chavicoski commited on
Commit
80b39f5
1 Parent(s): 16f1b1a

Upload . with huggingface_hub

Browse files
.gitattributes CHANGED
@@ -32,3 +32,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
32
  *.zip filter=lfs diff=lfs merge=lfs -text
33
  *.zst filter=lfs diff=lfs merge=lfs -text
34
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
32
  *.zip filter=lfs diff=lfs merge=lfs -text
33
  *.zst filter=lfs diff=lfs merge=lfs -text
34
  *tfevents* filter=lfs diff=lfs merge=lfs -text
35
+ replay.mp4 filter=lfs diff=lfs merge=lfs -text
.summary/0/events.out.tfevents.1677404576.9eb66047014d ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01376fe98f844f34646c0f7ad74363ed7f43b040e45434d4de09029d60c65348
3
+ size 4168
README.md CHANGED
@@ -15,7 +15,7 @@ model-index:
15
  type: doom_health_gathering_supreme
16
  metrics:
17
  - type: mean_reward
18
- value: 4.10 +/- 0.81
19
  name: mean_reward
20
  verified: false
21
  ---
 
15
  type: doom_health_gathering_supreme
16
  metrics:
17
  - type: mean_reward
18
+ value: 3.97 +/- 0.21
19
  name: mean_reward
20
  verified: false
21
  ---
checkpoint_p0/best_000000026_106496_reward_4.390.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cacb1239206205f5d7a6cff8024ac7962fa46a181407eab3940057aa1a13b8c7
3
+ size 34928614
checkpoint_p0/checkpoint_000000026_106496.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b087142cf857cbbf43567536c6d1877683c80a06931d31bfe3eb97ef32d29dba
3
+ size 34929028
config.json CHANGED
@@ -65,7 +65,7 @@
65
  "summaries_use_frameskip": true,
66
  "heartbeat_interval": 20,
67
  "heartbeat_reporting_interval": 600,
68
- "train_for_env_steps": 10000,
69
  "train_for_seconds": 10000000000,
70
  "save_every_sec": 120,
71
  "keep_checkpoints": 2,
@@ -130,12 +130,12 @@
130
  "wide_aspect_ratio": false,
131
  "eval_env_frameskip": 1,
132
  "fps": 35,
133
- "command_line": "--env=doom_health_gathering_supreme --num_workers=12 --num_envs_per_worker=4 --train_for_env_steps=10000",
134
  "cli_args": {
135
  "env": "doom_health_gathering_supreme",
136
  "num_workers": 12,
137
  "num_envs_per_worker": 4,
138
- "train_for_env_steps": 10000
139
  },
140
  "git_hash": "unknown",
141
  "git_repo_name": "not a git repository"
 
65
  "summaries_use_frameskip": true,
66
  "heartbeat_interval": 20,
67
  "heartbeat_reporting_interval": 600,
68
+ "train_for_env_steps": 100000,
69
  "train_for_seconds": 10000000000,
70
  "save_every_sec": 120,
71
  "keep_checkpoints": 2,
 
130
  "wide_aspect_ratio": false,
131
  "eval_env_frameskip": 1,
132
  "fps": 35,
133
+ "command_line": "--env=doom_health_gathering_supreme --num_workers=12 --num_envs_per_worker=4 --train_for_env_steps=100000",
134
  "cli_args": {
135
  "env": "doom_health_gathering_supreme",
136
  "num_workers": 12,
137
  "num_envs_per_worker": 4,
138
+ "train_for_env_steps": 100000
139
  },
140
  "git_hash": "unknown",
141
  "git_repo_name": "not a git repository"
replay.mp4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8754468bbe5516fc4ee2f1c60eb4971f884992ebc479009b319ed841ba60430b
3
+ size 5886515
sf_log.txt CHANGED
@@ -1,47 +1,47 @@
1
- [2023-02-26 09:32:07,567][00001] Saving configuration to /workspace/train_dir/default_experiment/config.json...
2
- [2023-02-26 09:32:07,568][00001] Rollout worker 0 uses device cpu
3
- [2023-02-26 09:32:07,568][00001] Rollout worker 1 uses device cpu
4
- [2023-02-26 09:32:07,568][00001] Rollout worker 2 uses device cpu
5
- [2023-02-26 09:32:07,568][00001] Rollout worker 3 uses device cpu
6
- [2023-02-26 09:32:07,568][00001] Rollout worker 4 uses device cpu
7
- [2023-02-26 09:32:07,568][00001] Rollout worker 5 uses device cpu
8
- [2023-02-26 09:32:07,568][00001] Rollout worker 6 uses device cpu
9
- [2023-02-26 09:32:07,568][00001] Rollout worker 7 uses device cpu
10
- [2023-02-26 09:32:07,568][00001] Rollout worker 8 uses device cpu
11
- [2023-02-26 09:32:07,568][00001] Rollout worker 9 uses device cpu
12
- [2023-02-26 09:32:07,568][00001] Rollout worker 10 uses device cpu
13
- [2023-02-26 09:32:07,568][00001] Rollout worker 11 uses device cpu
14
- [2023-02-26 09:32:07,624][00001] Using GPUs [0] for process 0 (actually maps to GPUs [0])
15
- [2023-02-26 09:32:07,624][00001] InferenceWorker_p0-w0: min num requests: 4
16
- [2023-02-26 09:32:07,647][00001] Starting all processes...
17
- [2023-02-26 09:32:07,647][00001] Starting process learner_proc0
18
- [2023-02-26 09:32:08,374][00001] Starting all processes...
