },
177
  "trainer_threads": {
178
+ "total": 1.3310000213095918e-06,
179
  "count": 1,
180
+ "self": 1.3310000213095918e-06
181
  },
182
  "TrainerController._save_models": {
183
+ "total": 0.2745899989999998,
184
  "count": 1,
185
+ "self": 0.0012880399999630754,
186
  "children": {
187
  "RLTrainer._checkpoint": {
188
+ "total": 0.27330195900003673,
189
  "count": 1,
190
+ "self": 0.27330195900003673
191
  }
192
  }
193
  }
run_logs/training_status.json CHANGED
@@ -2,58 +2,22 @@
2
  "SnowballTarget": {
3
  "checkpoints": [
4
  {
5
- "steps": 49936,
6
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.onnx",
7
- "reward": 16.09090909090909,
8
- "creation_time": 1741745701.7511792,
9
  "auxillary_file_paths": [
10
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.pt"
11
- ]
12
- },
13
- {
14
- "steps": 99960,
15
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.onnx",
16
- "reward": 24.636363636363637,
17
- "creation_time": 1741745817.7127948,
18
- "auxillary_file_paths": [
19
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.pt"
20
- ]
21
- },
22
- {
23
- "steps": 149984,
24
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.onnx",
25
- "reward": 27.0,
26
- "creation_time": 1741745945.7596734,
27
- "auxillary_file_paths": [
28
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.pt"
29
- ]
30
- },
31
- {
32
- "steps": 199984,
33
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.onnx",
34
- "reward": 25.90909090909091,
35
- "creation_time": 1741746059.5441957,
36
- "auxillary_file_paths": [
37
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.pt"
38
- ]
39
- },
40
- {
41
- "steps": 200112,
42
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.onnx",
43
- "reward": 25.90909090909091,
44
- "creation_time": 1741746059.6598566,
45
- "auxillary_file_paths": [
46
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
47
  ]
48
  }
49
  ],
50
  "final_checkpoint": {
51
- "steps": 200112,
52
- "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
53
- "reward": 25.90909090909091,
54
- "creation_time": 1741746059.6598566,
55
  "auxillary_file_paths": [
56
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
57
  ]
58
  }
59
  },
 
2
  "SnowballTarget": {
3
  "checkpoints": [
4
  {
5
+ "steps": 7304,
6
+ "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-7304.onnx",
7
+ "reward": 2.272727272727273,
8
+ "creation_time": 1741746386.632966,
9
  "auxillary_file_paths": [
10
+ "results/SnowballTarget2/SnowballTarget/SnowballTarget-7304.pt"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
11
  ]
12
  }
13
  ],
14
  "final_checkpoint": {
15
+ "steps": 7304,
16
+ "file_path": "results/SnowballTarget2/SnowballTarget.onnx",
17
+ "reward": 2.272727272727273,
18
+ "creation_time": 1741746386.632966,
19
  "auxillary_file_paths": [
20
+ "results/SnowballTarget2/SnowballTarget/SnowballTarget-7304.pt"
21
  ]
22
  }
23
  },