adhisetiawan commited on
Commit
a5a9af0
1 Parent(s): 3ee64fc

change number of layers

Browse files
SnowballTarget.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:510fffc23a002d6bc4c199621b6f673a1ed128eed7f99a2a3a4f4194a723e173
3
  size 910131
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:30286a803b00de6bf453b13a9050185bcec05b0d84ee0c68bba7c46771dcc058
3
  size 910131
SnowballTarget/SnowballTarget-149984.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fbca599c83610ecdad2c6f9d8a66442440a2840c24aa0c33b3f20cd6d9031ccd
3
  size 910131
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:04a6335e4f960b957a09371d315649ff812e4b18c683bf904837432489655360
3
  size 910131
SnowballTarget/SnowballTarget-149984.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c2f085bd423c674e2558e9c02b3e195d97608821a937c1e3c1de22c6cb01b2d7
3
  size 5426908
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d08bdb03c4c91bec3c6074761d4dc508088f9cc20df44ed7eb1f9031ceef7f77
3
  size 5426908
SnowballTarget/SnowballTarget-199984.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:510fffc23a002d6bc4c199621b6f673a1ed128eed7f99a2a3a4f4194a723e173
3
  size 910131
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:30286a803b00de6bf453b13a9050185bcec05b0d84ee0c68bba7c46771dcc058
3
  size 910131
SnowballTarget/SnowballTarget-199984.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:41ce224edaf67a70520a025f68c2be3a3c7c0a6d7ee46f38489058191817b78b
3
  size 5426908
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b6fea289306e0a99d47d43a09c7876e693e76d0f02461e538a745f61b14e91b4
3
  size 5426908
SnowballTarget/SnowballTarget-200112.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:510fffc23a002d6bc4c199621b6f673a1ed128eed7f99a2a3a4f4194a723e173
3
  size 910131
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:30286a803b00de6bf453b13a9050185bcec05b0d84ee0c68bba7c46771dcc058
3
  size 910131
SnowballTarget/SnowballTarget-200112.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:da66ee1bddfded35b863053faaed30ae4d70826e2e4b3eafbf0e073fac71638e
3
  size 5426908
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee7cfab63a04e3392d0b1f6be163941d33132463dd293c113b9903ef17b5d24f
3
  size 5426908
SnowballTarget/SnowballTarget-49936.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:13eb0df36312a46fdd37125cf03bc8395537f1a17eeab36b9382829a9404a6b3
3
  size 910131
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5834fdefa37f1c54ce12476ed8eaa54e26d562d4f712a0fb11aa04a870923e88
3
  size 910131
SnowballTarget/SnowballTarget-49936.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:52d5bf107be74b3091fcb1c34699b02b05a60f39b7a1ccb4ada03b33339c1805
3
  size 5426908
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b2d9715636f96c2e9407bec0ec432f333df1768d7b02543f8fa4427acf0bc44d
3
  size 5426908
SnowballTarget/SnowballTarget-99960.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6e9dbc35d4da555d203f2ee0d0c46db73d3af5f7d6a40b2729da683b7e57c003
3
  size 910131
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea7a2d8c24e10638c04adb097408c56f2378bbe64fd908fc9d2d23cd8f95ecf8
3
  size 910131
SnowballTarget/SnowballTarget-99960.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f37db3c05a9a0fb9f370ef6070cc91e468c84f888231660312afc032b8a2e60b
3
  size 5426908
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d500ee1f3dd39d4e220fb981204c627ed6d8c446ee50808445285272f0357b68
3
  size 5426908
SnowballTarget/checkpoint.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:da66ee1bddfded35b863053faaed30ae4d70826e2e4b3eafbf0e073fac71638e
3
  size 5426908
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee7cfab63a04e3392d0b1f6be163941d33132463dd293c113b9903ef17b5d24f
3
  size 5426908
SnowballTarget/{events.out.tfevents.1679908425.efb1629e622b.26805.0 → events.out.tfevents.1679909146.efb1629e622b.30136.0} RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5ca596d92751d486ddd019de384f3d3f165ab6bda1de02a51c33eaa0e3ce28f8
3
- size 23489
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f9ed2923055dd44302aa10ae5b401d06a5eb4ba81c992490edda3aca522a79f
3
+ size 23523
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": 3, "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": "SnowballTarget1", "initialize_from": null, "load_model": false, "resume": false, "force": true, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
 
