Hugging Face's logo

Musha-the-Yusha
/
ppo-SnowballTarget

Reinforcement Learning
ml-agents
TensorBoard
ONNX
unity-ml-agents
deep-reinforcement-learning
ML-Agents-SnowballTarget
Model card Files
xet
Metrics Community
Musha-the-Yusha commited on
Commit
c1ff913
·
1 Parent(s): 7d6dcdc

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-200112.onnx → SnowballTarget-200200.onnx} +1 -1
  7. SnowballTarget/{SnowballTarget-200112.pt → SnowballTarget-200200.pt} +1 -1
  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.1673725675.e384dee17cb4.2426.0 → events.out.tfevents.1673727111.e384dee17cb4.8656.0} +2 -2
  14. config.json +1 -1
  15. configuration.yaml +2 -2
  16. run_logs/Player-0.log +4 -7
  17. run_logs/timers.json +115 -115
  18. run_logs/training_status.json +26 -26
SnowballTarget.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4b3bac7c8fd64ef2ec76fe2ac5f7499a0862aae1b40dd1fc8949bb9f6658eb2b
3
  size 645119
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:04840d8f972f562e5cd01fdb458f53dd86a829c11bb06bb0270f938a8b4ec756
3
  size 645119
SnowballTarget/SnowballTarget-149984.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6489f7cf79aa59844a761785811a554ef092be0db326f2a93996cab6735edcdc
3
  size 645119
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a0bb5f4adddd233e2821d631cabd508f8d00efd3f3015fe46213449847b297f
3
  size 645119
SnowballTarget/SnowballTarget-149984.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d521f85106bed7499ed3fe02b111d319e697529c453fae3f2b9e92c8856bcc32
3
  size 3845312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ff775d2b901b2710f9d1ea632b6932a23ac689c315b70f6cc904c3522ca834c
3
  size 3845312
SnowballTarget/SnowballTarget-199984.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4b3bac7c8fd64ef2ec76fe2ac5f7499a0862aae1b40dd1fc8949bb9f6658eb2b
3
  size 645119
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:04840d8f972f562e5cd01fdb458f53dd86a829c11bb06bb0270f938a8b4ec756
3
  size 645119
SnowballTarget/SnowballTarget-199984.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a7d5cf0cbe8fbb75180bae883f8877a6fa41c967daaad3e70c24937e67605d25
3
  size 3845312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae6d436aa2e5f574c43606fb280e4ac3b5e0da13677aa6db436c3179ea613c6e
3
  size 3845312
SnowballTarget/{SnowballTarget-200112.onnx → SnowballTarget-200200.onnx} RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4b3bac7c8fd64ef2ec76fe2ac5f7499a0862aae1b40dd1fc8949bb9f6658eb2b
3
  size 645119
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:04840d8f972f562e5cd01fdb458f53dd86a829c11bb06bb0270f938a8b4ec756
3
  size 645119
SnowballTarget/{SnowballTarget-200112.pt → SnowballTarget-200200.pt} RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:272631d0d84a81bd3bc6841105b085b2ecf82b22cf12446e90a7c79656d69625
3
  size 3845312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6fdc882350208426c4e05f8a59cc2189e84b24df69761420b01932f6396f0d03
3
  size 3845312
SnowballTarget/SnowballTarget-49936.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ee164ebc81d7cfe43885af51a38e1d87a60bfdabd29bd5ec3d96239ebe363779
3
  size 645119
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c20ac704725bbca52eba09f412483d13bb711affa2a214ff93a2ae630faba54e
3
  size 645119
SnowballTarget/SnowballTarget-49936.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:04c60534356e8cdac651d389a9eccaada0197048cb32b0e36f15cc89735f565a
3
  size 3845312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d31dd42f4a03166c3bf476447791bf1d791c630c57aed3dee1009098fde97e38
3
  size 3845312
SnowballTarget/SnowballTarget-99960.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d643db350f26b9c1afaab8c424419ca6f270277b9555f4de7c0ca194f891693a
3
  size 645119
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:271e71d28366644dfb2650e12517b805579d3d0073e1eec3fdad16761fac4231
3
  size 645119
SnowballTarget/SnowballTarget-99960.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a00f21e3efb93a87000a07f0d2bee00f42cf1798c80e2f9346bf69f34007a229
3
  size 3845312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c45c0cd93b0b7cadea970a7a7632ff4594526d9a95e42a6d431fcae1013d07bb
3
  size 3845312
SnowballTarget/checkpoint.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:272631d0d84a81bd3bc6841105b085b2ecf82b22cf12446e90a7c79656d69625
3
  size 3845312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6fdc882350208426c4e05f8a59cc2189e84b24df69761420b01932f6396f0d03
3
  size 3845312
SnowballTarget/{events.out.tfevents.1673725675.e384dee17cb4.2426.0 → events.out.tfevents.1673727111.e384dee17cb4.8656.0} RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fed0d8005366fda1143728f6a27792aa653cbb9028ba32f3519491c145552eed
3
- size 28398
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5faafac70419711833bf6f28b471fb6644e28ec8698923115828b83641ca2e51
3
+ size 28094
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, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "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, "checkpoint_interval": 50000, "max_steps": 200000, "time_horizon": 64, "summary_freq": 10000, "threaded": true, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/SnowballTarget/SnowballTarget", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SnowballTarget1", "initialize_from": null, "load_model": false, "resume": false, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
 
