voyzan commited on
Commit
c28610d
1 Parent(s): e9bfd24
SnowballTarget.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5edb4f53411dd7fb34a5fd60ccc6b42988727d6faea2e6ae1a014b2b9c034712
3
  size 326963
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc1db10ba95558b18d2cd408b03b1cd9337223a534e3ceb1f1d10f0bc442d5e5
3
  size 326963
SnowballTarget/SnowballTarget-149984.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c70e5d048019add6698441063e43910f041071142a3bb4222810f1af8b7ec321
3
+ size 326963
SnowballTarget/SnowballTarget-149984.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb0f22094fb05e1ec05f155c2aaba5b2439e2d1424a9e74e942521c3c66ac725
3
+ size 1938524
SnowballTarget/SnowballTarget-199984.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc1db10ba95558b18d2cd408b03b1cd9337223a534e3ceb1f1d10f0bc442d5e5
3
+ size 326963
SnowballTarget/SnowballTarget-199984.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:75826463ed21e9ff95f52126931f04d7ee672e75089d7153be85cab8fc05c75c
3
+ size 1938524
SnowballTarget/SnowballTarget-200112.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc1db10ba95558b18d2cd408b03b1cd9337223a534e3ceb1f1d10f0bc442d5e5
3
+ size 326963
SnowballTarget/SnowballTarget-200112.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc56d3fb4ef72e5649488db05eabc96b042a2bae13a4ce682ede131e06895362
3
+ size 1938524
SnowballTarget/SnowballTarget-49936.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d0c775894399684c28722f0ddd77848f24c793715c7afa6763213fff7bc25775
3
+ size 326963
SnowballTarget/SnowballTarget-49936.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b6b49154f4bbaae0c0c4a1cbc54e1531a1dc8522e55435139f8c4990e33a00e0
3
+ size 1938524
SnowballTarget/SnowballTarget-99960.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a851c2c735210278f6b1a9a566f066e9fe9485fc36ee9e821910926a8bbe7c9b
3
+ size 326963
SnowballTarget/SnowballTarget-99960.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99c144ffbe8145e577c5c9fbdfa493427ff8fe6e401f1d4ceebf439e42ec0d0d
3
+ size 1938524
SnowballTarget/checkpoint.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:492c3e3682251f7eb2f60e31854f3cb9bd4678e7d230f74d91cc7f571f440c39
3
  size 1938524
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc56d3fb4ef72e5649488db05eabc96b042a2bae13a4ce682ede131e06895362
3
  size 1938524
SnowballTarget/events.out.tfevents.1694195608.928acc295e7e.7575.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f0b24ae30951e2705e05b12ea5ad7d5e9c577b63543fbc1ffd9c22f6f11ffad6
3
+ size 28590
config.json CHANGED
@@ -1 +1 @@
1
- {"default_settings": null, "behaviors": {"SnowballTarget": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 256, "buffer_size": 4096, "learning_rate": 0.0003, "beta": 0.005, "epsilon": 0.25, "lambd": 0.93, "num_epoch": 4, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 50000, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 3, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.95, "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": 10000, "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": 256, "buffer_size": 4096, "learning_rate": 0.0003, "beta": 0.005, "epsilon": 0.25, "lambd": 0.93, "num_epoch": 4, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 50000, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 3, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.95, "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": "SnowballTarget2", "initialize_from": null, "load_model": false, "resume": false, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
configuration.yaml CHANGED
@@ -38,7 +38,7 @@ behaviors:
38
  init_path: null
39
  keep_checkpoints: 10
40
  even_checkpoints: false
41
- max_steps: 10000
42
  time_horizon: 64
43
  summary_freq: 10000
44
  threaded: true
@@ -64,7 +64,7 @@ engine_settings:
64
  no_graphics: true
65
  environment_parameters: null
66
  checkpoint_settings:
67
- run_id: SnowballTarget1
68
  initialize_from: null
69
  load_model: false
70
  resume: false
 
38
  init_path: null
39
  keep_checkpoints: 10
40
  even_checkpoints: false
41
+ max_steps: 200000
42
  time_horizon: 64
43
  summary_freq: 10000
44
  threaded: true
 
