Hugging Face's logo

shahafw
/
ppo-SnowballTarget

Reinforcement Learning
ml-agents
TensorBoard
ONNX
SnowballTarget
deep-reinforcement-learning
ML-Agents-SnowballTarget
Model card Files
xet
Metrics Community
shahafw commited on
Commit
7ee5ea8
·
1 Parent(s): 62dff8f

First Push

Browse files
Files changed (18) hide show
  1. SnowballTarget.onnx +1 -1
  2. SnowballTarget/SnowballTarget-149984.onnx +1 -1
  3. SnowballTarget/SnowballTarget-149984.pt +1 -1
  4. SnowballTarget/SnowballTarget-199984.onnx +1 -1
  5. SnowballTarget/SnowballTarget-199984.pt +1 -1
  6. SnowballTarget/SnowballTarget-200200.onnx +3 -0
  7. SnowballTarget/SnowballTarget-200200.pt +3 -0
  8. SnowballTarget/SnowballTarget-49936.onnx +1 -1
  9. SnowballTarget/SnowballTarget-49936.pt +1 -1
  10. SnowballTarget/SnowballTarget-99960.onnx +1 -1
  11. SnowballTarget/SnowballTarget-99960.pt +1 -1
  12. SnowballTarget/checkpoint.pt +1 -1
  13. SnowballTarget/events.out.tfevents.1686387465.f9711cf69cef.1105.0 +3 -0
  14. config.json +1 -1
  15. configuration.yaml +1 -1
  16. run_logs/Player-0.log +9 -6
  17. run_logs/timers.json +100 -100
  18. run_logs/training_status.json +25 -25
SnowballTarget.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1b4e2804620dc7dc0aaff872c0c863f2c816a0d77f727b85df8a8d2971b2f0d8
3
  size 646532
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9eef91f46a7e79a4fa0666cece9e2543c0b56b6599d414923dfe1716b71488d0
3
  size 646532
SnowballTarget/SnowballTarget-149984.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dbe2c6669920bbe2a3a92cee23581fa6cd9acc3d2ca2e091eff5867f476c8117
3
  size 646532
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c0580a7272823af440943630899eea4458cdbbbff5bb87386a8b3cfd33802e5
3
  size 646532
SnowballTarget/SnowballTarget-149984.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2e86a0ef1c7499f5423c1bd016f062e8d51f496df2815a77666b06be742c060d
3
  size 3843968
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7ce99fe62360d82188acea16facc4c9cdaae04257d1184bb9ed1f8e3537c4e0
3
  size 3843968
SnowballTarget/SnowballTarget-199984.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1b4e2804620dc7dc0aaff872c0c863f2c816a0d77f727b85df8a8d2971b2f0d8
3
  size 646532
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9eef91f46a7e79a4fa0666cece9e2543c0b56b6599d414923dfe1716b71488d0
3
  size 646532
SnowballTarget/SnowballTarget-199984.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3d042ab14a3f48912575d87c382323c740af2d38eae8fcd428aa5e64d65c111a
3
  size 3843968
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:801e971b10a9a9209d1c352377dd40566814d2903a15fd426f0de99fb15e663c
3
  size 3843968
SnowballTarget/SnowballTarget-200200.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9eef91f46a7e79a4fa0666cece9e2543c0b56b6599d414923dfe1716b71488d0
3
+ size 646532
SnowballTarget/SnowballTarget-200200.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7b9ea83c43095f1976ead6edbf2ce43bf098881119d70e3722a9c5a2138dc35
3
+ size 3843968
SnowballTarget/SnowballTarget-49936.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fd4b135e3943b89a62fc82f43815af8937bea1810b79336c10bc7327d782d96f
3
  size 646532
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb5b5db4505b70a887a999285e1e931f7d88d0b94fa637fe3b3fdede2adccbf0
3
  size 646532
SnowballTarget/SnowballTarget-49936.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9ac07b24f9d64703d9792350f35946d1db0eccdd54716d2ca8aa8654e7cf8cc1
3
  size 3843968
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e99d7e53948dfc0aa770a385b7ccd2175fbcac03072a00270928f72f9b18536e
3
  size 3843968
SnowballTarget/SnowballTarget-99960.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:45b7ee6e5366751990ec9d77e76f9148c1235c6e7d76d4adc0b8e07b9590818a
3
  size 646532
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc6d448922bd0f1235d0f3327e98ae3bb8462ddfc66baeb6546b40e494dc4e48
3
  size 646532
SnowballTarget/SnowballTarget-99960.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3ae032fd1dfbd74228dc2fc4edc6b3c8d733a97ca3f7a6035584880256efd65c
3
  size 3843968
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26ebe5a2ad5d97867ad72b7f6471f89710c6280ae612e936ab92f97ec57e7666
3
  size 3843968
SnowballTarget/checkpoint.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:32764a038f01af5a449e7d1e567f3e47bec1c66e3301dac54825455bb45ffae4
3
  size 3843968
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7b9ea83c43095f1976ead6edbf2ce43bf098881119d70e3722a9c5a2138dc35
3
  size 3843968
SnowballTarget/events.out.tfevents.1686387465.f9711cf69cef.1105.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cbe3ba0bcdb992e36965d0263ccac0c74b594b19d588bee615902b9eb6e8fe03
3
+ size 28813
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": true, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/SnowballTarget/SnowballTarget", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SnowballTarget11", "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": true, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/SnowballTarget/SnowballTarget", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SnowballTarget", "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
@@ -64,7 +64,7 @@ engine_settings:
64
  no_graphics: true
65
  environment_parameters: null
66
  checkpoint_settings:
67
- run_id: SnowballTarget11
68
  initialize_from: null
69
  load_model: false
70
  resume: false
 
