Hugging Face's logo

mmontecino
/
ppo-SnowballTarget

Reinforcement Learning
ml-agents
TensorBoard
ONNX
unity-ml-agents
deep-reinforcement-learning
ML-Agents-SnowballTarget
Model card Files
xet
Metrics Community
mmontecino commited on
Commit
c232181
·
1 Parent(s): 2f9850b

First Push

Browse files
Files changed (8) hide show
  1. SnowballTarget/SnowballTarget-200112.pt +1 -1
  2. SnowballTarget/checkpoint.pt +1 -1
  3. SnowballTarget/events.out.tfevents.1673979999.0b4de9a3285f.6680.0 +3 -0
  4. config.json +1 -1
  5. configuration.yaml +1 -1
  6. run_logs/Player-0.log +18 -21
  7. run_logs/timers.json +23 -329
  8. run_logs/training_status.json +11 -2
SnowballTarget/SnowballTarget-200112.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:535d5fc1fc264e9ad9cef516a6a68aaddd71590d01c57fdb5c1a85ba4969c348
3
  size 3845312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:55b73290685ce6daab1f13382a67bec3a2ecee0bad0c6fba863477f8738b63fa
3
  size 3845312
SnowballTarget/checkpoint.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:535d5fc1fc264e9ad9cef516a6a68aaddd71590d01c57fdb5c1a85ba4969c348
3
  size 3845312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:55b73290685ce6daab1f13382a67bec3a2ecee0bad0c6fba863477f8738b63fa
3
  size 3845312
SnowballTarget/events.out.tfevents.1673979999.0b4de9a3285f.6680.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:300711b35781c4a949f20407d3c6afb7e0cb88c614897c1a24f94b8dc7108e59
3
+ size 1017
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": "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": true, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
configuration.yaml CHANGED
@@ -65,7 +65,7 @@ checkpoint_settings:
65
  run_id: SnowballTarget1
66
  initialize_from: null
67
  load_model: false
68
- resume: false
69
  force: false
70
  train_model: false
71
  inference: false
 
65
  run_id: SnowballTarget1
66
  initialize_from: null
67
  load_model: false
68
+ resume: true
69
  force: false
70
  train_model: false
71
  inference: 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 0.077 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: 0.609157 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]: 5369 frames, [16.0 KB-32.0 KB]: 91 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
@@ -81,7 +78,7 @@ Memory Statistics:
81
  [ALLOC_TEMP_Job.Worker 0]
82
  Initial Block Size 256.0 KB
83
  Current Block Size 256.0 KB
84
- Peak Allocated Bytes 3.6 KB
85
  Overflow Count 0
86
  [ALLOC_TEMP_Background Job.Worker 10]
87
  Initial Block Size 32.0 KB
@@ -169,22 +166,22 @@ Memory Statistics:
169
  Peak Allocated Bytes 0 B
170
  Overflow Count 0
171
  [ALLOC_DEFAULT] Dual Thread Allocator
172
- Peak main deferred allocation count 41
173
  [ALLOC_BUCKET]
174
  Large Block size 4.0 MB
175
  Used Block count 1
176
  Peak Allocated bytes 0.9 MB
177
  [ALLOC_DEFAULT_MAIN]
178
- Peak usage frame count: [4.0 MB-8.0 MB]: 5461 frames
179
  Requested Block Size 16.0 MB
180
  Peak Block count 1
181
- Peak Allocated memory 6.5 MB
182
  Peak Large allocation bytes 0 B
183
  [ALLOC_DEFAULT_THREAD]
184
- Peak usage frame count: [16.0 MB-32.0 MB]: 5461 frames
185
  Requested Block Size 16.0 MB
186
  Peak Block count 1
187
- Peak Allocated memory 17.8 MB
188
  Peak Large allocation bytes 16.0 MB
189
  [ALLOC_TEMP_JOB_1_FRAME]
190
  Initial Block Size 2.0 MB
@@ -198,7 +195,7 @@ Memory Statistics:
198
  Overflow Count (full) 0
199
  [ALLOC_TEMP_JOB_4_FRAMES (JobTemp)]
200
  Initial Block Size 2.0 MB
201
- Used Block Count 2
202
  Overflow Count (too large) 0
203
  Overflow Count (full) 0
204
  [ALLOC_TEMP_JOB_ASYNC (Background)]
@@ -213,13 +210,13 @@ 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]: 4814 frames, [64.0 KB-128.0 KB]: 647 frames
217
  Requested Block Size 16.0 MB
218
  Peak Block count 1
219
- Peak Allocated memory 66.8 KB
220
  Peak Large allocation bytes 0 B
221
  [ALLOC_GFX_THREAD]
222
- Peak usage frame count: [32.0 KB-64.0 KB]: 5461 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 0.9 MB
233
  [ALLOC_CACHEOBJECTS_MAIN]
234
- Peak usage frame count: [0.5 MB-1.0 MB]: 5461 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]: 5460 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 0.9 MB
251
  [ALLOC_TYPETREE_MAIN]
252
- Peak usage frame count: [0-1.0 KB]: 5461 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]: 5461 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 0.083 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: 0.687627 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: [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
 