64
  no_graphics: true
65
  environment_parameters: null
66
  checkpoint_settings:
67
+ run_id: SnowballTarget2
68
  initialize_from: null
69
  load_model: false
70
  resume: false
run_logs/Player-0.log CHANGED
@@ -2,9 +2,6 @@ Mono path[0] = '/content/ml-agents/training-envs-executables/linux/SnowballTarge
2
  Mono config path = '/content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/MonoBleedingEdge/etc'
3
  Preloaded 'lib_burst_generated.so'
4
  Preloaded 'libgrpc_csharp_ext.x64.so'
5
- PlayerPrefs - Creating folder: /root/.config/unity3d/Hugging Face
6
- PlayerPrefs - Creating folder: /root/.config/unity3d/Hugging Face/SnowballTarget
7
- Unable to load player prefs
8
  Initialize engine version: 2021.3.14f1 (eee1884e7226)
9
  [Subsystems] Discovering subsystems at path /content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/UnitySubsystems
10
  Forcing GfxDevice: Null
@@ -34,7 +31,7 @@ ALSA lib pcm.c:2664:(snd_pcm_open_noupdate) Unknown PCM default
34
  FMOD failed to initialize the output device.: "Error initializing output device. " (60)
35
  FMOD initialized on nosound output
36
  Begin MonoManager ReloadAssembly
37
- - Completed reload, in 0.081 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: 0.642858 ms
49
  ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
50
  requesting resize 84 x 84
51
  Setting up 1 worker threads for Enlighten.
@@ -53,7 +50,7 @@ Memory Statistics:
53
  [ALLOC_TEMP_TLS] TLS Allocator
54
  StackAllocators :
55
  [ALLOC_TEMP_MAIN]
56
- Peak usage frame count: [8.0 KB-16.0 KB]: 276 frames, [16.0 KB-32.0 KB]: 4 frames, [2.0 MB-4.0 MB]: 1 frames
57
  Initial Block Size 4.0 MB
58
  Current Block Size 4.0 MB
59
  Peak Allocated Bytes 2.0 MB
@@ -169,19 +166,19 @@ Memory Statistics:
169
  Peak Allocated Bytes 0 B
170
  Overflow Count 0
171
  [ALLOC_DEFAULT] Dual Thread Allocator
172
- Peak main deferred allocation count 32
173
  [ALLOC_BUCKET]
174
  Large Block size 4.0 MB
175
  Used Block count 1
176
  Peak Allocated bytes 1.0 MB
177
  [ALLOC_DEFAULT_MAIN]
178
- Peak usage frame count: [4.0 MB-8.0 MB]: 281 frames
179
  Requested Block Size 16.0 MB
180
  Peak Block count 1
181
- Peak Allocated memory 5.2 MB
182
  Peak Large allocation bytes 0 B
183
  [ALLOC_DEFAULT_THREAD]
184
- Peak usage frame count: [16.0 MB-32.0 MB]: 281 frames
185
  Requested Block Size 16.0 MB
186
  Peak Block count 1
187
  Peak Allocated memory 17.8 MB
@@ -213,13 +210,13 @@ Memory Statistics:
213
  Used Block count 1
214
  Peak Allocated bytes 1.0 MB
215
  [ALLOC_GFX_MAIN]
216
- Peak usage frame count: [32.0 KB-64.0 KB]: 257 frames, [64.0 KB-128.0 KB]: 24 frames
217
  Requested Block Size 16.0 MB
218
  Peak Block count 1
219
  Peak Allocated memory 66.4 KB
220
  Peak Large allocation bytes 0 B
221
  [ALLOC_GFX_THREAD]
222
- Peak usage frame count: [32.0 KB-64.0 KB]: 281 frames
223
  Requested Block Size 16.0 MB
224
  Peak Block count 1
225
  Peak Allocated memory 39.6 KB
@@ -231,13 +228,13 @@ Memory Statistics:
231
  Used Block count 1
232
  Peak Allocated bytes 1.0 MB
233
  [ALLOC_CACHEOBJECTS_MAIN]
234
- Peak usage frame count: [0.5 MB-1.0 MB]: 281 frames
235
  Requested Block Size 4.0 MB
236
  Peak Block count 1
237
  Peak Allocated memory 0.6 MB
238
  Peak Large allocation bytes 0 B
239
  [ALLOC_CACHEOBJECTS_THREAD]
240
- Peak usage frame count: [0.5 MB-1.0 MB]: 280 frames, [2.0 MB-4.0 MB]: 1 frames
241
  Requested Block Size 4.0 MB
242
  Peak Block count 1
243
  Peak Allocated memory 2.2 MB
@@ -249,13 +246,13 @@ Memory Statistics:
249
  Used Block count 1
250
  Peak Allocated bytes 1.0 MB
251
  [ALLOC_TYPETREE_MAIN]
252
- Peak usage frame count: [0-1.0 KB]: 281 frames
253
  Requested Block Size 2.0 MB
254
  Peak Block count 1
255
  Peak Allocated memory 1.0 KB
256
  Peak Large allocation bytes 0 B
257
  [ALLOC_TYPETREE_THREAD]
258
- Peak usage frame count: [1.0 KB-2.0 KB]: 281 frames
259
  Requested Block Size 2.0 MB
260
  Peak Block count 1
261
  Peak Allocated memory 1.7 KB
 