1
+ {"default_settings": null, "behaviors": {"SnowballTarget": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "learning_rate": 0.0003, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "network_settings": {"normalize": false, "hidden_units": 256, "num_layers": 2, "vis_encode_type": "nature_cnn", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}}, "init_path": null, "keep_checkpoints": 10, "checkpoint_interval": 50000, "max_steps": 200000, "time_horizon": 64, "summary_freq": 10000, "threaded": true, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/SnowballTarget/SnowballTarget", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SnowballTarget-nature_cnn", "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
@@ -17,7 +17,7 @@ behaviors:
17
  normalize: false
18
  hidden_units: 256
19
  num_layers: 2
20
- vis_encode_type: simple
21
  memory: null
22
  goal_conditioning_type: hyper
23
  deterministic: false
@@ -62,7 +62,7 @@ engine_settings:
62
  no_graphics: true
63
  environment_parameters: null
64
  checkpoint_settings:
65
- run_id: SnowballTarget1
66
  initialize_from: null
67
  load_model: false
68
  resume: false
 
17
  normalize: false
18
  hidden_units: 256
19
  num_layers: 2
20
+ vis_encode_type: nature_cnn
21
  memory: null
22
  goal_conditioning_type: hyper
23
  deterministic: false
 
62
  no_graphics: true
63
  environment_parameters: null
64
  checkpoint_settings:
65
+ run_id: SnowballTarget-nature_cnn
66
  initialize_from: null
67
  load_model: false
68
  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:2495:(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 0.074 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: 0.604764 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 34
173
  [ALLOC_BUCKET]
174
  Large Block size 4.0 MB
175
  Used Block count 1
@@ -213,7 +210,7 @@ Memory Statistics:
213
  Used Block count 1
214
  Peak Allocated bytes 0.9 MB
215
  [ALLOC_GFX_MAIN]
216
- Peak usage frame count: [32.0 KB-64.0 KB]: 4695 frames, [64.0 KB-128.0 KB]: 766 frames
217
  Requested Block Size 16.0 MB
218
  Peak Block count 1
219
  Peak Allocated memory 66.4 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 0.086 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: 0.624752 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 33
170
  [ALLOC_BUCKET]
171
  Large Block size 4.0 MB
172
  Used Block count 1
 