19
- [2023-02-26 09:32:08,377][00001] Starting process inference_proc0-0
20
- [2023-02-26 09:32:08,377][00001] Starting process rollout_proc0
21
- [2023-02-26 09:32:08,377][00001] Starting process rollout_proc1
22
- [2023-02-26 09:32:08,378][00141] Using GPUs [0] for process 0 (actually maps to GPUs [0])
23
- [2023-02-26 09:32:08,378][00141] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for learning process 0
24
- [2023-02-26 09:32:08,377][00001] Starting process rollout_proc2
25
- [2023-02-26 09:32:08,377][00001] Starting process rollout_proc3
26
- [2023-02-26 09:32:08,377][00001] Starting process rollout_proc4
27
- [2023-02-26 09:32:08,378][00001] Starting process rollout_proc5
28
- [2023-02-26 09:32:08,378][00001] Starting process rollout_proc6
29
- [2023-02-26 09:32:08,387][00141] Num visible devices: 1
30
- [2023-02-26 09:32:08,378][00001] Starting process rollout_proc7
31
- [2023-02-26 09:32:08,379][00001] Starting process rollout_proc8
32
- [2023-02-26 09:32:08,380][00001] Starting process rollout_proc9
33
- [2023-02-26 09:32:08,381][00001] Starting process rollout_proc10
34
- [2023-02-26 09:32:08,383][00001] Starting process rollout_proc11
35
- [2023-02-26 09:32:08,422][00141] Starting seed is not provided
36
- [2023-02-26 09:32:08,422][00141] Using GPUs [0] for process 0 (actually maps to GPUs [0])
37
- [2023-02-26 09:32:08,422][00141] Initializing actor-critic model on device cuda:0
38
- [2023-02-26 09:32:08,422][00141] RunningMeanStd input shape: (3, 72, 128)
39
- [2023-02-26 09:32:08,423][00141] RunningMeanStd input shape: (1,)
40
- [2023-02-26 09:32:08,438][00141] ConvEncoder: input_channels=3
41
- [2023-02-26 09:32:08,565][00141] Conv encoder output size: 512
42
- [2023-02-26 09:32:08,566][00141] Policy head output size: 512
43
- [2023-02-26 09:32:08,579][00141] Created Actor Critic model with architecture:
44
- [2023-02-26 09:32:08,579][00141] ActorCriticSharedWeights(
45
  (obs_normalizer): ObservationNormalizer(
46
  (running_mean_std): RunningMeanStdDictInPlace(
47
  (running_mean_std): ModuleDict(
@@ -82,275 +82,315 @@
82
  (distribution_linear): Linear(in_features=512, out_features=5, bias=True)
83
  )
84
  )
85
- [2023-02-26 09:32:09,423][00201] Worker 10 uses CPU cores [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31]
86
- [2023-02-26 09:32:09,462][00197] Worker 8 uses CPU cores [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31]
87
- [2023-02-26 09:32:09,464][00195] Worker 4 uses CPU cores [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31]
88
- [2023-02-26 09:32:09,486][00190] Using GPUs [0] for process 0 (actually maps to GPUs [0])
89
- [2023-02-26 09:32:09,486][00192] Worker 2 uses CPU cores [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31]
90
- [2023-02-26 09:32:09,486][00190] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for inference process 0
91
- [2023-02-26 09:32:09,488][00196] Worker 6 uses CPU cores [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31]
92
- [2023-02-26 09:32:09,493][00189] Worker 1 uses CPU cores [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31]
93
- [2023-02-26 09:32:09,497][00190] Num visible devices: 1
94
- [2023-02-26 09:32:09,507][00191] Worker 0 uses CPU cores [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31]
95
- [2023-02-26 09:32:09,513][00200] Worker 9 uses CPU cores [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31]
96
- [2023-02-26 09:32:09,523][00194] Worker 5 uses CPU cores [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31]
97
- [2023-02-26 09:32:09,534][00199] Worker 11 uses CPU cores [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31]
98
- [2023-02-26 09:32:09,542][00198] Worker 7 uses CPU cores [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31]
99
- [2023-02-26 09:32:09,561][00193] Worker 3 uses CPU cores [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31]
100
- [2023-02-26 09:32:10,323][00141] Using optimizer <class 'torch.optim.adam.Adam'>
101
- [2023-02-26 09:32:10,324][00141] No checkpoints found
102
- [2023-02-26 09:32:10,324][00141] Did not load from checkpoint, starting from scratch!
103
- [2023-02-26 09:32:10,324][00141] Initialized policy 0 weights for model version 0
104
- [2023-02-26 09:32:10,325][00141] LearnerWorker_p0 finished initialization!
105
- [2023-02-26 09:32:10,325][00141] Using GPUs [0] for process 0 (actually maps to GPUs [0])
106
- [2023-02-26 09:32:10,383][00190] RunningMeanStd input shape: (3, 72, 128)
107
- [2023-02-26 09:32:10,383][00190] RunningMeanStd input shape: (1,)
108
- [2023-02-26 09:32:10,391][00190] ConvEncoder: input_channels=3
109
- [2023-02-26 09:32:10,454][00190] Conv encoder output size: 512
110
- [2023-02-26 09:32:10,454][00190] Policy head output size: 512
111
- [2023-02-26 09:32:10,996][00001] Fps is (10 sec: nan, 60 sec: nan, 300 sec: nan). Total num frames: 0. Throughput: 0: nan. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0)
112
- [2023-02-26 09:32:11,166][00001] Inference worker 0-0 is ready!
113
- [2023-02-26 09:32:11,166][00001] All inference workers are ready! Signal rollout workers to start!
114
- [2023-02-26 09:32:11,194][00196] Doom resolution: 160x120, resize resolution: (128, 72)
115
- [2023-02-26 09:32:11,199][00199] Doom resolution: 160x120, resize resolution: (128, 72)
116
- [2023-02-26 09:32:11,206][00200] Doom resolution: 160x120, resize resolution: (128, 72)
117
- [2023-02-26 09:32:11,206][00197] Doom resolution: 160x120, resize resolution: (128, 72)
118
- [2023-02-26 09:32:11,214][00193] Doom resolution: 160x120, resize resolution: (128, 72)
119
- [2023-02-26 09:32:11,214][00201] Doom resolution: 160x120, resize resolution: (128, 72)
120
- [2023-02-26 09:32:11,220][00198] Doom resolution: 160x120, resize resolution: (128, 72)
121
- [2023-02-26 09:32:11,227][00191] Doom resolution: 160x120, resize resolution: (128, 72)
122
- [2023-02-26 09:32:11,233][00189] Doom resolution: 160x120, resize resolution: (128, 72)
123
- [2023-02-26 09:32:11,234][00192] Doom resolution: 160x120, resize resolution: (128, 72)
124
- [2023-02-26 09:32:11,235][00194] Doom resolution: 160x120, resize resolution: (128, 72)
125
- [2023-02-26 09:32:11,235][00195] Doom resolution: 160x120, resize resolution: (128, 72)
126
- [2023-02-26 09:32:11,359][00196] Decorrelating experience for 0 frames...
