keerthimalladi commited on
Commit
8e08936
·
verified ·
1 Parent(s): 93d9b41

First Push

Browse files
SnowballTarget.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:81f6428bdcb3ff55359f4e9245e8bc4c756a8efedb68be663d33e7465012af0a
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:47cce9c6f2333f76fcb2fb38af5262bb1051847371e73c27c772559a8be3eaea
3
  size 650646
SnowballTarget/SnowballTarget-149984.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4495eb442bac46d6357b276add48a7b40fa935324ee109d86e9c8dd50d1113bf
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9254df51f8b7c4323745499f6f7b130802a2e0544e0669b778d60970bb258fd8
3
  size 650646
SnowballTarget/SnowballTarget-149984.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:54ce10b6096ef3179af549b318f699fb8006d76834c685d5c9566d65e1331725
3
  size 3849902
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b7bd1b9d0a7c65d65032e7dc72ebb707019fb29cb7240ea85abe915322e8896e
3
  size 3849902
SnowballTarget/SnowballTarget-199984.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:81f6428bdcb3ff55359f4e9245e8bc4c756a8efedb68be663d33e7465012af0a
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:47cce9c6f2333f76fcb2fb38af5262bb1051847371e73c27c772559a8be3eaea
3
  size 650646
SnowballTarget/SnowballTarget-199984.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:72a5b4a79b32a578afd455bb1b5f35f32c71ecfedf5fe2f10dc4a48da34428f3
3
  size 3849902
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0651f999d814e1bfb246309f890aa8b981ce2acc720ef4b46e81d0c8a544baab
3
  size 3849902
SnowballTarget/SnowballTarget-200112.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:81f6428bdcb3ff55359f4e9245e8bc4c756a8efedb68be663d33e7465012af0a
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:47cce9c6f2333f76fcb2fb38af5262bb1051847371e73c27c772559a8be3eaea
3
  size 650646
SnowballTarget/SnowballTarget-200112.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3651085bc7c4bef8f63cf4d98133042f4580678ecc16d893561561358a6a5eda
3
  size 3849902
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8bcded17679854edd661c506b123218e07713d8b9a859efa91b18a6c13c39b62
3
  size 3849902
SnowballTarget/SnowballTarget-49936.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2e4486cdc754048e63ffb0badc7a0cbfdde21c1393b6e64e7039ca35a5ea8195
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e2742d69b6c6ccb1038e7a5a8422bab41781518c1fdd345b8e78e6071005d38
3
  size 650646
SnowballTarget/SnowballTarget-49936.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4db1d75d28b14c18ccbb3cabf9ad4db7651e2d27ef6dcd3bb2a3af9e8702fd46
3
  size 3849827
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f19cfdccde9f4900b7d209c5e6223f70549f46fab670d1f8774e9b09e5eb60b6
3
  size 3849827
SnowballTarget/SnowballTarget-99960.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:34655954fe10f0f2e65707e0d5858a687eab37d72e8db4ce4da7c942e970c126
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c46a69d1fc16f417dea16625435fcc208ed5b9fe3679e7e8be72ba8b7b55acd6
3
  size 650646
SnowballTarget/SnowballTarget-99960.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d4bf9a15fac80a5fbfd4eaf6d75d2d90baa8355b4c959bde2a2da1ca647a883a
3
  size 3849827
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dce0575ba7642374b98b8873685a0aa4fe8ddbaae79d2d4ba063facf117d41dc
3
  size 3849827
SnowballTarget/checkpoint.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:74c1021efa35ad55a9d9ea324b4b64998d93c7ca56cfc20305cfd9c4e151b16c
3
  size 3849077
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:182045a2442006878ed72cd601d9b123ef699a72c24cf5ebb76ffe0eae29f900
3
  size 3849077
SnowballTarget/events.out.tfevents.1788951934.7a985a3efb5e.20909.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87f5f24c19a733e18926edae9a927e5f077098647642334f7e335bdc90c8122e
3
+ size 23493
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": 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": "./ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget.x86_64", "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": true, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
configuration.yaml CHANGED
@@ -45,7 +45,7 @@ behaviors:
45
  self_play: null
46
  behavioral_cloning: null
47
  env_settings:
48
- env_path: ./training-envs-executables/linux/SnowballTarget/SnowballTarget
49
  env_args: null
50
  base_port: 5005
51
  num_envs: 1
@@ -70,7 +70,7 @@ checkpoint_settings:
70
  initialize_from: null
71
  load_model: false
72
  resume: false
73
- force: false
74
  train_model: false
75
  inference: false
76
  results_dir: results
 