64
  no_graphics: true
65
  environment_parameters: null
66
  checkpoint_settings:
67
+ run_id: SnowballTarget
68
  initialize_from: null
69
  load_model: false
70
  resume: false
run_logs/Player-0.log CHANGED
@@ -2,6 +2,9 @@ Mono path[0] = '/content/ml-agents-patch/training-envs-executables/linux/Snowbal
2
  Mono config path = '/content/ml-agents-patch/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-patch/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/UnitySubsystems
7
  Forcing GfxDevice: Null
@@ -31,7 +34,7 @@ ALSA lib pcm.c:2642:(snd_pcm_open_noupdate) Unknown PCM default
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 0.090 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)
@@ -42,7 +45,7 @@ ERROR: Shader Standard shader is not supported on this GPU (none of subshaders/f
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: 0.664345 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.
@@ -166,7 +169,7 @@ Memory Statistics:
166
  Peak Allocated Bytes 0 B
167
  Overflow Count 0
168
  [ALLOC_DEFAULT] Dual Thread Allocator
169
- Peak main deferred allocation count 47
170
  [ALLOC_BUCKET]
171
  Large Block size 4.0 MB
172
  Used Block count 1
@@ -175,7 +178,7 @@ Memory Statistics:
175
  Peak usage frame count: [4.0 MB-8.0 MB]: 5462 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]: 5462 frames
@@ -210,10 +213,10 @@ Memory Statistics:
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]: 4647 frames, [64.0 KB-128.0 KB]: 815 frames
214
  Requested Block Size 16.0 MB
215
  Peak Block count 1
216
- Peak Allocated memory 66.8 KB
217
  Peak Large allocation bytes 0 B
218
  [ALLOC_GFX_THREAD]
219
  Peak usage frame count: [32.0 KB-64.0 KB]: 5462 frames
 
2
  Mono config path = '/content/ml-agents-patch/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-patch/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/UnitySubsystems
10
  Forcing GfxDevice: Null
 
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 0.084 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
  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: 0.668085 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
  Peak Allocated Bytes 0 B
170
  Overflow Count 0
171
  [ALLOC_DEFAULT] Dual Thread Allocator
172
+ Peak main deferred allocation count 41
173
  [ALLOC_BUCKET]
174
  Large Block size 4.0 MB
175
  Used Block count 1
 
178
  Peak usage frame count: [4.0 MB-8.0 MB]: 5462 frames
179
  Requested Block Size 16.0 MB
180
  Peak Block count 1
181
+ Peak Allocated memory 6.6 MB
182
  Peak Large allocation bytes 0 B
183
  [ALLOC_DEFAULT_THREAD]
184
  Peak usage frame count: [16.0 MB-32.0 MB]: 5462 frames
 