127
- [2023-02-26 09:32:11,359][00199] Decorrelating experience for 0 frames...
128
- [2023-02-26 09:32:11,401][00197] Decorrelating experience for 0 frames...
129
- [2023-02-26 09:32:11,401][00193] Decorrelating experience for 0 frames...
130
- [2023-02-26 09:32:11,401][00200] Decorrelating experience for 0 frames...
131
- [2023-02-26 09:32:11,407][00191] Decorrelating experience for 0 frames...
132
- [2023-02-26 09:32:11,407][00192] Decorrelating experience for 0 frames...
133
- [2023-02-26 09:32:11,534][00201] Decorrelating experience for 0 frames...
134
- [2023-02-26 09:32:11,578][00197] Decorrelating experience for 32 frames...
135
- [2023-02-26 09:32:11,579][00193] Decorrelating experience for 32 frames...
136
- [2023-02-26 09:32:11,582][00198] Decorrelating experience for 0 frames...
137
- [2023-02-26 09:32:11,582][00194] Decorrelating experience for 0 frames...
138
- [2023-02-26 09:32:11,586][00199] Decorrelating experience for 32 frames...
139
- [2023-02-26 09:32:11,586][00191] Decorrelating experience for 32 frames...
140
- [2023-02-26 09:32:11,586][00192] Decorrelating experience for 32 frames...
141
- [2023-02-26 09:32:11,673][00201] Decorrelating experience for 32 frames...
142
- [2023-02-26 09:32:11,691][00189] Decorrelating experience for 0 frames...
143
- [2023-02-26 09:32:11,719][00194] Decorrelating experience for 32 frames...
144
- [2023-02-26 09:32:11,768][00200] Decorrelating experience for 32 frames...
145
- [2023-02-26 09:32:11,772][00197] Decorrelating experience for 64 frames...
146
- [2023-02-26 09:32:11,776][00193] Decorrelating experience for 64 frames...
147
- [2023-02-26 09:32:11,778][00196] Decorrelating experience for 32 frames...
148
- [2023-02-26 09:32:11,778][00199] Decorrelating experience for 64 frames...
149
- [2023-02-26 09:32:11,828][00198] Decorrelating experience for 32 frames...
150
- [2023-02-26 09:32:11,860][00191] Decorrelating experience for 64 frames...
151
- [2023-02-26 09:32:11,884][00194] Decorrelating experience for 64 frames...
152
- [2023-02-26 09:32:11,943][00200] Decorrelating experience for 64 frames...
153
- [2023-02-26 09:32:11,955][00196] Decorrelating experience for 64 frames...
154
- [2023-02-26 09:32:11,962][00197] Decorrelating experience for 96 frames...
155
- [2023-02-26 09:32:11,964][00195] Decorrelating experience for 0 frames...
156
- [2023-02-26 09:32:11,968][00193] Decorrelating experience for 96 frames...
157
- [2023-02-26 09:32:11,982][00189] Decorrelating experience for 32 frames...
158
- [2023-02-26 09:32:11,992][00198] Decorrelating experience for 64 frames...
159
- [2023-02-26 09:32:12,096][00199] Decorrelating experience for 96 frames...
160
- [2023-02-26 09:32:12,107][00192] Decorrelating experience for 64 frames...
161
- [2023-02-26 09:32:12,133][00191] Decorrelating experience for 96 frames...
162
- [2023-02-26 09:32:12,140][00201] Decorrelating experience for 64 frames...
163
- [2023-02-26 09:32:12,156][00198] Decorrelating experience for 96 frames...
164
- [2023-02-26 09:32:12,157][00194] Decorrelating experience for 96 frames...
165
- [2023-02-26 09:32:12,281][00196] Decorrelating experience for 96 frames...
166
- [2023-02-26 09:32:12,305][00192] Decorrelating experience for 96 frames...
167
- [2023-02-26 09:32:12,318][00195] Decorrelating experience for 32 frames...
168
- [2023-02-26 09:32:12,321][00200] Decorrelating experience for 96 frames...
169
- [2023-02-26 09:32:12,489][00201] Decorrelating experience for 96 frames...
170
- [2023-02-26 09:32:12,502][00189] Decorrelating experience for 64 frames...
171
- [2023-02-26 09:32:12,511][00195] Decorrelating experience for 64 frames...
172
- [2023-02-26 09:32:12,629][00141] Signal inference workers to stop experience collection...
173
- [2023-02-26 09:32:12,632][00190] InferenceWorker_p0-w0: stopping experience collection
174
- [2023-02-26 09:32:12,696][00189] Decorrelating experience for 96 frames...
175
- [2023-02-26 09:32:12,698][00195] Decorrelating experience for 96 frames...
176
- [2023-02-26 09:32:13,348][00141] Signal inference workers to resume experience collection...
177
- [2023-02-26 09:32:13,348][00190] InferenceWorker_p0-w0: resuming experience collection
178
- [2023-02-26 09:32:14,002][00141] Stopping Batcher_0...
179
- [2023-02-26 09:32:14,002][00001] Component Batcher_0 stopped!
180
- [2023-02-26 09:32:14,002][00141] Saving /workspace/train_dir/default_experiment/checkpoint_p0/checkpoint_000000004_16384.pth...
181
- [2023-02-26 09:32:14,010][00198] Stopping RolloutWorker_w7...
182
- [2023-02-26 09:32:14,010][00001] Component RolloutWorker_w7 stopped!
183
- [2023-02-26 09:32:14,011][00198] Loop rollout_proc7_evt_loop terminating...
184
- [2023-02-26 09:32:14,011][00001] Component RolloutWorker_w1 stopped!
185
- [2023-02-26 09:32:14,002][00141] Loop batcher_evt_loop terminating...
186
- [2023-02-26 09:32:14,011][00189] Stopping RolloutWorker_w1...
187
- [2023-02-26 09:32:14,011][00001] Component RolloutWorker_w10 stopped!
188
- [2023-02-26 09:32:14,011][00201] Stopping RolloutWorker_w10...
189
- [2023-02-26 09:32:14,011][00195] Stopping RolloutWorker_w4...
190
- [2023-02-26 09:32:14,011][00001] Component RolloutWorker_w4 stopped!
191
- [2023-02-26 09:32:14,011][00201] Loop rollout_proc10_evt_loop terminating...