78
  [ALLOC_TEMP_Job.Worker 0]
79
  Initial Block Size 256.0 KB
80
  Current Block Size 256.0 KB
81
+ Peak Allocated Bytes 2.8 KB
82
  Overflow Count 0
83
  [ALLOC_TEMP_Background Job.Worker 10]
84
  Initial Block Size 32.0 KB
 
166
  Peak Allocated Bytes 0 B
167
  Overflow Count 0
168
  [ALLOC_DEFAULT] Dual Thread Allocator
169
+ Peak main deferred allocation count 3
170
  [ALLOC_BUCKET]
171
  Large Block size 4.0 MB
172
  Used Block count 1
173
  Peak Allocated bytes 0.9 MB
174
  [ALLOC_DEFAULT_MAIN]
175
+ Peak usage frame count: [4.0 MB-8.0 MB]: 1 frames
176
  Requested Block Size 16.0 MB
177
  Peak Block count 1
178
+ Peak Allocated memory 4.7 MB
179
  Peak Large allocation bytes 0 B
180
  [ALLOC_DEFAULT_THREAD]
181
+ Peak usage frame count: [16.0 MB-32.0 MB]: 1 frames
182
  Requested Block Size 16.0 MB
183
  Peak Block count 1
184
+ Peak Allocated memory 17.5 MB
185
  Peak Large allocation bytes 16.0 MB
186
  [ALLOC_TEMP_JOB_1_FRAME]
187
  Initial Block Size 2.0 MB
 
195
  Overflow Count (full) 0
196
  [ALLOC_TEMP_JOB_4_FRAMES (JobTemp)]
197
  Initial Block Size 2.0 MB
198
+ Used Block Count 1
199
  Overflow Count (too large) 0
200
  Overflow Count (full) 0
201
  [ALLOC_TEMP_JOB_ASYNC (Background)]
 