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]: 4445 frames, [64.0 KB-128.0 KB]: 1017 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]: 5462 frames
run_logs/timers.json CHANGED
@@ -2,15 +2,15 @@
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
- "value": 0.9829342365264893,
6
- "min": 0.9829342365264893,
7
- "max": 2.865917205810547,
8
  "count": 20
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
- "value": 9395.8681640625,
12
- "min": 9395.8681640625,
13
- "max": 29381.3828125,
14
  "count": 20
15
  },
16
  "SnowballTarget.Step.mean": {
@@ -26,15 +26,15 @@
26
  "count": 20
27
  },
28
  "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
- "value": 12.623763084411621,
30
- "min": 0.36927610635757446,
31
- "max": 12.623763084411621,
32
  "count": 20
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
- "value": 2461.6337890625,
36
- "min": 71.63956451416016,
37
- "max": 2525.593017578125,
38
  "count": 20
39
  },
40
  "SnowballTarget.Environment.EpisodeLength.mean": {
@@ -50,27 +50,27 @@
50
  "count": 20
51
  },
52
  "SnowballTarget.Losses.PolicyLoss.mean": {
53
- "value": 0.07280002598246724,
54
- "min": 0.06108100912971685,
55
- "max": 0.07529431707956188,
56
  "count": 20
57
  },
58
  "SnowballTarget.Losses.PolicyLoss.sum": {
59
- "value": 0.29120010392986895,
60
- "min": 0.25601398065405456,
61
- "max": 0.36138179990880687,
62
  "count": 20
63
  },
64
  "SnowballTarget.Losses.ValueLoss.mean": {
65
- "value": 0.21106607992859447,
66
- "min": 0.12309441370569973,
67
- "max": 0.2818194264874738,
68
  "count": 20
69
  },
70
  "SnowballTarget.Losses.ValueLoss.sum": {
71
- "value": 0.8442643197143779,
72
- "min": 0.49237765482279894,
73
- "max": 1.4090971324373691,
74
  "count": 20
75
  },
76
  "SnowballTarget.Policy.LearningRate.mean": {
@@ -110,27 +110,27 @@
110
  "count": 20
111
  },
112
  "SnowballTarget.Environment.CumulativeReward.mean": {
113
- "value": 25.113636363636363,
114
- "min": 3.25,
115
- "max": 25.29090909090909,
116
  "count": 20
117
  },
118
  "SnowballTarget.Environment.CumulativeReward.sum": {
119
- "value": 1105.0,
120
- "min": 143.0,
121
- "max": 1391.0,
122
  "count": 20
123
  },
124
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
- "value": 25.113636363636363,
126
- "min": 3.25,
127
- "max": 25.29090909090909,
128
  "count": 20
129
  },
130
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
- "value": 1105.0,
132
- "min": 143.0,
133
- "max": 1391.0,
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": "1686342282",
152
  "python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [GCC 9.4.0]",
153
- "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget11 --no-graphics",
154
  "mlagents_version": "0.31.0.dev0",
155
  "mlagents_envs_version": "0.31.0.dev0",
156
  "communication_protocol_version": "1.5.0",
157
  "pytorch_version": "1.11.0+cu102",
158
  "numpy_version": "1.21.2",
159
- "end_time_seconds": "1686342783"
160
  },
161
- "total": 500.689434057,
162
  "count": 1,
163
- "self": 0.42702736600000435,
164
  "children": {
165
  "run_training.setup": {
166
- "total": 0.04125100900000689,
167
  "count": 1,
168
- "self": 0.04125100900000689
169
  },
170
  "TrainerController.start_learning": {
171
- "total": 500.221155682,
172
  "count": 1,
173
- "self": 0.5725422419995994,
174
  "children": {
175
  "TrainerController._reset_env": {
176
- "total": 3.908960798999999,
177
  "count": 1,
178
- "self": 3.908960798999999
179
  },
180
  "TrainerController.advance": {
181
- "total": 495.5872944550004,
182
  "count": 18204,
183
- "self": 0.28807763799363784,
184
  "children": {
185
  "env_step": {
186
- "total": 495.29921681700677,
187
  "count": 18204,
188
- "self": 360.16837258400165,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
- "total": 134.84929339200482,
192
  "count": 18204,
193
- "self": 1.8046705460168369,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