2
  Mono config path = '/content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/MonoBleedingEdge/etc'
3
  Preloaded 'lib_burst_generated.so'
4
  Preloaded 'libgrpc_csharp_ext.x64.so'
 
 
 
5
  Initialize engine version: 2021.3.14f1 (eee1884e7226)
6
  [Subsystems] Discovering subsystems at path /content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/UnitySubsystems
7
  Forcing GfxDevice: Null
 
31
  FMOD failed to initialize the output device.: "Error initializing output device. " (60)
32
  FMOD initialized on nosound output
33
  Begin MonoManager ReloadAssembly
34
+ - Completed reload, in 0.085 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: 0.626587 ms
46
  ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
47
  requesting resize 84 x 84
48
  Setting up 1 worker threads for Enlighten.
 
50
  [ALLOC_TEMP_TLS] TLS Allocator
51
  StackAllocators :
52
  [ALLOC_TEMP_MAIN]
53
+ Peak usage frame count: [8.0 KB-16.0 KB]: 5369 frames, [16.0 KB-32.0 KB]: 91 frames, [2.0 MB-4.0 MB]: 1 frames
54
  Initial Block Size 4.0 MB
55
  Current Block Size 4.0 MB
56
  Peak Allocated Bytes 2.0 MB
 
166
  Peak Allocated Bytes 0 B
167
  Overflow Count 0
168
  [ALLOC_DEFAULT] Dual Thread Allocator
169
+ Peak main deferred allocation count 41
170
  [ALLOC_BUCKET]
171
  Large Block size 4.0 MB
172
  Used Block count 1
173
  Peak Allocated bytes 1.0 MB
174
  [ALLOC_DEFAULT_MAIN]
175
+ Peak usage frame count: [4.0 MB-8.0 MB]: 5461 frames
176
  Requested Block Size 16.0 MB
177
  Peak Block count 1
178
+ Peak Allocated memory 6.6 MB
179
  Peak Large allocation bytes 0 B
180
  [ALLOC_DEFAULT_THREAD]
181
+ Peak usage frame count: [16.0 MB-32.0 MB]: 5461 frames
182
  Requested Block Size 16.0 MB
183
  Peak Block count 1
184
  Peak Allocated memory 17.8 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]: 4613 frames, [64.0 KB-128.0 KB]: 848 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]: 5461 frames
220
  Requested Block Size 16.0 MB
221
  Peak Block count 1
222
  Peak Allocated memory 39.6 KB
 
228
  Used Block count 1
229
  Peak Allocated bytes 1.0 MB
230
  [ALLOC_CACHEOBJECTS_MAIN]
231
+ Peak usage frame count: [0.5 MB-1.0 MB]: 5461 frames
232
  Requested Block Size 4.0 MB
233
  Peak Block count 1
234
  Peak Allocated memory 0.6 MB
235
  Peak Large allocation bytes 0 B
236
  [ALLOC_CACHEOBJECTS_THREAD]
237
+ Peak usage frame count: [0.5 MB-1.0 MB]: 5460 frames, [2.0 MB-4.0 MB]: 1 frames
238
  Requested Block Size 4.0 MB
239
  Peak Block count 1
240
  Peak Allocated memory 2.2 MB
 