210
  Used Block count 1
211
  Peak Allocated bytes 0.9 MB
212
  [ALLOC_GFX_MAIN]
213
+ Peak usage frame count: [64.0 KB-128.0 KB]: 1 frames
214
  Requested Block Size 16.0 MB
215
  Peak Block count 1
216
+ Peak Allocated memory 65.6 KB
217
  Peak Large allocation bytes 0 B
218
  [ALLOC_GFX_THREAD]
219
+ Peak usage frame count: [32.0 KB-64.0 KB]: 1 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 0.9 MB
230
  [ALLOC_CACHEOBJECTS_MAIN]
231
+ Peak usage frame count: [0.5 MB-1.0 MB]: 1 frames
232
  Requested Block Size 4.0 MB
233
  Peak Block count 1
234
+ Peak Allocated memory 0.5 MB
235
  Peak Large allocation bytes 0 B
236
  [ALLOC_CACHEOBJECTS_THREAD]
237
+ Peak usage frame count: [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 0.9 MB
248
  [ALLOC_TYPETREE_MAIN]
249
+ Peak usage frame count: [0-1.0 KB]: 1 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]: 1 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
@@ -1,324 +1,40 @@
1
  {
2
  "name": "root",
3
- "gauges": {
4
- "SnowballTarget.Policy.Entropy.mean": {
5
- "value": 0.9878819584846497,
6
- "min": 0.9878819584846497,
7
- "max": 2.8578507900238037,
8
- "count": 20
9
- },
10
- "SnowballTarget.Policy.Entropy.sum": {
11
- "value": 9432.296875,
12
- "min": 9432.296875,
13
- "max": 29267.25,
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": 12.572270393371582,
30
- "min": 0.4021381139755249,
31
- "max": 12.572270393371582,
32
- "count": 20
33
- },
34
- "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
- "value": 2451.5927734375,
36
- "min": 78.0147933959961,
37
- "max": 2561.22509765625,
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.Losses.PolicyLoss.mean": {
53
- "value": 0.06701367555868666,
54
- "min": 0.0624450823438226,
55
- "max": 0.07501150818712167,
56
- "count": 20
57
- },
58
- "SnowballTarget.Losses.PolicyLoss.sum": {
59
- "value": 0.26805470223474664,
60
- "min": 0.2626650821161913,
61
- "max": 0.3679603608673228,
62
- "count": 20
63
- },
64
- "SnowballTarget.Losses.ValueLoss.mean": {
65
- "value": 0.2283090652496207,
66
- "min": 0.13935039699415439,
67
- "max": 0.2746637744792536,
68
- "count": 20
69
- },
70
- "SnowballTarget.Losses.ValueLoss.sum": {
71
- "value": 0.9132362609984828,
72
- "min": 0.5574015879766175,
73
- "max": 1.3297799635751575,
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": {
89
- "value": 0.10269400000000001,
90
- "min": 0.10269400000000001,
91
- "max": 0.19729400000000002,
92
- "count": 20
93
- },
94
- "SnowballTarget.Policy.Epsilon.sum": {
95
- "value": 0.41077600000000003,
96
- "min": 0.41077600000000003,
97
- "max": 0.96172,
98
- "count": 20
99
- },
100
- "SnowballTarget.Policy.Beta.mean": {
101
- "value": 0.0001444306000000001,
102
- "min": 0.0001444306000000001,
103
- "max": 0.0048649706,
104
- "count": 20
105
- },
106
- "SnowballTarget.Policy.Beta.sum": {
107
- "value": 0.0005777224000000004,
108
- "min": 0.0005777224000000004,
109
- "max": 0.023089828,
110
- "count": 20
111
- },
112
- "SnowballTarget.Environment.CumulativeReward.mean": {
113
- "value": 24.863636363636363,
114
- "min": 3.6818181818181817,
115
- "max": 24.90909090909091,
116
- "count": 20
117
- },
118
- "SnowballTarget.Environment.CumulativeReward.sum": {
119
- "value": 1094.0,
120
- "min": 162.0,
121
- "max": 1360.0,
122
- "count": 20
123
- },
124
- "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
- "value": 24.863636363636363,
126
- "min": 3.6818181818181817,
127
- "max": 24.90909090909091,
128
- "count": 20
129
- },
130
- "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
- "value": 1094.0,
132
- "min": 162.0,
133
- "max": 1360.0,
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": "1673979129",
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": "1673979575"
160
  },
161
- "total": 446.13203932500005,
162
  "count": 1,
163
- "self": 0.3793545419999873,
164
  "children": {
165
  "run_training.setup": {
166
- "total": 0.11485291899998629,
167
  "count": 1,
168
- "self": 0.11485291899998629
169
  },
170
  "TrainerController.start_learning": {
171
- "total": 445.6378318640001,
172
  "count": 1,
173
- "self": 0.5161961609938999,
174
  "children": {
175
  "TrainerController._reset_env": {
176
- "total": 8.808931851000011,
177
  "count": 1,
178
- "self": 8.808931851000011
179
- },
180
- "TrainerController.advance": {
181
- "total": 436.183944828006,
182
- "count": 18203,
183
- "self": 0.2850680620017556,
184
- "children": {
185
- "env_step": {
186
- "total": 435.89887676600426,
187
- "count": 18203,
188
- "self": 282.92824375899136,
189
- "children": {
190
- "SubprocessEnvManager._take_step": {
191
- "total": 152.68716869399498,
192
- "count": 18203,
193
- "self": 1.439869030007344,
194
- "children": {
195
- "TorchPolicy.evaluate": {
196
- "total": 151.24729966398763,
197
- "count": 18203,
198
- "self": 34.8434197960006,
199
- "children": {
200
- "TorchPolicy.sample_actions": {
201
- "total": 116.40387986798703,
202
- "count": 18203,
203
- "self": 116.40387986798703
204
- }
205
- }
206
- }
207
- }
208
- },
209
- "workers": {
210
- "total": 0.2834643130179302,
211
- "count": 18203,
212
- "self": 0.0,
213
- "children": {
214
- "worker_root": {
215
- "total": 444.3742371149806,
216
- "count": 18203,
217
- "is_parallel": true,
218
- "self": 217.0628783499743,
219
- "children": {
220
- "run_training.setup": {
221
- "total": 0.0,
222
- "count": 0,
223
- "is_parallel": true,
224
- "self": 0.0,
225
- "children": {
226
- "steps_from_proto": {
227
- "total": 0.0057287120000637515,
228
- "count": 1,
229
- "is_parallel": true,
230
- "self": 0.003152651999812406,
231
- "children": {
232
- "_process_rank_one_or_two_observation": {
233
- "total": 0.0025760600002513456,
234
- "count": 10,
235
- "is_parallel": true,
236
- "self": 0.0025760600002513456
237
- }
238
- }
239
- },
240
- "UnityEnvironment.step": {
241
- "total": 0.03502038300007371,
242
- "count": 1,
243
- "is_parallel": true,
244
- "self": 0.0005591140002252359,
245
- "children": {
246
- "UnityEnvironment._generate_step_input": {
247
- "total": 0.0003283959999862418,
248
- "count": 1,
249
- "is_parallel": true,
250
- "self": 0.0003283959999862418
251
- },
252
- "communicator.exchange": {
253
- "total": 0.032003986999939116,
254
- "count": 1,
255
- "is_parallel": true,
256
- "self": 0.032003986999939116
257
- },
258
- "steps_from_proto": {
259
- "total": 0.0021288859999231136,
260
- "count": 1,
261
- "is_parallel": true,
262
- "self": 0.0004957109999850218,
263
- "children": {
264
- "_process_rank_one_or_two_observation": {
265
- "total": 0.0016331749999380918,
266
- "count": 10,
267
- "is_parallel": true,
268
- "self": 0.0016331749999380918
269
- }
270
- }
271
- }
272
- }
273
- }
274
- }
275
- },
276
- "UnityEnvironment.step": {
277
- "total": 227.31135876500628,
278
- "count": 18202,
279
- "is_parallel": true,
280
- "self": 8.70728544600047,
281
- "children": {
282
- "UnityEnvironment._generate_step_input": {
283
- "total": 5.354453021002655,
284
- "count": 18202,
285
- "is_parallel": true,
286
- "self": 5.354453021002655
287
- },
288
- "communicator.exchange": {
289
- "total": 180.61450623899657,
290
- "count": 18202,
291
- "is_parallel": true,
292
- "self": 180.61450623899657
293
- },
294
- "steps_from_proto": {
295
- "total": 32.63511405900658,
296
- "count": 18202,
297
- "is_parallel": true,
298
- "self": 6.979137509995553,
299
- "children": {
300
- "_process_rank_one_or_two_observation": {
301
- "total": 25.65597654901103,
302
- "count": 182020,
303
- "is_parallel": true,
304
- "self": 25.65597654901103
305
- }
306
- }
307
- }
308
- }
309
- }
310
- }
311
- }
312
- }
313
- }
314
- }
315
- }
316
- }
317
  },
318
  "trainer_threads": {
319
- "total": 4.878200002167432e-05,
320
  "count": 1,
321
- "self": 4.878200002167432e-05,
322
  "children": {
323
  "thread_root": {
324
  "total": 0.0,
@@ -327,38 +43,16 @@
327
  "self": 0.0,
328
  "children": {
329
  "trainer_advance": {
330
- "total": 432.93975211699353,
331
- "count": 351789,
332
  "is_parallel": true,
333
- "self": 9.610342719021219,
334
  "children": {
335
  "process_trajectory": {
336
- "total": 248.12628097297284,
337
- "count": 351789,
338
- "is_parallel": true,
339
- "self": 247.31418318497276,
340
- "children": {
341
- "RLTrainer._checkpoint": {
342
- "total": 0.8120977880000737,
343
- "count": 4,
344
- "is_parallel": true,
345
- "self": 0.8120977880000737
346
- }
347
- }
348
- },
349
- "_update_policy": {
350
- "total": 175.20312842499948,
351
- "count": 90,
352
  "is_parallel": true,
353
- "self": 45.383336348001876,
354
- "children": {
355
- "TorchPPOOptimizer.update": {
356
- "total": 129.8197920769976,
357
- "count": 4587,
358
- "is_parallel": true,
359
- "self": 129.8197920769976
360
- }
361
- }
362
  }
363
  }
364
  }
@@ -367,14 +61,14 @@
367
  }
368
  },
369
  "TrainerController._save_models": {
370
- "total": 0.1287102420001247,
371
  "count": 1,
372
- "self": 0.0008558790002552996,
373
  "children": {
374
  "RLTrainer._checkpoint": {
375
- "total": 0.1278543629998694,
376
  "count": 1,
377
- "self": 0.1278543629998694
378
  }
379
  }
380
  }
 