- "total": 133.044622845988,
197
  "count": 18204,
198
- "self": 133.044622845988
199
  }
200
  }
201
  },
202
  "workers": {
203
- "total": 0.28155084100029626,
204
  "count": 18204,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
- "total": 498.527873404001,
209
  "count": 18204,
210
  "is_parallel": true,
211
- "self": 236.90754103900332,
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": 0.0027379279999877326,
221
  "count": 1,
222
  "is_parallel": true,
223
- "self": 0.0007037219999688205,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
- "total": 0.002034206000018912,
227
  "count": 10,
228
  "is_parallel": true,
229
- "self": 0.002034206000018912
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
- "total": 0.049086267000006956,
235
  "count": 1,
236
  "is_parallel": true,
237
- "self": 0.000500081999973645,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
- "total": 0.0003881110000065746,
241
  "count": 1,
242
  "is_parallel": true,
243
- "self": 0.0003881110000065746
244
  },
245
  "communicator.exchange": {
246
- "total": 0.0459134449999965,
247
  "count": 1,
248
  "is_parallel": true,
249
- "self": 0.0459134449999965
250
  },
251
  "steps_from_proto": {
252
- "total": 0.002284629000030236,
253
  "count": 1,
254
  "is_parallel": true,
255
- "self": 0.0005715790001090681,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
- "total": 0.001713049999921168,
259
  "count": 10,
260
  "is_parallel": true,
261
- "self": 0.001713049999921168
262
  }
263
  }
264
  }
@@ -267,34 +267,34 @@
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
- "total": 261.6203323649977,
271
  "count": 18203,
272
  "is_parallel": true,
273
- "self": 10.724119716005873,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
- "total": 5.7101396779913784,
277
  "count": 18203,
278
  "is_parallel": true,
279
- "self": 5.7101396779913784
280
  },
281
  "communicator.exchange": {
282
- "total": 206.99653442599777,
283
  "count": 18203,
284
  "is_parallel": true,
285
- "self": 206.99653442599777
286
  },
287
  "steps_from_proto": {
288
- "total": 38.18953854500268,
289
  "count": 18203,
290
  "is_parallel": true,
291
- "self": 7.022838214011188,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
- "total": 31.16670033099149,
295
  "count": 182030,
296
  "is_parallel": true,
297
- "self": 31.16670033099149
298
  }
299
  }
300
  }
@@ -309,9 +309,9 @@
309
  }
310
  },
311
  "trainer_threads": {
312
- "total": 9.224300004007091e-05,
313
  "count": 1,
314
- "self": 9.224300004007091e-05,
315
  "children": {
316
  "thread_root": {
317
  "total": 0.0,
@@ -320,36 +320,36 @@
320
  "self": 0.0,
321
  "children": {
322
  "trainer_advance": {
323
- "total": 491.62902670200634,
324
- "count": 466500,
325
  "is_parallel": true,
326
- "self": 10.759211416984726,
327
  "children": {
328
  "process_trajectory": {
329
- "total": 268.79954234602116,
330
- "count": 466500,
331
  "is_parallel": true,
332
- "self": 267.48715303802123,
333
  "children": {
334
  "RLTrainer._checkpoint": {
335
- "total": 1.312389307999922,
336
  "count": 4,
337
  "is_parallel": true,
338
- "self": 1.312389307999922
339
  }
340
  }
341
  },
342
  "_update_policy": {
343
- "total": 212.07027293900046,
344
  "count": 90,
345
  "is_parallel": true,
346
- "self": 85.47357697099812,
347
  "children": {
348
  "TorchPPOOptimizer.update": {
349
- "total": 126.59669596800234,
350
  "count": 4587,
351
  "is_parallel": true,
352
- "self": 126.59669596800234
353
  }
354
  }
355
  }
@@ -360,14 +360,14 @@
360
  }
361
  },
362
  "TrainerController._save_models": {
363
- "total": 0.15226594299997487,
364
  "count": 1,
365
- "self": 0.0009300809999785997,
366
  "children": {
367
  "RLTrainer._checkpoint": {
368
- "total": 0.15133586199999627,
369
  "count": 1,
370
- "self": 0.15133586199999627
371
  }
372
  }
373
  }
 