1
+ {"default_settings": null, "behaviors": {"SnowballTarget": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "learning_rate": 0.001, "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": 3, "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": "SnowballTarget1", "initialize_from": null, "load_model": false, "resume": false, "force": true, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
configuration.yaml CHANGED
@@ -5,7 +5,7 @@ behaviors:
5
  hyperparameters:
6
  batch_size: 128
7
  buffer_size: 2048
8
- learning_rate: 0.0003
9
  beta: 0.005
10
  epsilon: 0.2
11
  lambd: 0.95
 
5
  hyperparameters:
6
  batch_size: 128
7
  buffer_size: 2048
8
+ learning_rate: 0.001
9
  beta: 0.005
10
  epsilon: 0.2
11
  lambd: 0.95
run_logs/Player-0.log CHANGED
@@ -31,7 +31,7 @@ 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 0.080 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 +42,7 @@ 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: 0.649644 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.
@@ -50,7 +50,7 @@ Memory Statistics:
50
  [ALLOC_TEMP_TLS] TLS Allocator
51
  StackAllocators :
52
  [ALLOC_TEMP_MAIN]
53
- Peak usage frame count: [8.0 KB-16.0 KB]: 5374 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
@@ -166,19 +166,19 @@ Memory Statistics:
166
  Peak Allocated Bytes 0 B
167
  Overflow Count 0
168
  [ALLOC_DEFAULT] Dual Thread Allocator
169
- Peak main deferred allocation count 42
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]: 5466 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]: 5466 frames
182
  Requested Block Size 16.0 MB
183
  Peak Block count 1
184
  Peak Allocated memory 17.8 MB
@@ -210,13 +210,13 @@ 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]: 4388 frames, [64.0 KB-128.0 KB]: 1078 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]: 5466 frames
220
  Requested Block Size 16.0 MB
221
  Peak Block count 1
222
  Peak Allocated memory 39.6 KB
@@ -228,13 +228,13 @@ Memory Statistics:
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]: 5466 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]: 5465 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
@@ -246,13 +246,13 @@ Memory Statistics:
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]: 5466 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]: 5466 frames
256
  Requested Block Size 2.0 MB
257
  Peak Block count 1
258
  Peak Allocated memory 1.7 KB
 