210
  Used Block count 1
211
  Peak Allocated bytes 0.9 MB
212
  [ALLOC_GFX_MAIN]
213
+ Peak usage frame count: [32.0 KB-64.0 KB]: 5145 frames, [64.0 KB-128.0 KB]: 316 frames
214
  Requested Block Size 16.0 MB
215
  Peak Block count 1
216
  Peak Allocated memory 66.4 KB
run_logs/timers.json CHANGED
@@ -2,15 +2,15 @@
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
- "value": 0.9947798848152161,
6
- "min": 0.9947798848152161,
7
- "max": 2.865860939025879,
8
  "count": 20
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
- "value": 9498.158203125,
12
- "min": 9498.158203125,
13
- "max": 29349.28125,
14
  "count": 20
15
  },
16
  "SnowballTarget.Step.mean": {
@@ -26,15 +26,15 @@
26
  "count": 20
27
  },
28
  "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
- "value": 12.572388648986816,
30
- "min": 0.528537392616272,
31
- "max": 12.572388648986816,
32
  "count": 20
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
- "value": 2451.61572265625,
36
- "min": 102.5362548828125,
37
- "max": 2510.642333984375,
38
  "count": 20
39
  },
40
  "SnowballTarget.Environment.EpisodeLength.mean": {
@@ -50,27 +50,27 @@
50
  "count": 20
51
  },
52
  "SnowballTarget.Losses.PolicyLoss.mean": {
53
- "value": 0.06834656691286874,
54
- "min": 0.06264792513798502,
55
- "max": 0.07698864114808666,
56
  "count": 20
57
  },
58
  "SnowballTarget.Losses.PolicyLoss.sum": {
59
- "value": 0.27338626765147495,
60
- "min": 0.2505917005519401,
61
- "max": 0.36924396927797176,
62
  "count": 20
63
  },
64
  "SnowballTarget.Losses.ValueLoss.mean": {
65
- "value": 0.2041589637451312,
66
- "min": 0.11432847374589092,
67
- "max": 0.26253485621190537,
68
  "count": 20
69
  },
70
  "SnowballTarget.Losses.ValueLoss.sum": {
71
- "value": 0.8166358549805248,
72
- "min": 0.4573138949835637,
73
- "max": 1.3126742810595269,
74
  "count": 20
75
  },
76
  "SnowballTarget.Policy.LearningRate.mean": {
@@ -110,27 +110,27 @@
110
  "count": 20
111
  },
112
  "SnowballTarget.Environment.CumulativeReward.mean": {
113
- "value": 25.5,
114
- "min": 2.909090909090909,
115
- "max": 25.5,
116
  "count": 20
117
  },
118
  "SnowballTarget.Environment.CumulativeReward.sum": {
119
- "value": 1122.0,
120
- "min": 128.0,
121
- "max": 1375.0,
122
  "count": 20
123
  },
124
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
- "value": 25.5,
126
- "min": 2.909090909090909,
127
- "max": 25.5,
128
  "count": 20
129
  },
130
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
- "value": 1122.0,
132
- "min": 128.0,
133
- "max": 1375.0,
134
  "count": 20
135
  },
136
  "SnowballTarget.IsTraining.mean": {
@@ -148,74 +148,74 @@
148
  },
149
  "metadata": {
150
  "timer_format_version": "0.1.0",
151
- "start_time_seconds": "1673725668",
152
  "python_version": "3.8.16 (default, Dec 7 2022, 01:12:13) \n[GCC 7.5.0]",
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": "0.29.0.dev0",
155
  "mlagents_envs_version": "0.29.0.dev0",
156
  "communication_protocol_version": "1.5.0",
157
  "pytorch_version": "1.8.1+cu102",
158
  "numpy_version": "1.21.6",
159
- "end_time_seconds": "1673726090"
160
  },
161
- "total": 422.12217210899996,
162
  "count": 1,
163
- "self": 0.38375494999991133,
164
  "children": {
165
  "run_training.setup": {
166
- "total": 0.10594863799997256,
167
  "count": 1,
168
- "self": 0.10594863799997256
169
  },
170
  "TrainerController.start_learning": {
171
- "total": 421.6324685210001,
172
  "count": 1,
173
- "self": 0.4890895760049716,
174
  "children": {
175
  "TrainerController._reset_env": {
176
- "total": 10.021658269,
177
  "count": 1,
178
- "self": 10.021658269
179
  },
180
  "TrainerController.advance": {
181
- "total": 411.0064559659952,
182
- "count": 18202,
183
- "self": 0.2699875979925537,
184
  "children": {
185
  "env_step": {
186
- "total": 410.73646836800265,
187
- "count": 18202,
188
- "self": 266.9627976130055,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
- "total": 143.51332598099714,
192
- "count": 18202,
193
- "self": 1.3264392839944321,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
- "total": 142.1868866970027,
197
- "count": 18202,
198
- "self": 31.655224240999246,
199