192
- [2023-02-26 09:32:14,011][00197] Stopping RolloutWorker_w8...
193
- [2023-02-26 09:32:14,011][00189] Loop rollout_proc1_evt_loop terminating...
194
- [2023-02-26 09:32:14,011][00195] Loop rollout_proc4_evt_loop terminating...
195
- [2023-02-26 09:32:14,011][00001] Component RolloutWorker_w8 stopped!
196
- [2023-02-26 09:32:14,011][00199] Stopping RolloutWorker_w11...
197
- [2023-02-26 09:32:14,011][00001] Component RolloutWorker_w11 stopped!
198
- [2023-02-26 09:32:14,011][00197] Loop rollout_proc8_evt_loop terminating...
199
- [2023-02-26 09:32:14,011][00001] Component RolloutWorker_w2 stopped!
200
- [2023-02-26 09:32:14,011][00191] Stopping RolloutWorker_w0...
201
- [2023-02-26 09:32:14,011][00200] Stopping RolloutWorker_w9...
202
- [2023-02-26 09:32:14,011][00192] Stopping RolloutWorker_w2...
203
- [2023-02-26 09:32:14,011][00193] Stopping RolloutWorker_w3...
204
- [2023-02-26 09:32:14,011][00199] Loop rollout_proc11_evt_loop terminating...
205
- [2023-02-26 09:32:14,011][00196] Stopping RolloutWorker_w6...
206
- [2023-02-26 09:32:14,012][00001] Component RolloutWorker_w9 stopped!
207
- [2023-02-26 09:32:14,012][00191] Loop rollout_proc0_evt_loop terminating...
208
- [2023-02-26 09:32:14,012][00001] Component RolloutWorker_w3 stopped!
209
- [2023-02-26 09:32:14,011][00194] Stopping RolloutWorker_w5...
210
- [2023-02-26 09:32:14,012][00200] Loop rollout_proc9_evt_loop terminating...
211
- [2023-02-26 09:32:14,012][00193] Loop rollout_proc3_evt_loop terminating...
212
- [2023-02-26 09:32:14,012][00001] Component RolloutWorker_w0 stopped!
213
- [2023-02-26 09:32:14,012][00196] Loop rollout_proc6_evt_loop terminating...
214
- [2023-02-26 09:32:14,012][00192] Loop rollout_proc2_evt_loop terminating...
215
- [2023-02-26 09:32:14,012][00001] Component RolloutWorker_w6 stopped!
216
- [2023-02-26 09:32:14,012][00194] Loop rollout_proc5_evt_loop terminating...
217
- [2023-02-26 09:32:14,012][00001] Component RolloutWorker_w5 stopped!
218
- [2023-02-26 09:32:14,018][00190] Weights refcount: 2 0
219
- [2023-02-26 09:32:14,020][00001] Component InferenceWorker_p0-w0 stopped!
220
- [2023-02-26 09:32:14,020][00190] Stopping InferenceWorker_p0-w0...
221
- [2023-02-26 09:32:14,021][00190] Loop inference_proc0-0_evt_loop terminating...
222
- [2023-02-26 09:32:14,053][00141] Saving /workspace/train_dir/default_experiment/checkpoint_p0/checkpoint_000000004_16384.pth...
223
- [2023-02-26 09:32:14,118][00141] Stopping LearnerWorker_p0...
224
- [2023-02-26 09:32:14,118][00001] Component LearnerWorker_p0 stopped!
225
- [2023-02-26 09:32:14,119][00141] Loop learner_proc0_evt_loop terminating...
226
- [2023-02-26 09:32:14,119][00001] Waiting for process learner_proc0 to stop...
227
- [2023-02-26 09:32:14,900][00001] Waiting for process inference_proc0-0 to join...
228
- [2023-02-26 09:32:14,901][00001] Waiting for process rollout_proc0 to join...
229
- [2023-02-26 09:32:14,901][00001] Waiting for process rollout_proc1 to join...
230
- [2023-02-26 09:32:14,901][00001] Waiting for process rollout_proc2 to join...
231
- [2023-02-26 09:32:14,901][00001] Waiting for process rollout_proc3 to join...
232
- [2023-02-26 09:32:14,902][00001] Waiting for process rollout_proc4 to join...
233
- [2023-02-26 09:32:14,902][00001] Waiting for process rollout_proc5 to join...
234
- [2023-02-26 09:32:14,902][00001] Waiting for process rollout_proc6 to join...
235
- [2023-02-26 09:32:14,902][00001] Waiting for process rollout_proc7 to join...
236
- [2023-02-26 09:32:14,903][00001] Waiting for process rollout_proc8 to join...
237
- [2023-02-26 09:32:14,903][00001] Waiting for process rollout_proc9 to join...
238
- [2023-02-26 09:32:14,903][00001] Waiting for process rollout_proc10 to join...
239
- [2023-02-26 09:32:14,903][00001] Waiting for process rollout_proc11 to join...
240
- [2023-02-26 09:32:14,904][00001] Batcher 0 profile tree view:
241
- batching: 0.0462, releasing_batches: 0.0008
242
- [2023-02-26 09:32:14,904][00001] InferenceWorker_p0-w0 profile tree view:
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
243
  wait_policy: 0.0000
244
- wait_policy_total: 0.8600
245
- update_model: 0.2093
246
- weight_update: 0.0513
247
- one_step: 0.0016
248
- handle_policy_step: 0.7327
249
- deserialize: 0.0239, stack: 0.0026, obs_to_device_normalize: 0.1050, forward: 0.4757, send_messages: 0.0396
250
- prepare_outputs: 0.0622
251
- to_cpu: 0.0383
252
- [2023-02-26 09:32:14,904][00001] Learner 0 profile tree view:
253
- misc: 0.0000, prepare_batch: 1.1570
254
- train: 0.2483
255
- epoch_init: 0.0000, minibatch_init: 0.0000, losses_postprocess: 0.0007, kl_divergence: 0.0010, after_optimizer: 0.0080
256
- calculate_losses: 0.0434
257
- losses_init: 0.0000, forward_head: 0.0259, bptt_initial: 0.0108, tail: 0.0013, advantages_returns: 0.0005, losses: 0.0024
258
- bptt: 0.0021
259
- bptt_forward_core: 0.0020
260
- update: 0.1943
261
- clip: 0.0026
262
- [2023-02-26 09:32:14,904][00001] RolloutWorker_w0 profile tree view:
263
- wait_for_trajectories: 0.0006, enqueue_policy_requests: 0.0198, env_step: 0.3360, overhead: 0.0196, complete_rollouts: 0.0005
264
- save_policy_outputs: 0.0217
265
- split_output_tensors: 0.0106
266
- [2023-02-26 09:32:14,904][00001] RolloutWorker_w11 profile tree view:
267
- wait_for_trajectories: 0.0006, enqueue_policy_requests: 0.0212, env_step: 0.3282, overhead: 0.0214, complete_rollouts: 0.0006
268
- save_policy_outputs: 0.0236
269
- split_output_tensors: 0.0113
270
- [2023-02-26 09:32:14,905][00001] Loop Runner_EvtLoop terminating...