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 0.082 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: 0.598230 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]: 5371 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]: 5463 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]: 5463 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]: 5242 frames, [64.0 KB-128.0 KB]: 221 frames
214
  Requested Block Size 16.0 MB
215
  Peak Block count 1
216
+ Peak Allocated memory 66.0 KB
217
  Peak Large allocation bytes 0 B
218
  [ALLOC_GFX_THREAD]
219
+ Peak usage frame count: [32.0 KB-64.0 KB]: 5463 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]: 5463 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]: 5462 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]: 5463 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]: 5463 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
@@ -2,15 +2,15 @@
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
- "value": 0.9946820735931396,
6
- "min": 0.9946820735931396,
7
- "max": 2.8663761615753174,
8
  "count": 20
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
- "value": 9530.048828125,
12
- "min": 9530.048828125,
13
- "max": 29480.677734375,
14
  "count": 20
15
  },
16
  "SnowballTarget.Step.mean": {
@@ -26,15 +26,15 @@
26
  "count": 20
27
  },
28
  "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
- "value": 12.850577354431152,
30
- "min": 0.4389503598213196,
31
- "max": 12.850577354431152,
32
  "count": 20
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
- "value": 2505.862548828125,
36
- "min": 85.1563720703125,
37
- "max": 2582.72509765625,
38
  "count": 20
39
  },
40
  "SnowballTarget.Environment.EpisodeLength.mean": {
@@ -50,39 +50,39 @@
50
  "count": 20
51
  },
52
  "SnowballTarget.Losses.PolicyLoss.mean": {
53
- "value": 0.07140613051103406,
54
- "min": 0.06089604495951505,
55
- "max": 0.07297919158322744,
56
  "count": 20
57
  },
58
  "SnowballTarget.Losses.PolicyLoss.sum": {
59
- "value": 0.28562452204413624,
60
- "min": 0.25895955315568514,
61
- "max": 0.3648959579161372,
62
  "count": 20
63
  },
64
  "SnowballTarget.Losses.ValueLoss.mean": {
65
- "value": 0.21466431233520603,
66
- "min": 0.12085397768418725,
67
- "max": 0.29286830470550296,
68
  "count": 20
69
  },
70
  "SnowballTarget.Losses.ValueLoss.sum": {
71
- "value": 0.8586572493408241,
72
- "min": 0.483415910736749,
73
- "max": 1.3729174195551404,
74
  "count": 20
75
  },
76
  "SnowballTarget.Policy.LearningRate.mean": {
77
- "value": 8.082097306000005e-06,
78
- "min": 8.082097306000005e-06,
79
- "max": 0.000291882002706,
80
  "count": 20
81
  },
82
  "SnowballTarget.Policy.LearningRate.sum": {
83
- "value": 3.232838922400002e-05,
84
- "min": 3.232838922400002e-05,
85
- "max": 0.00138516003828,
86
  "count": 20
87
  },
88
  "SnowballTarget.Policy.Epsilon.mean": {
@@ -110,27 +110,27 @@
110
  "count": 20
111
  },
112
  "SnowballTarget.Environment.CumulativeReward.mean": {
113
- "value": 25.613636363636363,
114
- "min": 3.3863636363636362,
115
- "max": 25.613636363636363,
116
  "count": 20
117
  },
118
  "SnowballTarget.Environment.CumulativeReward.sum": {
119
- "value": 1127.0,
120
- "min": 149.0,
121
- "max": 1394.0,
122
  "count": 20
123
  },
124
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
- "value": 25.613636363636363,
126
- "min": 3.3863636363636362,
127
- "max": 25.613636363636363,
128
  "count": 20
129
  },
130
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
- "value": 1127.0,
132
- "min": 149.0,
133
- "max": 1394.0,
134
  "count": 20
135
  },
136
  "SnowballTarget.IsTraining.mean": {
@@ -148,7 +148,7 @@
148
  },
149
  "metadata": {
150
  "timer_format_version": "0.1.0",
151
- "start_time_seconds": "1679908422",
152
  "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[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=SnowballTarget1 --no-graphics --force",
154
  "mlagents_version": "0.31.0.dev0",
@@ -156,59 +156,59 @@
156
  "communication_protocol_version": "1.5.0",
157
  "pytorch_version": "1.11.0+cu102",
158
  "numpy_version": "1.21.2",
159
- "end_time_seconds": "1679908882"
160
  },
161
- "total": 460.14895640899977,
162
  "count": 1,
163
- "self": 0.7895674730007158,
164
  "children": {
165
  "run_training.setup": {
166
- "total": 0.10292876199946477,
167
  "count": 1,
168
- "self": 0.10292876199946477
169
  },
170
  "TrainerController.start_learning": {