  "children": {
200
  "TorchPolicy.sample_actions": {
201
- "total": 110.53166245600346,
202
- "count": 18202,
203
- "self": 110.53166245600346
204
  }
205
  }
206
  }
207
  }
208
  },
209
  "workers": {
210
- "total": 0.260344774000032,
211
- "count": 18202,
212
  "self": 0.0,
213
  "children": {
214
  "worker_root": {
215
- "total": 420.44029482200347,
216
- "count": 18202,
217
  "is_parallel": true,
218
- "self": 205.9397554499892,
219
  "children": {
220
  "run_training.setup": {
221
  "total": 0.0,
@@ -224,48 +224,48 @@
224
  "self": 0.0,
225
  "children": {
226
  "steps_from_proto": {
227
- "total": 0.016465992000007645,
228
  "count": 1,
229
  "is_parallel": true,
230
- "self": 0.009812255000156256,
231
  "children": {
232
  "_process_rank_one_or_two_observation": {
233
- "total": 0.0066537369998513896,
234
  "count": 10,
235
  "is_parallel": true,
236
- "self": 0.0066537369998513896
237
  }
238
  }
239
  },
240
  "UnityEnvironment.step": {
241
- "total": 0.04087618099993051,
242
  "count": 1,
243
  "is_parallel": true,
244
- "self": 0.00043687099991984724,
245
  "children": {
246
  "UnityEnvironment._generate_step_input": {
247
- "total": 0.000310231000071326,
248
  "count": 1,
249
  "is_parallel": true,
250
- "self": 0.000310231000071326
251
  },
252
  "communicator.exchange": {
253
- "total": 0.038586151000004065,
254
  "count": 1,
255
  "is_parallel": true,
256
- "self": 0.038586151000004065
257
  },
258
  "steps_from_proto": {
259
- "total": 0.001542927999935273,
260
  "count": 1,
261
  "is_parallel": true,
262
- "self": 0.00036484700001437886,
263
  "children": {
264
  "_process_rank_one_or_two_observation": {
265
- "total": 0.001178080999920894,
266
  "count": 10,
267
  "is_parallel": true,
268
- "self": 0.001178080999920894
269
  }
270
  }
271
  }
@@ -274,34 +274,34 @@
274
  }
275
  },
276
  "UnityEnvironment.step": {
277
- "total": 214.50053937201426,
278
- "count": 18201,
279
  "is_parallel": true,
280
- "self": 8.408719294013054,
281
  "children": {
282
  "UnityEnvironment._generate_step_input": {
283
- "total": 4.980733927001438,
284
- "count": 18201,
285
  "is_parallel": true,
286
- "self": 4.980733927001438
287
  },
288
  "communicator.exchange": {
289
- "total": 171.6940063809983,
290
- "count": 18201,
291
  "is_parallel": true,
292
- "self": 171.6940063809983
293
  },
294
  "steps_from_proto": {
295
- "total": 29.417079770001465,
296
- "count": 18201,
297
  "is_parallel": true,
298
- "self": 6.273460777001787,
299
  "children": {
300
  "_process_rank_one_or_two_observation": {
301
- "total": 23.143618992999677,
302
- "count": 182010,
303
  "is_parallel": true,
304
- "self": 23.143618992999677
305
  }
306
  }
307
  }
@@ -316,9 +316,9 @@
316
  }
317
  },
318
  "trainer_threads": {
319
- "total": 4.172699993887363e-05,
320
  "count": 1,
321
- "self": 4.172699993887363e-05,
322
  "children": {
323
  "thread_root": {
324
  "total": 0.0,
@@ -327,36 +327,36 @@
327
  "self": 0.0,
328
  "children": {
329
  "trainer_advance": {
330
- "total": 408.146657900008,
331
- "count": 332664,
332
  "is_parallel": true,
333
- "self": 8.65442758201857,
334
  "children": {
335
  "process_trajectory": {
336
- "total": 233.04696325298994,
337
- "count": 332664,
338
  "is_parallel": true,
339
- "self": 232.32474822599022,
340
  "children": {
341
  "RLTrainer._checkpoint": {
342
- "total": 0.7222150269997201,
343
  "count": 4,
344
  "is_parallel": true,
345
- "self": 0.7222150269997201
346
  }
347
  }
348
  },
349
  "_update_policy": {
350
- "total": 166.44526706499948,
351
  "count": 90,
352
  "is_parallel": true,
353
- "self": 43.7430472239995,
354
  "children": {
355
  "TorchPPOOptimizer.update": {
356
- "total": 122.70221984099999,
357
- "count": 4584,
358
  "is_parallel": true,
359
- "self": 122.70221984099999
360
  }
361
  }
362
  }
@@ -367,14 +367,14 @@
367
  }
368
  },
369
  "TrainerController._save_models": {
370
- "total": 0.11522298299996692,
371
  "count": 1,
372
- "self": 0.0008103459999801998,
373
  "children": {
374
  "RLTrainer._checkpoint": {
375
- "total": 0.11441263699998672,
376
  "count": 1,
377
- "self": 0.11441263699998672
378
  }
379
  }
380
  }
 