1
  {
2
  "name": "root",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3
  "metadata": {
4
  "timer_format_version": "0.1.0",
5
+ "start_time_seconds": "1673979996",
6
  "python_version": "3.8.16 (default, Dec 7 2022, 01:12:13) \n[GCC 7.5.0]",
7
+ "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics --resume",
8
  "mlagents_version": "0.29.0.dev0",
9
  "mlagents_envs_version": "0.29.0.dev0",
10
  "communication_protocol_version": "1.5.0",
11
  "pytorch_version": "1.8.1+cu102",
12
  "numpy_version": "1.21.6",
13
+ "end_time_seconds": "1673980003"
14
  },
15
+ "total": 6.6908181350002,
16
  "count": 1,
17
+ "self": 0.4361209480002799,
18
  "children": {
19
  "run_training.setup": {
20
+ "total": 0.10750213400001485,
21
  "count": 1,
22
+ "self": 0.10750213400001485
23
  },
24
  "TrainerController.start_learning": {
25
+ "total": 6.147195052999905,
26
  "count": 1,
27
+ "self": 0.00030923899998924753,
28
  "children": {
29
  "TrainerController._reset_env": {
30
+ "total": 6.008276127000045,
31
  "count": 1,
32
+ "self": 6.008276127000045
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
33
  },
34
  "trainer_threads": {
35
+ "total": 2.2739999849363812e-05,
36
  "count": 1,
37
+ "self": 2.2739999849363812e-05,
38
  "children": {
39
  "thread_root": {
40
  "total": 0.0,
 