171
- "total": 459.2564601739996,
172
  "count": 1,
173
- "self": 0.49016623697934847,
174
  "children": {
175
  "TrainerController._reset_env": {
176
- "total": 5.846241936000297,
177
  "count": 1,
178
- "self": 5.846241936000297
179
  },
180
  "TrainerController.advance": {
181
- "total": 452.6829718790186,
182
- "count": 18217,
183
- "self": 0.263493961050699,
184
  "children": {
185
  "env_step": {
186
- "total": 452.4194779179679,
187
- "count": 18217,
188
- "self": 329.18339330596154,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
- "total": 122.98751471001287,
192
- "count": 18217,
193
- "self": 1.8901296979720428,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
- "total": 121.09738501204083,
197
- "count": 18217,
198
- "self": 121.09738501204083
199
  }
200
  }
201
  },
202
  "workers": {
203
- "total": 0.24856990199350548,
204
- "count": 18217,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
- "total": 457.74583978990995,
209
- "count": 18217,
210
  "is_parallel": true,
211
- "self": 223.41518318488306,
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": 0.002092693000122381,
221
  "count": 1,
222
  "is_parallel": true,
223
- "self": 0.0006417580016204738,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
- "total": 0.001450934998501907,
227
  "count": 10,
228
  "is_parallel": true,
229
- "self": 0.001450934998501907
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
- "total": 0.034367600999758,
235
  "count": 1,
236
  "is_parallel": true,
237
- "self": 0.00047767500018380815,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
- "total": 0.0003021359998456319,
241
  "count": 1,
242
  "is_parallel": true,
243
- "self": 0.0003021359998456319
244
  },
245
  "communicator.exchange": {
246
- "total": 0.032102486999974644,
247
  "count": 1,
248
  "is_parallel": true,
249
- "self": 0.032102486999974644
250
  },
251
  "steps_from_proto": {
252
- "total": 0.0014853029997539124,
253
  "count": 1,
254
  "is_parallel": true,
255
- "self": 0.0003237099999751081,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
- "total": 0.0011615929997788044,
259
  "count": 10,
260
  "is_parallel": true,
261
- "self": 0.0011615929997788044
262
  }
263
  }
264
  }
@@ -267,34 +267,34 @@
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
- "total": 234.3306566050269,
271
- "count": 18216,
272
  "is_parallel": true,
273
- "self": 9.466481910018956,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
- "total": 5.099213578037052,
277
- "count": 18216,
278
  "is_parallel": true,
279
- "self": 5.099213578037052
280
  },
281
  "communicator.exchange": {
282
- "total": 189.53019968192984,
283
- "count": 18216,
284
  "is_parallel": true,
285
- "self": 189.53019968192984
286
  },
287
  "steps_from_proto": {
288
- "total": 30.234761435041037,
289
- "count": 18216,
290
  "is_parallel": true,
291
- "self": 5.846674117066868,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
- "total": 24.38808731797417,
295
- "count": 182160,
296
  "is_parallel": true,
297
- "self": 24.38808731797417
298
  }
299
  }
300
  }
@@ -309,9 +309,9 @@
309
  }
310
  },
311
  "trainer_threads": {
312
- "total": 8.636000075057382e-05,
313
  "count": 1,
314
- "self": 8.636000075057382e-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": 449.5033354977977,
324
- "count": 385886,
325
  "is_parallel": true,
326
- "self": 9.206752954598414,
327
  "children": {
328
  "process_trajectory": {
329
- "total": 244.94867293820062,
330
- "count": 385886,
331
  "is_parallel": true,
332
- "self": 243.48391041620016,
333
  "children": {
334
  "RLTrainer._checkpoint": {
335
- "total": 1.4647625220004556,
336
  "count": 4,
337
  "is_parallel": true,
338
- "self": 1.4647625220004556
339
  }
340
  }
341
  },
342
  "_update_policy": {
343
- "total": 195.34790960499868,
344
  "count": 90,
345
  "is_parallel": true,
346
- "self": 75.03490625402355,
347
  "children": {
348
  "TorchPPOOptimizer.update": {
349
- "total": 120.31300335097512,
350
- "count": 4587,
351
  "is_parallel": true,
352
- "self": 120.31300335097512
353
  }
354
  }
355
  }
@@ -360,14 +360,14 @@
360
  }
361
  },
362
  "TrainerController._save_models": {
363
- "total": 0.23699376200056577,
364
  "count": 1,
365
- "self": 0.002571512000031362,
366
  "children": {
367
  "RLTrainer._checkpoint": {
368
- "total": 0.2344222500005344,
369
  "count": 1,
370
- "self": 0.2344222500005344
371
  }
372
  }
373
  }
 