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
+ "value": 0.9268479943275452,
6
+ "min": 0.9268479943275452,
7
+ "max": 2.872371196746826,
8
  "count": 20
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
+ "value": 8849.544921875,
12
+ "min": 8849.544921875,
13
+ "max": 29415.953125,
14
  "count": 20
15
  },
16
  "SnowballTarget.Step.mean": {
 
26
  "count": 20
27
  },
28
  "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
+ "value": 12.850757598876953,
30
+ "min": 0.49157002568244934,
31
+ "max": 12.850757598876953,
32
  "count": 20
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
+ "value": 2505.897705078125,
36
+ "min": 95.36458587646484,
37
+ "max": 2593.2705078125,
38
  "count": 20
39
  },
40
  "SnowballTarget.Environment.EpisodeLength.mean": {
 
50
  "count": 20
51
  },
52
  "SnowballTarget.Losses.PolicyLoss.mean": {
53
+ "value": 0.0722709397943582,
54
+ "min": 0.0640588521939136,
55
+ "max": 0.0761550700556779,
56
  "count": 20
57
  },
58
  "SnowballTarget.Losses.PolicyLoss.sum": {
59
+ "value": 0.2890837591774328,
60
+ "min": 0.25934755381896657,
61
+ "max": 0.3616007176183213,
62
  "count": 20
63
  },
64
  "SnowballTarget.Losses.ValueLoss.mean": {
65
+ "value": 0.1863731088518512,
66
+ "min": 0.1267329887509821,
67
+ "max": 0.2944844097775572,
68
  "count": 20
69
  },
70
  "SnowballTarget.Losses.ValueLoss.sum": {
71
+ "value": 0.7454924354074048,
72
+ "min": 0.5069319550039284,
73
+ "max": 1.3869839334020426,
74
  "count": 20
75
  },
76
  "SnowballTarget.Policy.LearningRate.mean": {
 