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
+ "value": 1.0653297901153564,
6
+ "min": 1.0653297901153564,
7
+ "max": 2.858488082885742,
8
  "count": 20
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
+ "value": 10183.4873046875,
12
+ "min": 10183.4873046875,
13
+ "max": 29273.77734375,
14
  "count": 20
15
  },
16
  "SnowballTarget.Step.mean": {
 
26
  "count": 20
27
  },
28
  "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
+ "value": 12.638876914978027,
30
+ "min": 0.36404725909233093,
31
+ "max": 12.638876914978027,
32
  "count": 20
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
+ "value": 2464.5810546875,
36
+ "min": 70.62516784667969,
37
+ "max": 2563.384765625,
38
  "count": 20
39
  },
40
  "SnowballTarget.Environment.EpisodeLength.mean": {
 
50
  "count": 20
51
  },
52
  "SnowballTarget.Losses.PolicyLoss.mean": {
53
+ "value": 0.06756832470066501,
54
+ "min": 0.06126134650320654,
55
+ "max": 0.07445792262716328,
56
  "count": 20
57
  },
58
  "SnowballTarget.Losses.PolicyLoss.sum": {
59
+ "value": 0.27027329880266004,
60
+ "min": 0.24504538601282616,
61
+ "max": 0.3722896131358164,
62
  "count": 20
63
  },
64
  "SnowballTarget.Losses.ValueLoss.mean": {
65
+ "value": 0.2581539674132478,
66
+ "min": 0.15281490772259515,
67
+ "max": 0.2732131793072411,
68
  "count": 20
69
  },
70
  "SnowballTarget.Losses.ValueLoss.sum": {
71
+ "value": 1.0326158696529912,
72
+ "min": 0.6112596308903806,
73
+ "max": 1.3492888837468389,
74
  "count": 20
75
  },
76
  "SnowballTarget.Policy.LearningRate.mean": {
 
110
  "count": 20
111
  },
112
  "SnowballTarget.Environment.CumulativeReward.mean": {
113
+ "value": 24.886363636363637,
114
+ "min": 3.772727272727273,
115
+ "max": 24.90909090909091,
116
  "count": 20
117
  },
118
  "SnowballTarget.Environment.CumulativeReward.sum": {
119
+ "value": 1095.0,
120
+ "min": 166.0,
121
+ "max": 1370.0,
122
  "count": 20
123
  },
124
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
+ "value": 24.886363636363637,
126
+ "min": 3.772727272727273,
127
+ "max": 24.90909090909091,
128
  "count": 20
129
  },
130
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
+ "value": 1095.0,
132
+ "min": 166.0,
133
+ "max": 1370.0,
134
  "count": 20
135
  },
136
  "SnowballTarget.IsTraining.mean": {
 
148
  },
149
  "metadata": {
150
  "timer_format_version": "0.1.0",
151
+ "start_time_seconds": "1686387464",
152
  "python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [GCC 9.4.0]",
153
+ "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget --no-graphics",
154
  "mlagents_version": "0.31.0.dev0",
155
  "mlagents_envs_version": "0.31.0.dev0",
156
  "communication_protocol_version": "1.5.0",
157
  "pytorch_version": "1.11.0+cu102",
158
  "numpy_version": "1.21.2",
159
+ "end_time_seconds": "1686387940"
160
  },
161
+ "total": 476.149789041,
162
  "count": 1,
163
+ "self": 0.4313932070000419,
164
  "children": {
165
  "run_training.setup": {
166
+ "total": 0.043099917999995796,
167
  "count": 1,
168
+ "self": 0.043099917999995796
169
  },
170
  "TrainerController.start_learning": {
171
+ "total": 475.675295916,
172
  "count": 1,
173
+ "self": 0.6231617049925262,
174
  "children": {
175
  "TrainerController._reset_env": {
176
+ "total": 4.137711034999995,
177
  "count": 1,
178
+ "self": 4.137711034999995
179
  },
180
  "TrainerController.advance": {
181
+ "total": 470.78015949700756,
182
  "count": 18204,
183
+ "self": 0.2754055160073108,
184
  "children": {
185
  "env_step": {
186
+ "total": 470.50475398100025,
187
  "count": 18204,
188
+ "self": 345.81845625501,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
+ "total": 124.40468182899639,
192
  "count": 18204,
193
+ "self": 1.8459019109993164,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
+ "total": 122.55877991799707,
197
  "count": 18204,
198
+ "self": 122.55877991799707
199
  }
200
  }
201
  },
202
  "workers": {
203
+ "total": 0.28161589699382716,
204
  "count": 18204,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
+ "total": 474.10254149799437,
209
  "count": 18204,
210
  "is_parallel": true,
211
+ "self": 220.06562533399813,
212
  "children": {
213
  "run_training.setup": {
214
  "total": 0.0,
 