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
+ "value": 0.9692443609237671,
6
+ "min": 0.927122175693512,
7
+ "max": 2.8436264991760254,
8
  "count": 20
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
+ "value": 9286.330078125,
12
+ "min": 8811.369140625,
13
+ "max": 29152.859375,
14
  "count": 20
15
  },
16
  "SnowballTarget.Step.mean": {
 
26
  "count": 20
27
  },
28
  "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
+ "value": 13.431455612182617,
30
+ "min": 0.39277899265289307,
31
+ "max": 13.490251541137695,
32
  "count": 20
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
+ "value": 2619.1337890625,
36
+ "min": 76.19912719726562,
37
+ "max": 2752.01123046875,
38
  "count": 20
39
  },
40
  "SnowballTarget.Environment.EpisodeLength.mean": {
 
50
  "count": 20
51
  },
52
  "SnowballTarget.Losses.PolicyLoss.mean": {
53
+ "value": 0.07533240765812534,
54
+ "min": 0.060603809537589724,
55
+ "max": 0.07533240765812534,
56
  "count": 20
57
  },
58
  "SnowballTarget.Losses.PolicyLoss.sum": {
59
+ "value": 0.30132963063250134,
60
+ "min": 0.2543733938678177,
61
+ "max": 0.3590799850257919,
62
  "count": 20
63
  },
64
  "SnowballTarget.Losses.ValueLoss.mean": {
65
+ "value": 0.17713492524390126,
66
+ "min": 0.1094620518920505,
67
+ "max": 0.270675156411587,
68
  "count": 20
69
  },
70
  "SnowballTarget.Losses.ValueLoss.sum": {
71
+ "value": 0.708539700975605,
72
+ "min": 0.437848207568202,
73
+ "max": 1.2626544186918467,
74
  "count": 20
75
  },
76
  "SnowballTarget.Policy.LearningRate.mean": {
77
+ "value": 2.6940097306000015e-05,
78
+ "min": 2.6940097306000015e-05,
79
+ "max": 0.000972940002706,
80
  "count": 20
81
  },
82
  "SnowballTarget.Policy.LearningRate.sum": {
83
+ "value": 0.00010776038922400006,
84
+ "min": 0.00010776038922400006,
85
+ "max": 0.004617200038280001,
86
  "count": 20
87
  },
88
  "SnowballTarget.Policy.Epsilon.mean": {
 
110
  "count": 20
111
  },
112
  "SnowballTarget.Environment.CumulativeReward.mean": {
113
+ "value": 26.363636363636363,
114
+ "min": 3.2954545454545454,
115
+ "max": 26.75,
116
  "count": 20
117
  },
118
  "SnowballTarget.Environment.CumulativeReward.sum": {
119
+ "value": 1160.0,
120
+ "min": 145.0,
121
+ "max": 1462.0,
122
  "count": 20
123
  },
124
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
+ "value": 26.363636363636363,
126
+ "min": 3.2954545454545454,
127
+ "max": 26.75,
128
  "count": 20
129
  },
130
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
+ "value": 1160.0,
132
+ "min": 145.0,
133
+ "max": 1462.0,
134
  "count": 20
135
  },
136
  "SnowballTarget.IsTraining.mean": {
 