110
  "count": 20
111
  },
112
  "SnowballTarget.Environment.CumulativeReward.mean": {
113
+ "value": 25.681818181818183,
114
+ "min": 3.727272727272727,
115
+ "max": 25.681818181818183,
116
  "count": 20
117
  },
118
  "SnowballTarget.Environment.CumulativeReward.sum": {
119
+ "value": 1130.0,
120
+ "min": 164.0,
121
+ "max": 1392.0,
122
  "count": 20
123
  },
124
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
+ "value": 25.681818181818183,
126
+ "min": 3.727272727272727,
127
+ "max": 25.681818181818183,
128
  "count": 20
129
  },
130
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
+ "value": 1130.0,
132
+ "min": 164.0,
133
+ "max": 1392.0,
134
  "count": 20
135
  },
136
  "SnowballTarget.IsTraining.mean": {
 
148
  },
149
  "metadata": {
150
  "timer_format_version": "0.1.0",
151
+ "start_time_seconds": "1673727108",
152
  "python_version": "3.8.16 (default, Dec 7 2022, 01:12:13) \n[GCC 7.5.0]",
153
+ "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget-nature_cnn --no-graphics",
154
  "mlagents_version": "0.29.0.dev0",
155
  "mlagents_envs_version": "0.29.0.dev0",
156
  "communication_protocol_version": "1.5.0",
157
  "pytorch_version": "1.8.1+cu102",
158
  "numpy_version": "1.21.6",
159
+ "end_time_seconds": "1673727533"
160
  },
161
+ "total": 424.89689197999996,
162
  "count": 1,
163
+ "self": 0.4229490420000275,
164
  "children": {
165
  "run_training.setup": {
166
+ "total": 0.1093391540000539,
167
  "count": 1,
168
+ "self": 0.1093391540000539
169
  },
170
  "TrainerController.start_learning": {
171
+ "total": 424.3646037839999,
172
  "count": 1,
173
+ "self": 0.515026282022518,
174
  "children": {
175
  "TrainerController._reset_env": {
176
+ "total": 6.164795256999923,
177
  "count": 1,
178
+ "self": 6.164795256999923
179
  },
180
  "TrainerController.advance": {
181
+ "total": 417.55850797497783,
182
+ "count": 18201,
183
+ "self": 0.25266607996672974,
184
  "children": {
185
  "env_step": {
186
+ "total": 417.3058418950111,
187
+ "count": 18201,
188
+ "self": 272.70386744500183,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
+ "total": 144.33831795802598,
192
+ "count": 18201,
193
+ "self": 1.3555206449827892,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
+ "total": 142.9827973130432,
197
+ "count": 18201,
198
+ "self": 31.8605759190732,
199
  "children": {
200
  "TorchPolicy.sample_actions": {
201
+ "total": 111.12222139397,
202
+ "count": 18201,
203
+ "self": 111.12222139397
204
  }
205
  }
206
  }
207
  }
208
  },
209
  "workers": {
210
+ "total": 0.26365649198328356,
211
+ "count": 18201,
212
  "self": 0.0,
213
  "children": {
214
  "worker_root": {
215
+ "total": 423.1508067570253,
216
+ "count": 18201,
217
  "is_parallel": true,
218
+ "self": 203.34157348599274,
219
  "children": {
220
  "run_training.setup": {
221
  "total": 0.0,
 