45
  self_play: null
46
  behavioral_cloning: null
47
  env_settings:
48
+ env_path: ./ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget.x86_64
49
  env_args: null
50
  base_port: 5005
51
  num_envs: 1
 
70
  initialize_from: null
71
  load_model: false
72
  resume: false
73
+ force: true
74
  train_model: false
75
  inference: false
76
  results_dir: results
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 0.216 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: 0.821294 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.
@@ -169,7 +166,7 @@ Memory Statistics:
169
  Peak Allocated Bytes 0 B
170
  Overflow Count 0
171
  [ALLOC_DEFAULT] Dual Thread Allocator
172
- Peak main deferred allocation count 38
173
  [ALLOC_BUCKET]
174
  Large Block size 4.0 MB
175
  Used Block count 1
@@ -178,13 +175,13 @@ Memory Statistics:
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 6.8 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 17.6 MB
188
  Peak Large allocation bytes 16.0 MB
189
  [ALLOC_TEMP_JOB_1_FRAME]
190
  Initial Block Size 2.0 MB
@@ -213,10 +210,10 @@ 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]: 5108 frames, [64.0 KB-128.0 KB]: 350 frames
217
  Requested Block Size 16.0 MB
218
  Peak Block count 1
219
- Peak Allocated memory 67.3 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
 
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 0.078 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: 0.734810 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.
 
166
  Peak Allocated Bytes 0 B
167
  Overflow Count 0
168
  [ALLOC_DEFAULT] Dual Thread Allocator
169
+ Peak main deferred allocation count 37
170
  [ALLOC_BUCKET]
171
  Large Block size 4.0 MB
172
  Used Block count 1
 