148
  },
149
  "metadata": {
150
  "timer_format_version": "0.1.0",
151
+ "start_time_seconds": "1679909142",
152
  "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[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=SnowballTarget1 --no-graphics --force",
154
  "mlagents_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": "1679909616"
160
  },
161
+ "total": 474.01528819100076,
162
  "count": 1,
163
+ "self": 0.9354834430005212,
164
  "children": {
165
  "run_training.setup": {
166
+ "total": 0.11649593800029834,
167
  "count": 1,
168
+ "self": 0.11649593800029834
169
  },
170
  "TrainerController.start_learning": {
171
+ "total": 472.96330880999994,
172
  "count": 1,
173
+ "self": 0.5450964140818542,
174
  "children": {
175
  "TrainerController._reset_env": {
176
+ "total": 7.216771080000399,
177
  "count": 1,
178
+ "self": 7.216771080000399
179
  },
180
  "TrainerController.advance": {
181
+ "total": 464.9384942569177,
182
+ "count": 18207,
183
+ "self": 0.2670243389102325,
184
  "children": {
185
  "env_step": {
186
+ "total": 464.67146991800746,
187
+ "count": 18207,
188
+ "self": 336.548142367089,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
+ "total": 127.85904619493431,
192
+ "count": 18207,
193
+ "self": 2.3067254889247124,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
+ "total": 125.5523207060096,
197
+ "count": 18207,
198
+ "self": 125.5523207060096
199
  }
200
  }
201
  },
202
  "workers": {
203
+ "total": 0.264281355984167,
204
+ "count": 18207,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
+ "total": 471.22251515205244,
209
+ "count": 18207,
210
  "is_parallel": true,
211
+ "self": 228.7384939289741,
212
  "children": {
213
  "run_training.setup": {
214
  "total": 0.0,
 
217
  "self": 0.0,
218
  "children": {
219
  "steps_from_proto": {
220
+ "total": 0.002133738999873458,
221
  "count": 1,
222
  "is_parallel": true,
223
+ "self": 0.0006460940003307769,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
+ "total": 0.001487644999542681,
227
  "count": 10,
228
  "is_parallel": true,
229
+ "self": 0.001487644999542681
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
+ "total": 0.034104481999747804,
235
  "count": 1,
236
  "is_parallel": true,
237
+ "self": 0.0005338770006346749,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
+ "total": 0.0002983309996125172,
241
  "count": 1,
242
  "is_parallel": true,
243
+ "self": 0.0002983309996125172
244
  },
245
  "communicator.exchange": {
246
+ "total": 0.03133145199990395,
247
  "count": 1,
248
  "is_parallel": true,
249
+ "self": 0.03133145199990395
250
  },
251
  "steps_from_proto": {
252
+ "total": 0.0019408219995966647,
253
  "count": 1,
254
  "is_parallel": true,
255
+ "self": 0.00039802599894755986,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
+ "total": 0.0015427960006491048,
259
  "count": 10,
260
  "is_parallel": true,
261
+ "self": 0.0015427960006491048
262
  }
263
  }
264
  }
 
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
+ "total": 242.48402122307834,
271
+ "count": 18206,
272
  "is_parallel": true,
273
+ "self": 9.667503741089604,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
+ "total": 5.193780598013291,
277
+ "count": 18206,
278
  "is_parallel": true,
279
+ "self": 5.193780598013291
280
  },
281
  "communicator.exchange": {
282
+ "total": 196.30568538498846,
283
+ "count": 18206,
284
  "is_parallel": true,
285
+ "self": 196.30568538498846
286
  },
287
  "steps_from_proto": {
288
+ "total": 31.317051498986984,
289
+ "count": 18206,
290
  "is_parallel": true,
291
+ "self": 6.118698400159701,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
+ "total": 25.198353098827283,
295
+ "count": 182060,
296
  "is_parallel": true,
297
+ "self": 25.198353098827283
298
  }
299
  }
300
  }
 
309
  }
310
  },
311
  "trainer_threads": {
312
+ "total": 0.00017419699997844873,
313
  "count": 1,
314
+ "self": 0.00017419699997844873,
315
  "children": {
316
  "thread_root": {
317
  "total": 0.0,
 
320
  "self": 0.0,
321
  "children": {
322
  "trainer_advance": {
323
+ "total": 461.45478128468767,
324
+ "count": 409844,
325
  "is_parallel": true,
326
+ "self": 10.227170245810157,
327
  "children": {
328
  "process_trajectory": {
329
+ "total": 253.52621373487636,
330
+ "count": 409844,
331
  "is_parallel": true,
332
+ "self": 251.92142233887625,
333
  "children": {
334
  "RLTrainer._checkpoint": {
335
+ "total": 1.6047913960001097,
336
  "count": 4,
337
  "is_parallel": true,
338
+ "self": 1.6047913960001097
339
  }
340
  }
341
  },
342
  "_update_policy": {
343
+ "total": 197.70139730400115,
344
  "count": 90,
345
  "is_parallel": true,
346
+ "self": 73.85614802703094,
347
  "children": {
348
  "TorchPPOOptimizer.update": {
349
+ "total": 123.84524927697021,
350
+ "count": 4584,
351
  "is_parallel": true,
352
+ "self": 123.84524927697021
353
  }
354
  }
355
  }
 