271
- [2023-02-26 09:32:14,905][00001] Runner profile tree view:
272
- main_loop: 7.2583
273
- [2023-02-26 09:32:14,905][00001] Collected {0: 16384}, FPS: 2257.3
274
- [2023-02-26 09:32:14,921][00001] Loading existing experiment configuration from /workspace/train_dir/default_experiment/config.json
275
- [2023-02-26 09:32:14,922][00001] Overriding arg 'num_workers' with value 1 passed from command line
276
- [2023-02-26 09:32:14,922][00001] Adding new argument 'no_render'=True that is not in the saved config file!
277
- [2023-02-26 09:32:14,922][00001] Adding new argument 'save_video'=True that is not in the saved config file!
278
- [2023-02-26 09:32:14,922][00001] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file!
279
- [2023-02-26 09:32:14,922][00001] Adding new argument 'video_name'=None that is not in the saved config file!
280
- [2023-02-26 09:32:14,922][00001] Adding new argument 'max_num_frames'=100000 that is not in the saved config file!
281
- [2023-02-26 09:32:14,922][00001] Adding new argument 'max_num_episodes'=10 that is not in the saved config file!
282
- [2023-02-26 09:32:14,922][00001] Adding new argument 'push_to_hub'=True that is not in the saved config file!
283
- [2023-02-26 09:32:14,923][00001] Adding new argument 'hf_repository'='chavicoski/vizdoom_health_gathering_supreme' that is not in the saved config file!
284
- [2023-02-26 09:32:14,923][00001] Adding new argument 'policy_index'=0 that is not in the saved config file!
285
- [2023-02-26 09:32:14,923][00001] Adding new argument 'eval_deterministic'=False that is not in the saved config file!
286
- [2023-02-26 09:32:14,923][00001] Adding new argument 'train_script'=None that is not in the saved config file!
287
- [2023-02-26 09:32:14,923][00001] Adding new argument 'enjoy_script'=None that is not in the saved config file!
288
- [2023-02-26 09:32:14,923][00001] Using frameskip 1 and render_action_repeat=4 for evaluation
289
- [2023-02-26 09:32:14,930][00001] Doom resolution: 160x120, resize resolution: (128, 72)
290
- [2023-02-26 09:32:14,930][00001] RunningMeanStd input shape: (3, 72, 128)
291
- [2023-02-26 09:32:14,931][00001] RunningMeanStd input shape: (1,)
292
- [2023-02-26 09:32:14,945][00001] ConvEncoder: input_channels=3
293
- [2023-02-26 09:32:15,033][00001] Conv encoder output size: 512
294
- [2023-02-26 09:32:15,034][00001] Policy head output size: 512
295
- [2023-02-26 09:32:16,298][00001] Loading state from checkpoint /workspace/train_dir/default_experiment/checkpoint_p0/checkpoint_000000004_16384.pth...
296
- [2023-02-26 09:32:16,922][00001] Num frames 100...
297
- [2023-02-26 09:32:17,014][00001] Num frames 200...
298
- [2023-02-26 09:32:17,108][00001] Num frames 300...
299
- [2023-02-26 09:32:17,200][00001] Num frames 400...
300
- [2023-02-26 09:32:17,293][00001] Num frames 500...
301
- [2023-02-26 09:32:17,386][00001] Avg episode rewards: #0: 7.440, true rewards: #0: 5.440
302
- [2023-02-26 09:32:17,387][00001] Avg episode reward: 7.440, avg true_objective: 5.440
303
- [2023-02-26 09:32:17,463][00001] Num frames 600...
304
- [2023-02-26 09:32:17,556][00001] Num frames 700...
305
- [2023-02-26 09:32:17,649][00001] Num frames 800...
306
- [2023-02-26 09:32:17,743][00001] Num frames 900...
307
- [2023-02-26 09:32:17,837][00001] Num frames 1000...
308
- [2023-02-26 09:32:17,972][00001] Avg episode rewards: #0: 7.940, true rewards: #0: 5.440
309
- [2023-02-26 09:32:17,972][00001] Avg episode reward: 7.940, avg true_objective: 5.440
310
- [2023-02-26 09:32:17,988][00001] Num frames 1100...
311
- [2023-02-26 09:32:18,095][00001] Num frames 1200...
312
- [2023-02-26 09:32:18,188][00001] Num frames 1300...
313
- [2023-02-26 09:32:18,281][00001] Num frames 1400...
314
- [2023-02-26 09:32:18,404][00001] Avg episode rewards: #0: 6.573, true rewards: #0: 4.907
315
- [2023-02-26 09:32:18,404][00001] Avg episode reward: 6.573, avg true_objective: 4.907
316
- [2023-02-26 09:32:18,442][00001] Num frames 1500...
317
- [2023-02-26 09:32:18,543][00001] Num frames 1600...
318
- [2023-02-26 09:32:18,635][00001] Num frames 1700...
319
- [2023-02-26 09:32:18,728][00001] Num frames 1800...
320
- [2023-02-26 09:32:18,832][00001] Avg episode rewards: #0: 5.890, true rewards: #0: 4.640
321
- [2023-02-26 09:32:18,833][00001] Avg episode reward: 5.890, avg true_objective: 4.640
322
- [2023-02-26 09:32:18,890][00001] Num frames 1900...
323
- [2023-02-26 09:32:18,986][00001] Num frames 2000...
324
- [2023-02-26 09:32:19,079][00001] Num frames 2100...
325
- [2023-02-26 09:32:19,173][00001] Num frames 2200...