246
  Used Block count 1
247
  Peak Allocated bytes 1.0 MB
248
  [ALLOC_TYPETREE_MAIN]
249
+ Peak usage frame count: [0-1.0 KB]: 5461 frames
250
  Requested Block Size 2.0 MB
251
  Peak Block count 1
252
  Peak Allocated memory 1.0 KB
253
  Peak Large allocation bytes 0 B
254
  [ALLOC_TYPETREE_THREAD]
255
+ Peak usage frame count: [1.0 KB-2.0 KB]: 5461 frames
256
  Requested Block Size 2.0 MB
257
  Peak Block count 1
258
  Peak Allocated memory 1.7 KB
run_logs/timers.json CHANGED
@@ -2,213 +2,213 @@
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
- "value": 2.8894050121307373,
6
- "min": 2.8894050121307373,
7
- "max": 2.8894050121307373,
8
- "count": 1
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
- "value": 29653.96484375,
12
- "min": 29653.96484375,
13
- "max": 29653.96484375,
14
- "count": 1
15
  },
16
  "SnowballTarget.Step.mean": {
17
- "value": 9952.0,
18
  "min": 9952.0,
19
- "max": 9952.0,
20
- "count": 1
21
  },
22
  "SnowballTarget.Step.sum": {
23
- "value": 9952.0,
24
  "min": 9952.0,
25
- "max": 9952.0,
26
- "count": 1
27
  },
28
  "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
- "value": 0.07252310961484909,
30
- "min": 0.07252310961484909,
31
- "max": 0.07252310961484909,
32
- "count": 1
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
- "value": 14.069483757019043,
36
- "min": 14.069483757019043,
37
- "max": 14.069483757019043,
38
- "count": 1
39
  },
40
  "SnowballTarget.Environment.EpisodeLength.mean": {
41
  "value": 199.0,
42
  "min": 199.0,
43
  "max": 199.0,
44
- "count": 1
45
  },
46
  "SnowballTarget.Environment.EpisodeLength.sum": {
47
  "value": 8756.0,
48
  "min": 8756.0,
49
- "max": 8756.0,
50
- "count": 1
51
  },
52
  "SnowballTarget.Environment.CumulativeReward.mean": {
53
- "value": 2.5681818181818183,
54
- "min": 2.5681818181818183,
55
- "max": 2.5681818181818183,
56
- "count": 1
57
  },
58
  "SnowballTarget.Environment.CumulativeReward.sum": {
59
- "value": 113.0,
60
- "min": 113.0,
61
- "max": 113.0,
62
- "count": 1
63
  },
64
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
65
- "value": 2.5681818181818183,
66
- "min": 2.5681818181818183,
67
- "max": 2.5681818181818183,
68
- "count": 1
69
  },
70
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
71
- "value": 113.0,
72
- "min": 113.0,
73
- "max": 113.0,
74
- "count": 1
75
  },
76
  "SnowballTarget.Losses.PolicyLoss.mean": {
77
- "value": 0.048945861431712784,
78
- "min": 0.048945861431712784,
79
- "max": 0.048945861431712784,
80
- "count": 1
81
  },
82
  "SnowballTarget.Losses.PolicyLoss.sum": {
83
- "value": 0.09789172286342557,
84
- "min": 0.09789172286342557,
85
- "max": 0.09789172286342557,
86
- "count": 1
87
  },
88
  "SnowballTarget.Losses.ValueLoss.mean": {
89
- "value": 0.047466835674747604,
90
- "min": 0.047466835674747604,
91
- "max": 0.047466835674747604,
92
- "count": 1
93
  },
94
  "SnowballTarget.Losses.ValueLoss.sum": {
95
- "value": 0.09493367134949521,
96
- "min": 0.09493367134949521,
97
- "max": 0.09493367134949521,
98
- "count": 1
99
  },
100
  "SnowballTarget.Policy.LearningRate.mean": {
101
- "value": 0.00010464006512000002,
102
- "min": 0.00010464006512000002,
103
- "max": 0.00010464006512000002,
104
- "count": 1
105
  },
106
  "SnowballTarget.Policy.LearningRate.sum": {
107
- "value": 0.00020928013024000005,
108
- "min": 0.00020928013024000005,
109
- "max": 0.00020928013024000005,
110
- "count": 1
111
  },
112
  "SnowballTarget.Policy.Epsilon.mean": {
113
- "value": 0.15231999999999996,
114
- "min": 0.15231999999999996,
115
- "max": 0.15231999999999996,
116
- "count": 1
117
  },
118
  "SnowballTarget.Policy.Epsilon.sum": {
119
- "value": 0.3046399999999999,
120
- "min": 0.3046399999999999,
121
- "max": 0.3046399999999999,
122
- "count": 1
123
  },
124
  "SnowballTarget.Policy.Beta.mean": {
125
- "value": 0.0017505119999999999,
126
- "min": 0.0017505119999999999,
127
- "max": 0.0017505119999999999,
128
- "count": 1
129
  },
130
  "SnowballTarget.Policy.Beta.sum": {
131
- "value": 0.0035010239999999997,
132
- "min": 0.0035010239999999997,
133
- "max": 0.0035010239999999997,
134
- "count": 1
135
  },
136
  "SnowballTarget.IsTraining.mean": {
137
  "value": 1.0,
138
  "min": 1.0,
139
  "max": 1.0,
140
- "count": 1
141
  },
142
  "SnowballTarget.IsTraining.sum": {
143
  "value": 1.0,
144