360
  }
361
  },
362
  "TrainerController._save_models": {
363
+ "total": 0.2627728620000198,
364
  "count": 1,
365
+ "self": 0.0019030799994652625,
366
  "children": {
367
  "RLTrainer._checkpoint": {
368
+ "total": 0.26086978200055455,
369
  "count": 1,
370
+ "self": 0.26086978200055455
371
  }
372
  }
373
  }
run_logs/training_status.json CHANGED
@@ -4,8 +4,8 @@
4
  {
5
  "steps": 49936,
6
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.onnx",
7
- "reward": 13.909090909090908,
8
- "creation_time": 1679908542.6574535,
9
  "auxillary_file_paths": [
10
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.pt"
11
  ]
@@ -13,8 +13,8 @@
13
  {
14
  "steps": 99960,
15
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.onnx",
16
- "reward": 21.727272727272727,
17
- "creation_time": 1679908655.6292062,
18
  "auxillary_file_paths": [
19
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.pt"
20
  ]
@@ -22,8 +22,8 @@
22
  {
23
  "steps": 149984,
24
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.onnx",
25
- "reward": 23.90909090909091,
26
- "creation_time": 1679908769.2580125,
27
  "auxillary_file_paths": [
28
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.pt"
29
  ]
@@ -31,8 +31,8 @@
31
  {
32
  "steps": 199984,
33
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.onnx",
34
- "reward": 26.545454545454547,
35
- "creation_time": 1679908881.3867598,
36
  "auxillary_file_paths": [
37
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.pt"
38
  ]
@@ -40,8 +40,8 @@
40
  {
41
  "steps": 200112,
42
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.onnx",
43
- "reward": 26.545454545454547,
44
- "creation_time": 1679908881.6471078,
45
  "auxillary_file_paths": [
46
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
47
  ]
@@ -50,8 +50,8 @@
50
  "final_checkpoint": {
51
  "steps": 200112,
52
  "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
53
- "reward": 26.545454545454547,
54
- "creation_time": 1679908881.6471078,
55
  "auxillary_file_paths": [
56
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
57
  ]
 
4
  {
5
  "steps": 49936,
6
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.onnx",
7
+ "reward": 16.0,
8
+ "creation_time": 1679909264.0238843,
9
  "auxillary_file_paths": [
10
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.pt"
11
  ]
 
13
  {
14
  "steps": 99960,
15
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.onnx",
16
+ "reward": 24.545454545454547,
17
+ "creation_time": 1679909378.3134155,
18
  "auxillary_file_paths": [
19
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.pt"
20
  ]
 
22
  {
23
  "steps": 149984,
24
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.onnx",
25
+ "reward": 25.545454545454547,
26
+ "creation_time": 1679909493.969131,
27
  "auxillary_file_paths": [
28
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.pt"
29
  ]
 
31
  {
32
  "steps": 199984,
33
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.onnx",
34
+ "reward": 28.818181818181817,
35
+ "creation_time": 1679909614.8385818,
36
  "auxillary_file_paths": [
37
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.pt"
38
  ]
 
40
  {
41
  "steps": 200112,
42
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.onnx",
43
+ "reward": 28.818181818181817,
44
+ "creation_time": 1679909615.3084714,
45
  "auxillary_file_paths": [
46
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
47
  ]
 
50
  "final_checkpoint": {
51
  "steps": 200112,
52
  "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
53
+ "reward": 28.818181818181817,
54
+ "creation_time": 1679909615.3084714,
55
  "auxillary_file_paths": [
56
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
57
  ]