224
  "self": 0.0,
225
  "children": {
226
  "steps_from_proto": {
227
+ "total": 0.0019309989997964294,
228
  "count": 1,
229
  "is_parallel": true,
230
+ "self": 0.000678426999684234,
231
  "children": {
232
  "_process_rank_one_or_two_observation": {
233
+ "total": 0.0012525720001121954,
234
  "count": 10,
235
  "is_parallel": true,
236
+ "self": 0.0012525720001121954
237
  }
238
  }
239
  },
240
  "UnityEnvironment.step": {
241
+ "total": 0.04584217100000387,
242
  "count": 1,
243
  "is_parallel": true,
244
+ "self": 0.0005011769999327953,
245
  "children": {
246
  "UnityEnvironment._generate_step_input": {
247
+ "total": 0.0003017870001258416,
248
  "count": 1,
249
  "is_parallel": true,
250
+ "self": 0.0003017870001258416
251
  },
252
  "communicator.exchange": {
253
+ "total": 0.0430484080000042,
254
  "count": 1,
255
  "is_parallel": true,
256
+ "self": 0.0430484080000042
257
  },
258
  "steps_from_proto": {
259
+ "total": 0.0019907989999410347,
260
  "count": 1,
261
  "is_parallel": true,
262
+ "self": 0.00048542200011070236,
263
  "children": {
264
  "_process_rank_one_or_two_observation": {
265
+ "total": 0.0015053769998303324,
266
  "count": 10,
267
  "is_parallel": true,
268
+ "self": 0.0015053769998303324
269
  }
270
  }
271
  }
 
274
  }
275
  },
276
  "UnityEnvironment.step": {
277
+ "total": 219.80923327103255,
278
+ "count": 18200,
279
  "is_parallel": true,
280
+ "self": 8.326347810035486,
281
  "children": {
282
  "UnityEnvironment._generate_step_input": {
283
+ "total": 4.811132445990779,
284
+ "count": 18200,
285
  "is_parallel": true,
286
+ "self": 4.811132445990779
287
  },
288
  "communicator.exchange": {
289
+ "total": 174.3423243809707,
290
+ "count": 18200,
291
  "is_parallel": true,
292
+ "self": 174.3423243809707
293
  },
294
  "steps_from_proto": {
295
+ "total": 32.329428634035594,
296
+ "count": 18200,
297
  "is_parallel": true,
298
+ "self": 6.520087415919988,
299
  "children": {
300
  "_process_rank_one_or_two_observation": {
301
+ "total": 25.809341218115605,
302
+ "count": 182000,
303
  "is_parallel": true,
304
+ "self": 25.809341218115605
305
  }
306
  }
307
  }
 
316
  }
317
  },
318
  "trainer_threads": {
319
+ "total": 4.3527999878278933e-05,
320
  "count": 1,
321
+ "self": 4.3527999878278933e-05,
322
  "children": {
323
  "thread_root": {
324
  "total": 0.0,
 
327
  "self": 0.0,
328
  "children": {
329
  "trainer_advance": {
330
+ "total": 414.81130502598194,
331
+ "count": 326572,
332
  "is_parallel": true,
333
+ "self": 8.523008061926248,
334
  "children": {
335
  "process_trajectory": {
336
+ "total": 236.09358654105517,
337
+ "count": 326572,
338
  "is_parallel": true,
339
+ "self": 235.37957152105537,
340
  "children": {
341
  "RLTrainer._checkpoint": {
342
+ "total": 0.7140150199998061,
343
  "count": 4,
344
  "is_parallel": true,
345
+ "self": 0.7140150199998061
346
  }
347
  }
348
  },
349
  "_update_policy": {
350
+ "total": 170.19471042300052,
351
  "count": 90,
352
  "is_parallel": true,
353
+ "self": 44.2483758919966,
354
  "children": {
355
  "TorchPPOOptimizer.update": {
356
+ "total": 125.94633453100391,
357
+ "count": 4587,
358
  "is_parallel": true,
359
+ "self": 125.94633453100391
360
  }
361
  }
362
  }
 