217
  "self": 0.0,
218
  "children": {
219
  "steps_from_proto": {
220
+ "total": 0.005703778999986753,
221
  "count": 1,
222
  "is_parallel": true,
223
+ "self": 0.004112338999959775,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
+ "total": 0.001591440000026978,
227
  "count": 10,
228
  "is_parallel": true,
229
+ "self": 0.001591440000026978
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
+ "total": 0.052595511999982136,
235
  "count": 1,
236
  "is_parallel": true,
237
+ "self": 0.0006636710000123003,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
+ "total": 0.0003221030000020164,
241
  "count": 1,
242
  "is_parallel": true,
243
+ "self": 0.0003221030000020164
244
  },
245
  "communicator.exchange": {
246
+ "total": 0.04946189399998957,
247
  "count": 1,
248
  "is_parallel": true,
249
+ "self": 0.04946189399998957
250
  },
251
  "steps_from_proto": {
252
+ "total": 0.0021478439999782495,
253
  "count": 1,
254
  "is_parallel": true,
255
+ "self": 0.0003648979999297808,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
+ "total": 0.0017829460000484687,
259
  "count": 10,
260
  "is_parallel": true,
261
+ "self": 0.0017829460000484687
262
  }
263
  }
264
  }
 
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
+ "total": 254.03691616399624,
271
  "count": 18203,
272
  "is_parallel": true,
273
+ "self": 10.576325412007378,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
+ "total": 5.3421877689913515,
277
  "count": 18203,
278
  "is_parallel": true,
279
+ "self": 5.3421877689913515
280
  },
281
  "communicator.exchange": {
282
+ "total": 203.22721400599457,
283
  "count": 18203,
284
  "is_parallel": true,
285
+ "self": 203.22721400599457
286
  },
287
  "steps_from_proto": {
288
+ "total": 34.89118897700294,
289
  "count": 18203,
290
  "is_parallel": true,
291
+ "self": 6.285768090999568,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
+ "total": 28.605420886003373,
295
  "count": 182030,
296
  "is_parallel": true,
297
+ "self": 28.605420886003373
298
  }
299
  }
300
  }
 
309
  }
310
  },
311
  "trainer_threads": {
312
+ "total": 0.0001696159999937663,
313
  "count": 1,
314
+ "self": 0.0001696159999937663,
315
  "children": {
316
  "thread_root": {
317
  "total": 0.0,
 
320
  "self": 0.0,
321
  "children": {
322
  "trainer_advance": {
323
+ "total": 467.0786967380349,
324
+ "count": 462394,
325
  "is_parallel": true,
326
+ "self": 9.9716951830531,
327
  "children": {
328
  "process_trajectory": {
329
+ "total": 255.84439582698175,
330
+ "count": 462394,
331
  "is_parallel": true,
332
+ "self": 254.98892250198176,
333
  "children": {
334
  "RLTrainer._checkpoint": {
335
+ "total": 0.8554733249999913,
336
  "count": 4,
337
  "is_parallel": true,
338
+ "self": 0.8554733249999913
339
  }
340
  }
341
  },
342
  "_update_policy": {
343
+ "total": 201.26260572800004,
344
  "count": 90,
345
  "is_parallel": true,
346
+ "self": 78.3491579639983,
347
  "children": {
348
  "TorchPPOOptimizer.update": {
349
+ "total": 122.91344776400175,
350
  "count": 4587,
351
  "is_parallel": true,
352
+ "self": 122.91344776400175
353
  }
354
  }
355
  }
 