326
- [2023-02-26 09:32:19,267][00001] Num frames 2300...
327
- [2023-02-26 09:32:19,324][00001] Avg episode rewards: #0: 5.808, true rewards: #0: 4.608
328
- [2023-02-26 09:32:19,324][00001] Avg episode reward: 5.808, avg true_objective: 4.608
329
- [2023-02-26 09:32:19,440][00001] Num frames 2400...
330
- [2023-02-26 09:32:19,532][00001] Num frames 2500...
331
- [2023-02-26 09:32:19,627][00001] Num frames 2600...
332
- [2023-02-26 09:32:19,762][00001] Avg episode rewards: #0: 5.480, true rewards: #0: 4.480
333
- [2023-02-26 09:32:19,762][00001] Avg episode reward: 5.480, avg true_objective: 4.480
334
- [2023-02-26 09:32:19,773][00001] Num frames 2700...
335
- [2023-02-26 09:32:19,866][00001] Num frames 2800...
336
- [2023-02-26 09:32:19,958][00001] Num frames 2900...
337
- [2023-02-26 09:32:20,051][00001] Avg episode rewards: #0: 5.063, true rewards: #0: 4.206
338
- [2023-02-26 09:32:20,051][00001] Avg episode reward: 5.063, avg true_objective: 4.206
339
- [2023-02-26 09:32:20,126][00001] Num frames 3000...
340
- [2023-02-26 09:32:20,219][00001] Num frames 3100...
341
- [2023-02-26 09:32:20,312][00001] Num frames 3200...
342
- [2023-02-26 09:32:20,405][00001] Num frames 3300...
343
- [2023-02-26 09:32:20,483][00001] Avg episode rewards: #0: 4.910, true rewards: #0: 4.160
344
- [2023-02-26 09:32:20,483][00001] Avg episode reward: 4.910, avg true_objective: 4.160
345
- [2023-02-26 09:32:20,575][00001] Num frames 3400...
346
- [2023-02-26 09:32:20,667][00001] Num frames 3500...
347
- [2023-02-26 09:32:20,760][00001] Num frames 3600...
348
- [2023-02-26 09:32:20,853][00001] Num frames 3700...
349
- [2023-02-26 09:32:20,917][00001] Avg episode rewards: #0: 4.791, true rewards: #0: 4.124
350
- [2023-02-26 09:32:20,917][00001] Avg episode reward: 4.791, avg true_objective: 4.124
351
- [2023-02-26 09:32:21,019][00001] Num frames 3800...
352
- [2023-02-26 09:32:21,112][00001] Num frames 3900...
353
- [2023-02-26 09:32:21,204][00001] Num frames 4000...
354
- [2023-02-26 09:32:21,346][00001] Avg episode rewards: #0: 4.696, true rewards: #0: 4.096
355
- [2023-02-26 09:32:21,346][00001] Avg episode reward: 4.696, avg true_objective: 4.096
356
- [2023-02-26 09:32:22,553][00001] Replay video saved to /workspace/train_dir/default_experiment/replay.mp4!
 
1
+ [2023-02-26 09:42:58,503][00001] Saving configuration to /workspace/train_dir/default_experiment/config.json...
2
+ [2023-02-26 09:42:58,504][00001] Rollout worker 0 uses device cpu
3
+ [2023-02-26 09:42:58,504][00001] Rollout worker 1 uses device cpu
4
+ [2023-02-26 09:42:58,504][00001] Rollout worker 2 uses device cpu
5
+ [2023-02-26 09:42:58,504][00001] Rollout worker 3 uses device cpu
6
+ [2023-02-26 09:42:58,504][00001] Rollout worker 4 uses device cpu
7
+ [2023-02-26 09:42:58,504][00001] Rollout worker 5 uses device cpu
8
+ [2023-02-26 09:42:58,504][00001] Rollout worker 6 uses device cpu
9
+ [2023-02-26 09:42:58,504][00001] Rollout worker 7 uses device cpu
10
+ [2023-02-26 09:42:58,504][00001] Rollout worker 8 uses device cpu
11
+ [2023-02-26 09:42:58,505][00001] Rollout worker 9 uses device cpu
12
+ [2023-02-26 09:42:58,505][00001] Rollout worker 10 uses device cpu
13
+ [2023-02-26 09:42:58,505][00001] Rollout worker 11 uses device cpu
14
+ [2023-02-26 09:42:58,560][00001] Using GPUs [0] for process 0 (actually maps to GPUs [0])
15
+ [2023-02-26 09:42:58,560][00001] InferenceWorker_p0-w0: min num requests: 4
16
+ [2023-02-26 09:42:58,583][00001] Starting all processes...
17
+ [2023-02-26 09:42:58,584][00001] Starting process learner_proc0
18
+ [2023-02-26 09:42:59,337][00001] Starting all processes...