  "min": 1.0,
145
  "max": 1.0,
146
- "count": 1
147
  }
148
  },
149
  "metadata": {
150
  "timer_format_version": "0.1.0",
151
- "start_time_seconds": "1694195380",
152
  "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]",
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": "0.31.0.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": "1694195409"
160
  },
161
- "total": 29.02839592800001,
162
  "count": 1,
163
- "self": 0.4291761509996377,
164
  "children": {
165
  "run_training.setup": {
166
- "total": 0.05066195000017615,
167
  "count": 1,
168
- "self": 0.05066195000017615
169
  },
170
  "TrainerController.start_learning": {
171
- "total": 28.548557827000195,
172
  "count": 1,
173
- "self": 0.04960406900295311,
174
  "children": {
175
  "TrainerController._reset_env": {
176
- "total": 4.073276859000089,
177
  "count": 1,
178
- "self": 4.073276859000089
179
  },
180
  "TrainerController.advance": {
181
- "total": 24.27220436799712,
182
- "count": 934,
183
- "self": 0.013697022993483188,
184
  "children": {
185
  "env_step": {
186
- "total": 24.258507345003636,
187
- "count": 934,
188
- "self": 17.645529235004233,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
- "total": 6.599235522002118,
192
- "count": 934,
193
- "self": 0.0817164420006975,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
- "total": 6.517519080001421,
197
- "count": 934,
198
- "self": 6.517519080001421
199
  }
200
  }
201
  },
202
  "workers": {
203
- "total": 0.013742587997285227,
204
- "count": 934,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
- "total": 28.340408872997614,
209
- "count": 934,
210
  "is_parallel": true,
211
- "self": 15.729059506996236,
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": 0.0050898710001092695,
221
  "count": 1,
222
  "is_parallel": true,
223
- "self": 0.0035374720000618254,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
- "total": 0.0015523990000474441,
227
  "count": 10,
228
  "is_parallel": true,
229
- "self": 0.0015523990000474441
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
- "total": 0.0375554289998945,
235
  "count": 1,
236
  "is_parallel": true,
237
- "self": 0.0006312569998954132,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
- "total": 0.00037489600003937085,
241
  "count": 1,
242
  "is_parallel": true,
243
- "self": 0.00037489600003937085
244
  },
245
  "communicator.exchange": {
246
- "total": 0.03338095899994187,
247
  "count": 1,
248
  "is_parallel": true,
249
- "self": 0.03338095899994187
250
  },
251
  "steps_from_proto": {
252
- "total": 0.0031683170000178507,
253
  "count": 1,
254
  "is_parallel": true,
255
- "self": 0.00040893699974731135,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
- "total": 0.0027593800002705393,
259
  "count": 10,
260
  "is_parallel": true,
261
- "self": 0.0027593800002705393
262
  }
263
  }
264
  }
@@ -267,34 +267,34 @@
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
- "total": 12.611349366001377,
271
- "count": 933,
272
  "is_parallel": true,
273
- "self": 0.537294581010201,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
- "total": 0.27039484499505306,
277
- "count": 933,
278
  "is_parallel": true,
279
- "self": 0.27039484499505306
280
  },
281
  "communicator.exchange": {
282
- "total": 9.939632270995617,
283
- "count": 933,
284
  "is_parallel": true,
285
- "self": 9.939632270995617
286
  },
287
  "steps_from_proto": {
288
- "total": 1.8640276690005066,
289
- "count": 933,
290
  "is_parallel": true,
291
- "self": 0.34912224099684863,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
- "total": 1.514905428003658,
295
- "count": 9330,
296
  "is_parallel": true,
297
- "self": 1.514905428003658
298
  }
299
  }
300
  }
@@ -309,9 +309,9 @@
309
  }
310
  },
311
  "trainer_threads": {
312
- "total": 0.00023283299992726825,
313
  "count": 1,
314
- "self": 0.00023283299992726825,
315
  "children": {
316
  "thread_root": {
317
  "total": 0.0,
@@ -320,28 +320,36 @@
320
  "self": 0.0,
321
  "children": {
322
  "trainer_advance": {
323
- "total": 24.048281263001627,
324
- "count": 29422,
325
  "is_parallel": true,
326
- "self": 0.644191267008182,
327
  "children": {
328
  "process_trajectory": {
329
- "total": 16.19414100299332,
330
- "count": 29422,
331
  "is_parallel": true,
332
- "self": 16.19414100299332
 