175
  Peak usage frame count: [4.0 MB-8.0 MB]: 5458 frames
176
  Requested Block Size 16.0 MB
177
  Peak Block count 1
178
+ Peak Allocated memory 6.7 MB
179
  Peak Large allocation bytes 0 B
180
  [ALLOC_DEFAULT_THREAD]
181
  Peak usage frame count: [16.0 MB-32.0 MB]: 5458 frames
182
  Requested Block Size 16.0 MB
183
  Peak Block count 1
184
+ Peak Allocated memory 17.7 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]: 5152 frames, [64.0 KB-128.0 KB]: 306 frames
214
  Requested Block Size 16.0 MB
215
  Peak Block count 1
216
+ Peak Allocated memory 66.4 KB
217
  Peak Large allocation bytes 0 B
218
  [ALLOC_GFX_THREAD]
219
  Peak usage frame count: [32.0 KB-64.0 KB]: 5458 frames
run_logs/timers.json CHANGED
@@ -2,15 +2,15 @@
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
- "value": 0.9309353232383728,
6
- "min": 0.885608434677124,
7
- "max": 2.8674821853637695,
8
  "count": 20
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
- "value": 8847.609375,
12
- "min": 8535.5439453125,
13
- "max": 29271.2578125,
14
  "count": 20
15
  },
16
  "SnowballTarget.Step.mean": {
@@ -26,39 +26,39 @@
26
  "count": 20
27
  },
28
  "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
- "value": 13.27536678314209,
30
- "min": 0.46905985474586487,
31
- "max": 13.27536678314209,
32
  "count": 20
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
- "value": 2588.696533203125,
36
- "min": 90.99761199951172,
37
- "max": 2694.41650390625,
38
  "count": 20
39
  },
40
  "SnowballTarget.Losses.PolicyLoss.mean": {
41
- "value": 0.07191022377396711,
42
- "min": 0.06511002199954864,
43
- "max": 0.07552011392746114,
44
  "count": 20
45
  },
46
  "SnowballTarget.Losses.PolicyLoss.sum": {
47
- "value": 0.28764089509586843,
48
- "min": 0.26044008799819457,
49
- "max": 0.3776005696373057,
50
  "count": 20
51
  },
52
  "SnowballTarget.Losses.ValueLoss.mean": {
53
- "value": 0.186674841624849,
54
- "min": 0.11129206329511077,
55
- "max": 0.3004161765178045,
56
  "count": 20
57
  },
58
  "SnowballTarget.Losses.ValueLoss.sum": {
59
- "value": 0.746699366499396,
60
- "min": 0.44516825318044306,
61
- "max": 1.4678371206802479,
62
  "count": 20
63
  },
64
  "SnowballTarget.Policy.LearningRate.mean": {
@@ -110,27 +110,27 @@
110
  "count": 20
111
  },
112
  "SnowballTarget.Environment.CumulativeReward.mean": {
113
- "value": 26.522727272727273,
114
- "min": 3.227272727272727,
115
- "max": 26.522727272727273,
116
  "count": 20
117
  },
118
  "SnowballTarget.Environment.CumulativeReward.sum": {
119
- "value": 1167.0,
120
- "min": 142.0,
121
- "max": 1423.0,
122
  "count": 20
123
  },
124
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
- "value": 26.522727272727273,
126
- "min": 3.227272727272727,
127
- "max": 26.522727272727273,
128
  "count": 20
129
  },
130
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
- "value": 1167.0,
132
- "min": 142.0,
133
- "max": 1423.0,
134
  "count": 20
135
  },
136
  "SnowballTarget.IsTraining.mean": {
@@ -148,67 +148,67 @@
148
  },
149
  "metadata": {
150
  "timer_format_version": "0.1.0",
151
- "start_time_seconds": "1788948810",
152
  "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
153
- "command_line_arguments": "/usr/local/envs/mlagents_env/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": "2.8.0+cu128",
158
  "numpy_version": "1.23.5",
159
- "end_time_seconds": "1788949276"
160
  },
161
- "total": 465.677966494,
162
  "count": 1,
163
- "self": 0.4889124100002391,
164
  "children": {
165
  "run_training.setup": {
166
- "total": 0.021754644999873562,
167
  "count": 1,
168
- "self": 0.021754644999873562
169
  },
170
  "TrainerController.start_learning": {
171
- "total": 465.16729943899986,
172
  "count": 1,
173
- "self": 0.368447631021354,
174
  "children": {
175
  "TrainerController._reset_env": {
176
- "total": 3.5148378779999803,
177
  "count": 1,
178
- "self": 3.5148378779999803
179
  },
180
  "TrainerController.advance": {
181
- "total": 461.2034845359783,
182
  "count": 18192,
183
- "self": 0.401373608986205,
184
  "children": {
185
  "env_step": {
186
- "total": 337.45067007298985,
187
  "count": 18192,
188
- "self": 264.09124624498304,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
- "total": 73.13908405901498,
192
  "count": 18192,
193
- "self": 1.3345309450071454,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
- "total": 71.80455311400783,
197
  "count": 18192,
198
- "self": 71.80455311400783
199
  }
200
  }
201
  },
202
  "workers": {
203
- "total": 0.22033976899183472,
204
  "count": 18192,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
- "total": 463.152875113994,
209
  "count": 18192,
210
  "is_parallel": true,
211
- "self": 230.8636687929902,
212
  "children": {
213
  "run_training.setup": {
214
  "total": 0.0,
@@ -217,48 +217,48 @@
217
  "self": 0.0,
218
  "children": {
219
  "steps_from_proto": {
220
- "total": 0.00437959700002466,
221
  "count": 1,
222
  "is_parallel": true,
223
- "self": 0.0030134440003166674,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
- "total": 0.0013661529997079924,
227
  "count": 10,
228
  "is_parallel": true,
229
- "self": 0.0013661529997079924
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
- "total": 0.03748341400000754,
235
  "count": 1,
236
  "is_parallel": true,
237
- "self": 0.0006281060000219441,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
- "total": 0.0004254860000401095,
241
  "count": 1,
242
  "is_parallel": true,
243
- "self": 0.0004254860000401095
244
  },
245
  "communicator.exchange": {
246
- "total": 0.03422019300001011,
247
  "count": 1,
248
  "is_parallel": true,
249
- "self": 0.03422019300001011
250
  },
251
  "steps_from_proto": {
252
- "total": 0.0022096289999353758,
253
  "count": 1,
254
  "is_parallel": true,
255
- "self": 0.0005975269998543808,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
- "total": 0.001612102000080995,
259
  "count": 10,
260
  "is_parallel": true,
261
- "self": 0.001612102000080995
262
  }
263
  }
264
  }
@@ -267,34 +267,34 @@
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
- "total": 232.2892063210038,
271
  "count": 18191,
272
  "is_parallel": true,
273
- "self": 10.56794811198074,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
- "total": 5.601862455016089,
277
  "count": 18191,
278
  "is_parallel": true,
279
- "self": 5.601862455016089
280
  },
281
  "communicator.exchange": {
282
- "total": 177.44859156799885,
283
  "count": 18191,
284
  "is_parallel": true,
285
- "self": 177.44859156799885
286
  },
287
  "steps_from_proto": {
288
- "total": 38.67080418600813,
289
  "count": 18191,
290
  "is_parallel": true,
291
- "self": 6.923726637041,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
- "total": 31.747077548967127,
295
  "count": 181910,
296
  "is_parallel": true,
297
- "self": 31.747077548967127
298
  }
299
  }
300
  }
@@ -307,31 +307,31 @@
307
  }
308
  },
309
  "trainer_advance": {
310
- "total": 123.35144085400225,
311
  "count": 18192,
312
- "self": 0.44081046400924606,
313
  "children": {
314
  "process_trajectory": {
315
- "total": 25.045967463994202,
316
  "count": 18192,
317
- "self": 24.588582661993996,
318
  "children": {
319
  "RLTrainer._checkpoint": {
320
- "total": 0.45738480200020604,
321
  "count": 4,
322
- "self": 0.45738480200020604
323
  }
324
  }
325
  },
326
  "_update_policy": {
327
- "total": 97.8646629259988,
328
  "count": 90,
329
- "self": 40.55508738500066,
330
  "children": {
331
  "TorchPPOOptimizer.update": {
332
- "total": 57.30957554099814,
333
  "count": 4587,
334
- "self": 57.30957554099814
335
  }
336
  }
337
  }
@@ -340,19 +340,19 @@
340
  }
341
  },
342
  "trainer_threads": {
343
- "total": 9.99000121737481e-07,
344
  "count": 1,
345
- "self": 9.99000121737481e-07
346
  },
347
  "TrainerController._save_models": {
348
- "total": 0.08052839500010123,
349
  "count": 1,
350
- "self": 0.0008536309999271907,
351
  "children": {
352
  "RLTrainer._checkpoint": {
353
- "total": 0.07967476400017404,
354
  "count": 1,
355
- "self": 0.07967476400017404
356
  }
357
  }
358
  }
 