19
+ [2023-02-26 09:42:59,341][00001] Starting process inference_proc0-0
20
+ [2023-02-26 09:42:59,341][00001] Starting process rollout_proc0
21
+ [2023-02-26 09:42:59,342][00141] Using GPUs [0] for process 0 (actually maps to GPUs [0])
22
+ [2023-02-26 09:42:59,342][00141] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for learning process 0
23
+ [2023-02-26 09:42:59,341][00001] Starting process rollout_proc1
24
+ [2023-02-26 09:42:59,341][00001] Starting process rollout_proc2
25
+ [2023-02-26 09:42:59,342][00001] Starting process rollout_proc3
26
+ [2023-02-26 09:42:59,342][00001] Starting process rollout_proc4
27
+ [2023-02-26 09:42:59,342][00001] Starting process rollout_proc5
28
+ [2023-02-26 09:42:59,343][00001] Starting process rollout_proc6
29
+ [2023-02-26 09:42:59,343][00001] Starting process rollout_proc7
30
+ [2023-02-26 09:42:59,351][00141] Num visible devices: 1
31
+ [2023-02-26 09:42:59,344][00001] Starting process rollout_proc8
32
+ [2023-02-26 09:42:59,344][00001] Starting process rollout_proc9
33
+ [2023-02-26 09:42:59,344][00001] Starting process rollout_proc10
34
+ [2023-02-26 09:42:59,345][00001] Starting process rollout_proc11
35
+ [2023-02-26 09:42:59,385][00141] Starting seed is not provided
36
+ [2023-02-26 09:42:59,386][00141] Using GPUs [0] for process 0 (actually maps to GPUs [0])
37
+ [2023-02-26 09:42:59,386][00141] Initializing actor-critic model on device cuda:0
38
+ [2023-02-26 09:42:59,386][00141] RunningMeanStd input shape: (3, 72, 128)
39
+ [2023-02-26 09:42:59,387][00141] RunningMeanStd input shape: (1,)
40
+ [2023-02-26 09:42:59,397][00141] ConvEncoder: input_channels=3
41
+ [2023-02-26 09:42:59,491][00141] Conv encoder output size: 512
42
+ [2023-02-26 09:42:59,491][00141] Policy head output size: 512
43
+ [2023-02-26 09:42:59,504][00141] Created Actor Critic model with architecture:
44
+ [2023-02-26 09:42:59,504][00141] ActorCriticSharedWeights(
45
  (obs_normalizer): ObservationNormalizer(
46
  (running_mean_std): RunningMeanStdDictInPlace(
47
  (running_mean_std): ModuleDict(
 
82
  (distribution_linear): Linear(in_features=512, out_features=5, bias=True)
83
  )
84
  )
85
+ [2023-02-26 09:43:00,335][00191] Worker 0 uses CPU cores [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31]
86
+ [2023-02-26 09:43:00,380][00190] Worker 1 uses CPU cores [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31]
87
+ [2023-02-26 09:43:00,384][00200] Worker 11 uses CPU cores [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31]
88
+ [2023-02-26 09:43:00,392][00189] Using GPUs [0] for process 0 (actually maps to GPUs [0])
89
+ [2023-02-26 09:43:00,392][00189] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for inference process 0
90
+ [2023-02-26 09:43:00,402][00189] Num visible devices: 1
91
+ [2023-02-26 09:43:00,439][00197] Worker 8 uses CPU cores [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31]
92
+ [2023-02-26 09:43:00,442][00193] Worker 3 uses CPU cores [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31]
93
+ [2023-02-26 09:43:00,443][00192] Worker 2 uses CPU cores [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31]
94
+ [2023-02-26 09:43:00,443][00195] Worker 5 uses CPU cores [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31]
95
+ [2023-02-26 09:43:00,445][00198] Worker 6 uses CPU cores [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31]
96
+ [2023-02-26 09:43:00,454][00199] Worker 9 uses CPU cores [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31]
97
+ [2023-02-26 09:43:00,464][00201] Worker 10 uses CPU cores [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31]
98
+ [2023-02-26 09:43:00,494][00196] Worker 4 uses CPU cores [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31]
99
+ [2023-02-26 09:43:00,497][00194] Worker 7 uses CPU cores [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31]
100
+ [2023-02-26 09:43:01,102][00141] Using optimizer <class 'torch.optim.adam.Adam'>
101
+ [2023-02-26 09:43:01,103][00141] No checkpoints found
102
+ [2023-02-26 09:43:01,103][00141] Did not load from checkpoint, starting from scratch!
103
+ [2023-02-26 09:43:01,103][00141] Initialized policy 0 weights for model version 0
104
+ [2023-02-26 09:43:01,104][00141] LearnerWorker_p0 finished initialization!
105
+ [2023-02-26 09:43:01,104][00141] Using GPUs [0] for process 0 (actually maps to GPUs [0])
106
+ [2023-02-26 09:43:01,157][00189] RunningMeanStd input shape: (3, 72, 128)
107
+ [2023-02-26 09:43:01,158][00189] RunningMeanStd input shape: (1,)
108
+ [2023-02-26 09:43:01,166][00189] ConvEncoder: input_channels=3
109
+ [2023-02-26 09:43:01,226][00189] Conv encoder output size: 512
110
+ [2023-02-26 09:43:01,226][00189] Policy head output size: 512
111
+ [2023-02-26 09:43:01,907][00001] Inference worker 0-0 is ready!
112
+ [2023-02-26 09:43:01,907][00001] All inference workers are ready! Signal rollout workers to start!
113
+ [2023-02-26 09:43:01,936][00201] Doom resolution: 160x120, resize resolution: (128, 72)
114
+ [2023-02-26 09:43:01,942][00199] Doom resolution: 160x120, resize resolution: (128, 72)
115
+ [2023-02-26 09:43:01,944][00192] Doom resolution: 160x120, resize resolution: (128, 72)
116
+ [2023-02-26 09:43:01,944][00200] Doom resolution: 160x120, resize resolution: (128, 72)
117
+ [2023-02-26 09:43:01,948][00197] Doom resolution: 160x120, resize resolution: (128, 72)
118
+ [2023-02-26 09:43:01,952][00196] Doom resolution: 160x120, resize resolution: (128, 72)
119
+ [2023-02-26 09:43:01,952][00195] Doom resolution: 160x120, resize resolution: (128, 72)
120
+ [2023-02-26 09:43:01,953][00198] Doom resolution: 160x120, resize resolution: (128, 72)
121
+ [2023-02-26 09:43:01,953][00001] Fps is (10 sec: nan, 60 sec: nan, 300 sec: nan). Total num frames: 0. Throughput: 0: nan. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0)
122
+ [2023-02-26 09:43:01,953][00190] Doom resolution: 160x120, resize resolution: (128, 72)
123
+ [2023-02-26 09:43:01,959][00191] Doom resolution: 160x120, resize resolution: (128, 72)
124
+ [2023-02-26 09:43:01,961][00194] Doom resolution: 160x120, resize resolution: (128, 72)
125
+ [2023-02-26 09:43:01,961][00193] Doom resolution: 160x120, resize resolution: (128, 72)
126
+ [2023-02-26 09:43:02,012][00192] VizDoom game.init() threw an exception ViZDoomUnexpectedExitException('Controlled ViZDoom instance exited unexpectedly.'). Terminate process...
127
+ [2023-02-26 09:43:02,012][00192] EvtLoop [rollout_proc2_evt_loop, process=rollout_proc2] unhandled exception in slot='init' connected to emitter=Emitter(object_id='Sampler', signal_name='_inference_workers_initialized'), args=()
128
+ Traceback (most recent call last):
129
+ File "/usr/local/lib/python3.10/dist-packages/sf_examples/vizdoom/doom/doom_gym.py", line 228, in _game_init
130
+ self.game.init()
131
+ vizdoom.vizdoom.ViZDoomUnexpectedExitException: Controlled ViZDoom instance exited unexpectedly.