 
 
 
 
 
 
 
333
  },
334
  "_update_policy": {
335
- "total": 7.2099489930001255,
336
- "count": 2,
337
  "is_parallel": true,
338
- "self": 4.056289224001148,
339
  "children": {
340
  "TorchPPOOptimizer.update": {
341
- "total": 3.1536597689989776,
342
- "count": 132,
343
  "is_parallel": true,
344
- "self": 3.1536597689989776
345
  }
346
  }
347
  }
@@ -352,14 +360,14 @@
352
  }
353
  },
354
  "TrainerController._save_models": {
355
- "total": 0.15323969800010673,
356
  "count": 1,
357
- "self": 0.0006165100000998791,
358
  "children": {
359
  "RLTrainer._checkpoint": {
360
- "total": 0.15262318800000685,
361
  "count": 1,
362
- "self": 0.15262318800000685
363
  }
364
  }
365
  }
 
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
+ "value": 1.0823804140090942,
6
+ "min": 1.0823804140090942,
7
+ "max": 2.8865561485290527,
8
+ "count": 20
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
+ "value": 10358.380859375,
12
+ "min": 10358.380859375,
13
+ "max": 29624.724609375,
14
+ "count": 20
15
  },
16
  "SnowballTarget.Step.mean": {
17
+ "value": 199984.0,
18
  "min": 9952.0,
19
+ "max": 199984.0,
20
+ "count": 20
21
  },
22
  "SnowballTarget.Step.sum": {
23
+ "value": 199984.0,
24
  "min": 9952.0,
25
+ "max": 199984.0,
26
+ "count": 20
27
  },
28
  "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
+ "value": 2.567681312561035,
30
+ "min": 0.09589726477861404,
31
+ "max": 2.574761390686035,
32
+ "count": 20
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
+ "value": 500.6978759765625,
36
+ "min": 18.604068756103516,
37
+ "max": 525.2513427734375,
38
+ "count": 20
39
  },
40
  "SnowballTarget.Environment.EpisodeLength.mean": {
41
  "value": 199.0,
42
  "min": 199.0,
43
  "max": 199.0,
44
+ "count": 20
45
  },
46
  "SnowballTarget.Environment.EpisodeLength.sum": {
47
  "value": 8756.0,
48
  "min": 8756.0,
49
+ "max": 10945.0,
50
+ "count": 20
51
  },
52
  "SnowballTarget.Environment.CumulativeReward.mean": {
53
+ "value": 25.15909090909091,
54
+ "min": 3.272727272727273,
55
+ "max": 25.386363636363637,
56
+ "count": 20
57
  },
58
  "SnowballTarget.Environment.CumulativeReward.sum": {
59
+ "value": 1107.0,
60
+ "min": 144.0,
61
+ "max": 1389.0,
62
+ "count": 20
63
  },
64
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
65
+ "value": 25.15909090909091,
66
+ "min": 3.272727272727273,
67
+ "max": 25.386363636363637,
68
+ "count": 20
69
  },
70
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
71
+ "value": 1107.0,
72
+ "min": 144.0,
73
+ "max": 1389.0,
74
+ "count": 20
75
  },
76
  "SnowballTarget.Losses.PolicyLoss.mean": {
77
+ "value": 0.05303531138120246,
78
+ "min": 0.043000292613321695,
79
+ "max": 0.05497397439595421,
80
+ "count": 20
81
  },
82
  "SnowballTarget.Losses.PolicyLoss.sum": {
83
+ "value": 0.10607062276240492,
84
+ "min": 0.08600058522664339,
85
+ "max": 0.15276711164316273,
86
+ "count": 20
87
  },
88
  "SnowballTarget.Losses.ValueLoss.mean": {
89
+ "value": 0.12043402075548382,
90
+ "min": 0.05885272711833857,
91
+ "max": 0.1406230588498361,
92
+ "count": 20
93
  },
94
  "SnowballTarget.Losses.ValueLoss.sum": {
95
+ "value": 0.24086804151096763,
96
+ "min": 0.11770545423667714,
97
+ "max": 0.4104643968098304,
98
+ "count": 20
99
  },
100
  "SnowballTarget.Policy.LearningRate.mean": {
101
+ "value": 6.432097856000006e-06,
102
+ "min": 6.432097856000006e-06,
103
+ "max": 0.00029023200325599993,
104
+ "count": 20
105
  },
106
  "SnowballTarget.Policy.LearningRate.sum": {
107
+ "value": 1.2864195712000013e-05,
108
+ "min": 1.2864195712000013e-05,
109
+ "max": 0.0007419960526679999,
110
+ "count": 20
111
  },
112
  "SnowballTarget.Policy.Epsilon.mean": {
113
+ "value": 0.10321600000000003,
114
+ "min": 0.10321600000000003,
115
+ "max": 0.24511600000000003,
116
+ "count": 20
117
  },
118
  "SnowballTarget.Policy.Epsilon.sum": {
119
+ "value": 0.20643200000000006,
120
+ "min": 0.20643200000000006,
121
+ "max": 0.6709980000000001,
122
+ "count": 20
123
  },
124
  "SnowballTarget.Policy.Beta.mean": {
125
+ "value": 0.00011698560000000007,
126
+ "min": 0.00011698560000000007,
127
+ "max": 0.004837525599999999,
128
+ "count": 20
129
  },
130
  "SnowballTarget.Policy.Beta.sum": {
131
+ "value": 0.00023397120000000015,
132
+ "min": 0.00023397120000000015,
133
+ "max": 0.012371866800000002,
134
+ "count": 20
135
  },
136
  "SnowballTarget.IsTraining.mean": {
137
  "value": 1.0,
138
  "min": 1.0,
139
  "max": 1.0,
140
+ "count": 20
141
  },
142
  "SnowballTarget.IsTraining.sum": {
143
  "value": 1.0,
144
  "min": 1.0,
145
  "max": 1.0,
146
+ "count": 20
147
  }
148
  },
149
  "metadata": {
150
  "timer_format_version": "0.1.0",
151
+ "start_time_seconds": "1694195607",
152
  "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]",
153
+ "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget2 --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": "1694196083"
160
  },
161
+ "total": 475.86589398,
162
  "count": 1,
163
+ "self": 0.43534228899966365,
164
  "children": {
165
  "run_training.setup": {
166
+ "total": 0.03870379100021637,
167
  "count": 1,
168
+ "self": 0.03870379100021637
169
  },
170
  "TrainerController.start_learning": {
171
+ "total": 475.39184790000013,
172
  "count": 1,
173
+ "self": 0.5261172999864812,
174
  "children": {
175
  "TrainerController._reset_env": {
176
+ "total": 3.8278629380001803,
177
  "count": 1,
178
+ "self": 3.8278629380001803
179
  },
180
  "TrainerController.advance": {
181
+ "total": 470.90342204901344,
182
+ "count": 18202,
183
+ "self": 0.2622811350365737,
184
  "children": {
185
  "env_step": {
186
+ "total": 470.64114091397687,
187
+ "count": 18202,
188
+ "self": 348.71422680298383,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
+ "total": 121.66394710200075,
192
+ "count": 18202,
193
+ "self": 1.755945177010517,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
+ "total": 119.90800192499023,
197
+ "count": 18202,
198
+ "self": 119.90800192499023
199
  }
200
  }
201
  },
202
  "workers": {
203
+ "total": 0.2629670089922911,
204
+ "count": 18202,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
+ "total": 473.8338290559757,
209
+ "count": 18202,
210
  "is_parallel": true,
211
+ "self": 236.80496419895894,
212
  "children": {
213
  "run_training.setup": {
214
  "total": 0.0,
 