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
+ "value": 0.8975694179534912,
6
+ "min": 0.8971839547157288,
7
+ "max": 2.8548812866210938,
8
  "count": 20
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
+ "value": 8530.5,
12
+ "min": 8530.5,
13
+ "max": 29142.62890625,
14
  "count": 20
15
  },
16
  "SnowballTarget.Step.mean": {
 
26
  "count": 20
27
  },
28
  "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
+ "value": 13.246646881103516,
30
+ "min": 0.4216536581516266,
31
+ "max": 13.246646881103516,
32
  "count": 20
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
+ "value": 2583.09619140625,
36
+ "min": 81.80081176757812,
37
+ "max": 2688.9560546875,
38
  "count": 20
39
  },
40
  "SnowballTarget.Losses.PolicyLoss.mean": {
41
+ "value": 0.06602508749275847,
42
+ "min": 0.06231229684940712,
43
+ "max": 0.0754028665130118,
44
  "count": 20
45
  },
46
  "SnowballTarget.Losses.PolicyLoss.sum": {
47
+ "value": 0.2641003499710339,
48
+ "min": 0.24924918739762847,
49
+ "max": 0.377014332565059,
50
  "count": 20
51
  },
52
  "SnowballTarget.Losses.ValueLoss.mean": {
53
+ "value": 0.19076395487668468,
54
+ "min": 0.13510050879124844,
55
+ "max": 0.3107632037763502,
56
  "count": 20
57
  },
58
  "SnowballTarget.Losses.ValueLoss.sum": {
59
+ "value": 0.7630558195067387,
60
+ "min": 0.5404020351649937,
61
+ "max": 1.384523047828207,
62
  "count": 20
63
  },
64
  "SnowballTarget.Policy.LearningRate.mean": {
 
110
  "count": 20
111
  },
112
  "SnowballTarget.Environment.CumulativeReward.mean": {
113
+ "value": 25.977272727272727,
114
+ "min": 3.772727272727273,
115
+ "max": 25.98181818181818,
116
  "count": 20
117
  },
118
  "SnowballTarget.Environment.CumulativeReward.sum": {
119
+ "value": 1143.0,
120
+ "min": 166.0,
121
+ "max": 1429.0,
122
  "count": 20
123
  },
124
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
+ "value": 25.977272727272727,
126
+ "min": 3.772727272727273,
127
+ "max": 25.98181818181818,
128
  "count": 20
129
  },
130
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
+ "value": 1143.0,
132
+ "min": 166.0,
133
+ "max": 1429.0,
134
  "count": 20
135
  },
136
  "SnowballTarget.IsTraining.mean": {
 