360
  }
361
  },
362
  "TrainerController._save_models": {
363
+ "total": 0.13409406299990678,
364
  "count": 1,
365
+ "self": 0.0009151099999371581,
366
  "children": {
367
  "RLTrainer._checkpoint": {
368
+ "total": 0.13317895299996962,
369
  "count": 1,
370
+ "self": 0.13317895299996962
371
  }
372
  }
373
  }
run_logs/training_status.json CHANGED
@@ -3,57 +3,57 @@
3
  "checkpoints": [
4
  {
5
  "steps": 49936,
6
- "file_path": "results/SnowballTarget11/SnowballTarget/SnowballTarget-49936.onnx",
7
- "reward": 12.363636363636363,
8
- "creation_time": 1686342413.370025,
9
  "auxillary_file_paths": [
10
- "results/SnowballTarget11/SnowballTarget/SnowballTarget-49936.pt"
11
  ]
12
  },
13
  {
14
  "steps": 99960,
15
- "file_path": "results/SnowballTarget11/SnowballTarget/SnowballTarget-99960.onnx",
16
  "reward": 19.636363636363637,
17
- "creation_time": 1686342538.611239,
18
  "auxillary_file_paths": [
19
- "results/SnowballTarget11/SnowballTarget/SnowballTarget-99960.pt"
20
  ]
21
  },
22
  {
23
  "steps": 149984,
24
- "file_path": "results/SnowballTarget11/SnowballTarget/SnowballTarget-149984.onnx",
25
- "reward": 24.09090909090909,
26
- "creation_time": 1686342660.3551714,
27
  "auxillary_file_paths": [
28
- "results/SnowballTarget11/SnowballTarget/SnowballTarget-149984.pt"
29
  ]
30
  },
31
  {
32
  "steps": 199984,
33
- "file_path": "results/SnowballTarget11/SnowballTarget/SnowballTarget-199984.onnx",
34
- "reward": 25.363636363636363,
35
- "creation_time": 1686342782.9023669,
36
  "auxillary_file_paths": [
37
- "results/SnowballTarget11/SnowballTarget/SnowballTarget-199984.pt"
38
  ]
39
  },
40
  {
41
- "steps": 200112,
42
- "file_path": "results/SnowballTarget11/SnowballTarget/SnowballTarget-200112.onnx",
43
- "reward": 25.363636363636363,
44
- "creation_time": 1686342783.0883267,
45
  "auxillary_file_paths": [
46
- "results/SnowballTarget11/SnowballTarget/SnowballTarget-200112.pt"
47
  ]
48
  }
49
  ],
50
  "final_checkpoint": {
51
- "steps": 200112,
52
- "file_path": "results/SnowballTarget11/SnowballTarget.onnx",
53
- "reward": 25.363636363636363,
54
- "creation_time": 1686342783.0883267,
55
  "auxillary_file_paths": [
56
- "results/SnowballTarget11/SnowballTarget/SnowballTarget-200112.pt"
57
  ]
58
  }
59
  },
 
3
  "checkpoints": [
4
  {
5
  "steps": 49936,
6
+ "file_path": "results/SnowballTarget/SnowballTarget/SnowballTarget-49936.onnx",
7
+ "reward": 12.818181818181818,
8
+ "creation_time": 1686387589.7630868,
9
  "auxillary_file_paths": [
10
+ "results/SnowballTarget/SnowballTarget/SnowballTarget-49936.pt"
11
  ]
12
  },
13
  {
14
  "steps": 99960,
15
+ "file_path": "results/SnowballTarget/SnowballTarget/SnowballTarget-99960.onnx",
16
  "reward": 19.636363636363637,
17
+ "creation_time": 1686387708.8694067,
18
  "auxillary_file_paths": [
19
+ "results/SnowballTarget/SnowballTarget/SnowballTarget-99960.pt"
20
  ]
21
  },
22
  {
23
  "steps": 149984,
24
+ "file_path": "results/SnowballTarget/SnowballTarget/SnowballTarget-149984.onnx",
25
+ "reward": 23.181818181818183,
26
+ "creation_time": 1686387825.2703478,
27
  "auxillary_file_paths": [
28
+ "results/SnowballTarget/SnowballTarget/SnowballTarget-149984.pt"
29
  ]
30
  },
31
  {
32
  "steps": 199984,
33
+ "file_path": "results/SnowballTarget/SnowballTarget/SnowballTarget-199984.onnx",
34
+ "reward": 24.272727272727273,
35
+ "creation_time": 1686387940.3579473,
36
  "auxillary_file_paths": [
37
+ "results/SnowballTarget/SnowballTarget/SnowballTarget-199984.pt"
38
  ]
39
  },
40
  {
41
+ "steps": 200200,
42
+ "file_path": "results/SnowballTarget/SnowballTarget/SnowballTarget-200200.onnx",
43
+ "reward": 24.90909090909091,
44
+ "creation_time": 1686387940.5462108,
45
  "auxillary_file_paths": [
46
+ "results/SnowballTarget/SnowballTarget/SnowballTarget-200200.pt"
47
  ]
48
  }
49
  ],
50
  "final_checkpoint": {
51
+ "steps": 200200,
52
+ "file_path": "results/SnowballTarget/SnowballTarget.onnx",
53
+ "reward": 24.90909090909091,
54
+ "creation_time": 1686387940.5462108,
55
  "auxillary_file_paths": [
56
+ "results/SnowballTarget/SnowballTarget/SnowballTarget-200200.pt"
57
  ]
58
  }
59
  },