43
  "self": 0.0,
44
  "children": {
45
  "trainer_advance": {
46
+ "total": 0.00021882999999434105,
47
+ "count": 1,
48
  "is_parallel": true,
49
+ "self": 2.0627999901989824e-05,
50
  "children": {
51
  "process_trajectory": {
52
+ "total": 0.00019820200009235123,
53
+ "count": 1,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
54
  "is_parallel": true,
55
+ "self": 0.00019820200009235123
 
 
 
 
 
 
 
 
56
  }
57
  }
58
  }
 
61
  }
62
  },
63
  "TrainerController._save_models": {
64
+ "total": 0.1385869470000216,
65
  "count": 1,
66
+ "self": 0.0010593470001367677,
67
  "children": {
68
  "RLTrainer._checkpoint": {
69
+ "total": 0.13752759999988484,
70
  "count": 1,
71
+ "self": 0.13752759999988484
72
  }
73
  }
74
  }
run_logs/training_status.json CHANGED
@@ -45,13 +45,22 @@
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": 25.0,
54
- "creation_time": 1673979574.819088,
55
  "auxillary_file_paths": [
56
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
57
  ]
 
45
  "auxillary_file_paths": [
46
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
47
  ]
48
+ },
49
+ {
50
+ "steps": 200112,
51
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.onnx",
52
+ "reward": null,
53
+ "creation_time": 1673980002.6959622,
54
+ "auxillary_file_paths": [
55
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
56
+ ]
57
  }
58
  ],
59
  "final_checkpoint": {
60
  "steps": 200112,
61
  "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
62
+ "reward": null,
63
+ "creation_time": 1673980002.6959622,
64
  "auxillary_file_paths": [
65
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
66
  ]