148
  },
149
  "metadata": {
150
  "timer_format_version": "0.1.0",
151
+ "start_time_seconds": "1788951933",
152
  "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
153
+ "command_line_arguments": "/usr/local/envs/mlagents_env/bin/mlagents-learn ./ml-agents/config/ppo/SnowballTarget.yaml --env=./ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget.x86_64 --run-id=SnowballTarget1 --no-graphics --force",
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": "2.8.0+cu128",
158
  "numpy_version": "1.23.5",
159
+ "end_time_seconds": "1788952389"
160
  },
161
+ "total": 455.567600161,
162
  "count": 1,
163
+ "self": 0.4789442519995646,
164
  "children": {
165
  "run_training.setup": {
166
+ "total": 0.020568685000398546,
167
  "count": 1,
168
+ "self": 0.020568685000398546
169
  },
170
  "TrainerController.start_learning": {
171
+ "total": 455.068087224,
172
  "count": 1,
173
+ "self": 0.35191757701340975,
174
  "children": {
175
  "TrainerController._reset_env": {
176
+ "total": 1.9823938870003985,
177
  "count": 1,
178
+ "self": 1.9823938870003985
179
  },
180
  "TrainerController.advance": {
181
+ "total": 452.65186310298577,
182
  "count": 18192,
183
+ "self": 0.3913873040337421,
184
  "children": {
185
  "env_step": {
186
+ "total": 332.39746555598776,
187
  "count": 18192,
188
+ "self": 259.6360808439149,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
+ "total": 72.54314449398225,
192
  "count": 18192,
193
+ "self": 1.292711593945569,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
+ "total": 71.25043290003669,
197
  "count": 18192,
198
+ "self": 71.25043290003669
199
  }
200
  }
201
  },
202
  "workers": {
203
+ "total": 0.21824021809061378,
204
  "count": 18192,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
+ "total": 453.1068449739787,
209
  "count": 18192,
210
  "is_parallel": true,
211
+ "self": 224.66488464399754,
212
  "children": {
213
  "run_training.setup": {
214
  "total": 0.0,
 
217
  "self": 0.0,
218
  "children": {
219
  "steps_from_proto": {
220
+ "total": 0.0029527349997806596,
221
  "count": 1,
222
  "is_parallel": true,
223
+ "self": 0.0008152870013873326,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
+ "total": 0.002137447998393327,
227
  "count": 10,
228
  "is_parallel": true,
229
+ "self": 0.002137447998393327
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
+ "total": 0.04363022699999419,
235
  "count": 1,
236
  "is_parallel": true,
237
+ "self": 0.0008127409992084722,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
+ "total": 0.0004078780002600979,
241
  "count": 1,
242
  "is_parallel": true,
243
+ "self": 0.0004078780002600979
244
  },
245
  "communicator.exchange": {
246
+ "total": 0.0397641340005066,
247
  "count": 1,
248
  "is_parallel": true,
249
+ "self": 0.0397641340005066
250
  },
251
  "steps_from_proto": {
252
+ "total": 0.0026454740000190213,
253
  "count": 1,
254
  "is_parallel": true,
255
+ "self": 0.0007041270009722211,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
+ "total": 0.0019413469990468002,
259
  "count": 10,
260
  "is_parallel": true,
261
+ "self": 0.0019413469990468002
262
  }
263
  }
264
  }
 
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
+ "total": 228.44196032998116,
271
  "count": 18191,
272
  "is_parallel": true,
273
+ "self": 10.379013011933239,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
+ "total": 5.519224735059652,
277
  "count": 18191,
278
  "is_parallel": true,
279
+ "self": 5.519224735059652
280
  },
281
  "communicator.exchange": {
282
+ "total": 174.87968951999756,
283
  "count": 18191,
284
  "is_parallel": true,
285
+ "self": 174.87968951999756
286
  },
287
  "steps_from_proto": {
288
+ "total": 37.66403306299071,
289
  "count": 18191,
290
  "is_parallel": true,
291
+ "self": 6.795656010839593,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
+ "total": 30.868377052151118,
295
  "count": 181910,
296
  "is_parallel": true,
297
+ "self": 30.868377052151118
298
  }
299
  }
300
  }
 