367
  }
368
  },
369
  "TrainerController._save_models": {
370
+ "total": 0.12623074199973416,
371
  "count": 1,
372
+ "self": 0.0008290529995065299,
373
  "children": {
374
  "RLTrainer._checkpoint": {
375
+ "total": 0.12540168900022763,
376
  "count": 1,
377
+ "self": 0.12540168900022763
378
  }
379
  }
380
  }
run_logs/training_status.json CHANGED
@@ -3,57 +3,57 @@
3
  "checkpoints": [
4
  {
5
  "steps": 49936,
6
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.onnx",
7
- "reward": 12.0,
8
- "creation_time": 1673725781.3693237,
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": 20.818181818181817,
17
- "creation_time": 1673725884.5831916,
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": 22.818181818181817,
26
- "creation_time": 1673725988.17631,
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": 25.545454545454547,
35
- "creation_time": 1673726089.9148178,
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": 25.545454545454547,
44
- "creation_time": 1673726090.0669014,
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": 25.545454545454547,
54
- "creation_time": 1673726090.0669014,
55
  "auxillary_file_paths": [
56
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
57
  ]
58
  }
59
  },
 
3
  "checkpoints": [
4
  {
5
  "steps": 49936,
6
+ "file_path": "results/SnowballTarget-nature_cnn/SnowballTarget/SnowballTarget-49936.onnx",
7
+ "reward": 14.909090909090908,
8
+ "creation_time": 1673727218.8253741,
9
  "auxillary_file_paths": [
10
+ "results/SnowballTarget-nature_cnn/SnowballTarget/SnowballTarget-49936.pt"
11
  ]
12
  },
13
  {
14
  "steps": 99960,
15
+ "file_path": "results/SnowballTarget-nature_cnn/SnowballTarget/SnowballTarget-99960.onnx",
16
+ "reward": 23.09090909090909,
17
+ "creation_time": 1673727323.8906903,
18
  "auxillary_file_paths": [
19
+ "results/SnowballTarget-nature_cnn/SnowballTarget/SnowballTarget-99960.pt"
20
  ]
21
  },
22
  {
23
  "steps": 149984,
24
+ "file_path": "results/SnowballTarget-nature_cnn/SnowballTarget/SnowballTarget-149984.onnx",
25
+ "reward": 24.0,
26
+ "creation_time": 1673727429.1525705,
27
  "auxillary_file_paths": [
28
+ "results/SnowballTarget-nature_cnn/SnowballTarget/SnowballTarget-149984.pt"
29
  ]
30
  },
31
  {
32
  "steps": 199984,
33
+ "file_path": "results/SnowballTarget-nature_cnn/SnowballTarget/SnowballTarget-199984.onnx",
34
+ "reward": 25.90909090909091,
35
+ "creation_time": 1673727533.0744307,
36
  "auxillary_file_paths": [
37
+ "results/SnowballTarget-nature_cnn/SnowballTarget/SnowballTarget-199984.pt"
38
  ]
39
  },
40
  {
41
+ "steps": 200200,
42
+ "file_path": "results/SnowballTarget-nature_cnn/SnowballTarget/SnowballTarget-200200.onnx",
43
+ "reward": 24.90909090909091,
44
+ "creation_time": 1673727533.253759,
45
  "auxillary_file_paths": [
46
+ "results/SnowballTarget-nature_cnn/SnowballTarget/SnowballTarget-200200.pt"
47
  ]
48
  }
49
  ],
50
  "final_checkpoint": {
51
+ "steps": 200200,
52
+ "file_path": "results/SnowballTarget-nature_cnn/SnowballTarget.onnx",
53
+ "reward": 24.90909090909091,
54
+ "creation_time": 1673727533.253759,
55
  "auxillary_file_paths": [
56
+ "results/SnowballTarget-nature_cnn/SnowballTarget/SnowballTarget-200200.pt"
57
  ]
58
  }
59
  },