217
  "self": 0.0,
218
  "children": {
219
  "steps_from_proto": {
220
+ "total": 0.0018615440001212846,
221
  "count": 1,
222
  "is_parallel": true,
223
+ "self": 0.0005025840000598691,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
+ "total": 0.0013589600000614155,
227
  "count": 10,
228
  "is_parallel": true,
229
+ "self": 0.0013589600000614155
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
+ "total": 0.03816275599979235,
235
  "count": 1,
236
  "is_parallel": true,
237
+ "self": 0.0006009799997173104,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
+ "total": 0.00033410600008210167,
241
  "count": 1,
242
  "is_parallel": true,
243
+ "self": 0.00033410600008210167
244
  },
245
  "communicator.exchange": {
246
+ "total": 0.0350276470001063,
247
  "count": 1,
248
  "is_parallel": true,
249
+ "self": 0.0350276470001063
250
  },
251
  "steps_from_proto": {
252
+ "total": 0.0022000229998866416,
253
  "count": 1,
254
  "is_parallel": true,
255
+ "self": 0.000523639999983061,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
+ "total": 0.0016763829999035806,
259
  "count": 10,
260
  "is_parallel": true,
261
+ "self": 0.0016763829999035806
262
  }
263
  }
264
  }
 
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
+ "total": 237.02886485701674,
271
+ "count": 18201,
272
  "is_parallel": true,
273
+ "self": 10.0921474280849,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
+ "total": 5.2441317659774995,
277
+ "count": 18201,
278
  "is_parallel": true,
279
+ "self": 5.2441317659774995
280
  },
281
  "communicator.exchange": {
282
+ "total": 186.9509997249993,
283
+ "count": 18201,
284
  "is_parallel": true,
285
+ "self": 186.9509997249993
286
  },
287
  "steps_from_proto": {
288
+ "total": 34.74158593795505,
289
+ "count": 18201,
290
  "is_parallel": true,
291
+ "self": 6.252948916890773,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
+ "total": 28.488637021064278,
295
+ "count": 182010,
296
  "is_parallel": true,
297
+ "self": 28.488637021064278
298
  }
299
  }
300
  }
 