307
  }
308
  },
309
  "trainer_advance": {
310
+ "total": 119.86301024296426,
311
  "count": 18192,
312
+ "self": 0.45350401491214143,
313
  "children": {
314
  "process_trajectory": {
315
+ "total": 24.378870629049743,
316
  "count": 18192,
317
+ "self": 23.956908025049415,
318
  "children": {
319
  "RLTrainer._checkpoint": {
320
+ "total": 0.4219626040003277,
321
  "count": 4,
322
+ "self": 0.4219626040003277
323
  }
324
  }
325
  },
326
  "_update_policy": {
327
+ "total": 95.03063559900238,
328
  "count": 90,
329
+ "self": 38.245206299995516,
330
  "children": {
331
  "TorchPPOOptimizer.update": {
332
+ "total": 56.785429299006864,
333
  "count": 4587,
334
+ "self": 56.785429299006864
335
  }
336
  }
337
  }
 
340
  }
341
  },
342
  "trainer_threads": {
343
+ "total": 8.950000847107731e-07,
344
  "count": 1,
345
+ "self": 8.950000847107731e-07
346
  },
347
  "TrainerController._save_models": {
348
+ "total": 0.08191176200034533,
349
  "count": 1,
350
+ "self": 0.0009143500001300708,
351
  "children": {
352
  "RLTrainer._checkpoint": {
353
+ "total": 0.08099741200021526,
354
  "count": 1,
355
+ "self": 0.08099741200021526
356
  }
357
  }
358
  }
run_logs/training_status.json CHANGED
@@ -4,8 +4,8 @@
4
  {
5
  "steps": 49936,
6
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.onnx",
7
- "reward": 13.909090909090908,
8
- "creation_time": 1788948931.0770042,
9
  "auxillary_file_paths": [
10
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.pt"
11
  ]
@@ -14,7 +14,7 @@
14
  "steps": 99960,
15
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.onnx",
16
  "reward": 24.363636363636363,
17
- "creation_time": 1788949046.097881,
18
  "auxillary_file_paths": [
19
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.pt"
20
  ]
@@ -22,8 +22,8 @@
22
  {
23
  "steps": 149984,
24
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.onnx",
25
- "reward": 25.727272727272727,
26
- "creation_time": 1788949161.6550086,
27
  "auxillary_file_paths": [
28
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.pt"
29
  ]
@@ -31,8 +31,8 @@
31
  {
32
  "steps": 199984,
33
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.onnx",
34
- "reward": 27.09090909090909,
35
- "creation_time": 1788949275.9754188,
36
  "auxillary_file_paths": [
37
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.pt"
38
  ]
@@ -40,8 +40,8 @@
40
  {
41
  "steps": 200112,
42
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.onnx",
43
- "reward": 27.09090909090909,
44
- "creation_time": 1788949276.0658212,
45
  "auxillary_file_paths": [
46
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
47
  ]
@@ -50,8 +50,8 @@
50
  "final_checkpoint": {
51
  "steps": 200112,
52
  "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
53
- "reward": 27.09090909090909,
54
- "creation_time": 1788949276.0658212,
55
  "auxillary_file_paths": [
56
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
57
  ]
 
4
  {
5
  "steps": 49936,
6
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.onnx",
7
+ "reward": 17.545454545454547,
8
+ "creation_time": 1788952047.9039414,
9
  "auxillary_file_paths": [
10
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.pt"
11
  ]
 
14
  "steps": 99960,
15
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.onnx",
16
  "reward": 24.363636363636363,
17
+ "creation_time": 1788952162.298826,
18
  "auxillary_file_paths": [
19
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.pt"
20
  ]
 
22
  {
23
  "steps": 149984,
24
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.onnx",
25
+ "reward": 25.636363636363637,
26
+ "creation_time": 1788952276.2446718,
27
  "auxillary_file_paths": [
28
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.pt"
29
  ]
 
31
  {
32
  "steps": 199984,
33
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.onnx",
34
+ "reward": 25.272727272727273,
35
+ "creation_time": 1788952388.7931964,
36
  "auxillary_file_paths": [
37
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.pt"
38
  ]
 
40
  {
41
  "steps": 200112,
42
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.onnx",
43
+ "reward": 25.272727272727273,
44
+ "creation_time": 1788952388.8852367,
45
  "auxillary_file_paths": [
46
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
47
  ]
 
50
  "final_checkpoint": {
51
  "steps": 200112,
52
  "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
53
+ "reward": 25.272727272727273,
54
+ "creation_time": 1788952388.8852367,
55
  "auxillary_file_paths": [
56
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
57
  ]