309
  }
310
  },
311
  "trainer_threads": {
312
+ "total": 0.00015687999984947965,
313
  "count": 1,
314
+ "self": 0.00015687999984947965,
315
  "children": {
316
  "thread_root": {
317
  "total": 0.0,
 
320
  "self": 0.0,
321
  "children": {
322
  "trainer_advance": {
323
+ "total": 466.432363791929,
324
+ "count": 526672,
325
  "is_parallel": true,
326
+ "self": 11.80509066705963,
327
  "children": {
328
  "process_trajectory": {
329
+ "total": 299.5110636478719,
330
+ "count": 526672,
331
  "is_parallel": true,
332
+ "self": 298.73790789987197,
333
+ "children": {
334
+ "RLTrainer._checkpoint": {
335
+ "total": 0.7731557479999083,
336
+ "count": 4,
337
+ "is_parallel": true,
338
+ "self": 0.7731557479999083
339
+ }
340
+ }
341
  },
342
  "_update_policy": {
343
+ "total": 155.11620947699748,
344
+ "count": 45,
345
  "is_parallel": true,
346
+ "self": 87.08159226400198,
347
  "children": {
348
  "TorchPPOOptimizer.update": {
349
+ "total": 68.0346172129955,
350
+ "count": 3056,
351
  "is_parallel": true,
352
+ "self": 68.0346172129955
353
  }
354
  }
355
  }
 
360
  }
361
  },
362
  "TrainerController._save_models": {
363
+ "total": 0.13428873300017585,
364
  "count": 1,
365
+ "self": 0.0006541750003634661,
366
  "children": {
367
  "RLTrainer._checkpoint": {
368
+ "total": 0.1336345579998124,
369
  "count": 1,
370
+ "self": 0.1336345579998124
371
  }
372
  }
373
  }
run_logs/training_status.json CHANGED
@@ -2,22 +2,58 @@
2
  "SnowballTarget": {
3
  "checkpoints": [
4
  {
5
- "steps": 10208,
6
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-10208.onnx",
7
- "reward": 2.5454545454545454,
8
- "creation_time": 1694195408.9938948,
9
  "auxillary_file_paths": [
10
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-10208.pt"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
11
  ]
12
  }
13
  ],
14
  "final_checkpoint": {
15
- "steps": 10208,
16
- "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
17
- "reward": 2.5454545454545454,
18
- "creation_time": 1694195408.9938948,
19
  "auxillary_file_paths": [
20
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-10208.pt"
21
  ]
22
  }
23
  },
 
2
  "SnowballTarget": {
3
  "checkpoints": [
4
  {
5
+ "steps": 49936,
6
+ "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-49936.onnx",
7
+ "reward": 12.0,
8
+ "creation_time": 1694195729.460012,
9
  "auxillary_file_paths": [
10
+ "results/SnowballTarget2/SnowballTarget/SnowballTarget-49936.pt"
11
+ ]
12
+ },
13
+ {
14
+ "steps": 99960,
15
+ "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-99960.onnx",
16
+ "reward": 18.90909090909091,
17
+ "creation_time": 1694195846.0612614,
18
+ "auxillary_file_paths": [
19
+ "results/SnowballTarget2/SnowballTarget/SnowballTarget-99960.pt"
20
+ ]
21
+ },
22
+ {
23
+ "steps": 149984,
24
+ "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-149984.onnx",
25
+ "reward": 25.636363636363637,
26
+ "creation_time": 1694195964.9191837,
27
+ "auxillary_file_paths": [
28
+ "results/SnowballTarget2/SnowballTarget/SnowballTarget-149984.pt"
29
+ ]
30
+ },
31
+ {
32
+ "steps": 199984,
33
+ "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-199984.onnx",
34
+ "reward": 25.545454545454547,
35
+ "creation_time": 1694196083.1622114,
36
+ "auxillary_file_paths": [
37
+ "results/SnowballTarget2/SnowballTarget/SnowballTarget-199984.pt"
38
+ ]
39
+ },
40
+ {
41
+ "steps": 200112,
42
+ "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-200112.onnx",
43
+ "reward": 25.545454545454547,
44
+ "creation_time": 1694196083.3159246,
45
+ "auxillary_file_paths": [
46
+ "results/SnowballTarget2/SnowballTarget/SnowballTarget-200112.pt"
47
  ]
48
  }
49
  ],
50
  "final_checkpoint": {
51
+ "steps": 200112,
52
+ "file_path": "results/SnowballTarget2/SnowballTarget.onnx",
53
+ "reward": 25.545454545454547,
54
+ "creation_time": 1694196083.3159246,
55
  "auxillary_file_paths": [
56
+ "results/SnowballTarget2/SnowballTarget/SnowballTarget-200112.pt"
57
  ]
58
  }
59
  },