132
+
133
+ During handling of the above exception, another exception occurred:
134
+
135
+ Traceback (most recent call last):
136
+ File "/usr/local/lib/python3.10/dist-packages/signal_slot/signal_slot.py", line 355, in _process_signal
137
+ slot_callable(*args)
138
+ File "/usr/local/lib/python3.10/dist-packages/sample_factory/algo/sampling/rollout_worker.py", line 150, in init
139
+ env_runner.init(self.timing)
140
+ File "/usr/local/lib/python3.10/dist-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 418, in init
141
+ self._reset()
142
+ File "/usr/local/lib/python3.10/dist-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 430, in _reset
143
+ observations, info = e.reset(seed=seed) # new way of doing seeding since Gym 0.26.0
144
+ File "/usr/local/lib/python3.10/dist-packages/gym/core.py", line 323, in reset
145
+ return self.env.reset(**kwargs)
146
+ File "/usr/local/lib/python3.10/dist-packages/sample_factory/algo/utils/make_env.py", line 125, in reset
147
+ obs, info = self.env.reset(**kwargs)
148
+ File "/usr/local/lib/python3.10/dist-packages/sample_factory/algo/utils/make_env.py", line 110, in reset
149
+ obs, info = self.env.reset(**kwargs)
150
+ File "/usr/local/lib/python3.10/dist-packages/sf_examples/vizdoom/doom/wrappers/scenario_wrappers/gathering_reward_shaping.py", line 30, in reset
151
+ return self.env.reset(**kwargs)
152
+ File "/usr/local/lib/python3.10/dist-packages/gym/core.py", line 379, in reset
153
+ obs, info = self.env.reset(**kwargs)
154
+ File "/usr/local/lib/python3.10/dist-packages/sample_factory/envs/env_wrappers.py", line 84, in reset
155
+ obs, info = self.env.reset(**kwargs)
156
+ File "/usr/local/lib/python3.10/dist-packages/gym/core.py", line 323, in reset
157
+ return self.env.reset(**kwargs)
158
+ File "/usr/local/lib/python3.10/dist-packages/sf_examples/vizdoom/doom/wrappers/multiplayer_stats.py", line 51, in reset
159
+ return self.env.reset(**kwargs)
160
+ File "/usr/local/lib/python3.10/dist-packages/sf_examples/vizdoom/doom/doom_gym.py", line 323, in reset
161
+ self._ensure_initialized()
162
+ File "/usr/local/lib/python3.10/dist-packages/sf_examples/vizdoom/doom/doom_gym.py", line 274, in _ensure_initialized
163
+ self.initialize()
164
+ File "/usr/local/lib/python3.10/dist-packages/sf_examples/vizdoom/doom/doom_gym.py", line 269, in initialize
165
+ self._game_init()
166
+ File "/usr/local/lib/python3.10/dist-packages/sf_examples/vizdoom/doom/doom_gym.py", line 244, in _game_init
167
+ raise EnvCriticalError()
168
+ sample_factory.envs.env_utils.EnvCriticalError
169
+ [2023-02-26 09:43:02,013][00192] Unhandled exception in evt loop rollout_proc2_evt_loop
170
+ [2023-02-26 09:43:02,143][00196] Decorrelating experience for 0 frames...
171
+ [2023-02-26 09:43:02,143][00201] Decorrelating experience for 0 frames...
172
+ [2023-02-26 09:43:02,146][00195] Decorrelating experience for 0 frames...
173
+ [2023-02-26 09:43:02,150][00197] Decorrelating experience for 0 frames...
174
+ [2023-02-26 09:43:02,150][00199] Decorrelating experience for 0 frames...
175
+ [2023-02-26 09:43:02,151][00200] Decorrelating experience for 0 frames...
176
+ [2023-02-26 09:43:02,151][00193] Decorrelating experience for 0 frames...
177
+ [2023-02-26 09:43:02,294][00196] Decorrelating experience for 32 frames...
178
+ [2023-02-26 09:43:02,299][00195] Decorrelating experience for 32 frames...
179
+ [2023-02-26 09:43:02,308][00197] Decorrelating experience for 32 frames...
180
+ [2023-02-26 09:43:02,308][00200] Decorrelating experience for 32 frames...
181
+ [2023-02-26 09:43:02,308][00199] Decorrelating experience for 32 frames...
182
+ [2023-02-26 09:43:02,322][00190] Decorrelating experience for 0 frames...
183
+ [2023-02-26 09:43:02,322][00191] Decorrelating experience for 0 frames...
184
+ [2023-02-26 09:43:02,459][00196] Decorrelating experience for 64 frames...
185
+ [2023-02-26 09:43:02,460][00191] Decorrelating experience for 32 frames...
186
+ [2023-02-26 09:43:02,463][00198] Decorrelating experience for 0 frames...
187
+ [2023-02-26 09:43:02,478][00194] Decorrelating experience for 0 frames...
188
+ [2023-02-26 09:43:02,482][00200] Decorrelating experience for 64 frames...
189
+ [2023-02-26 09:43:02,487][00193] Decorrelating experience for 32 frames...
190
+ [2023-02-26 09:43:02,600][00198] Decorrelating experience for 32 frames...
191
+ [2023-02-26 09:43:02,612][00190] Decorrelating experience for 32 frames...
192
+ [2023-02-26 09:43:02,617][00194] Decorrelating experience for 32 frames...
193
+ [2023-02-26 09:43:02,628][00191] Decorrelating experience for 64 frames...
194
+ [2023-02-26 09:43:02,645][00201] Decorrelating experience for 32 frames...
195
+ [2023-02-26 09:43:02,648][00200] Decorrelating experience for 96 frames...
196
+ [2023-02-26 09:43:02,747][00193] Decorrelating experience for 64 frames...
197
+ [2023-02-26 09:43:02,785][00196] Decorrelating experience for 96 frames...
198
+ [2023-02-26 09:43:02,785][00190] Decorrelating experience for 64 frames...
199
+ [2023-02-26 09:43:02,789][00194] Decorrelating experience for 64 frames...
200
+ [2023-02-26 09:43:02,809][00201] Decorrelating experience for 64 frames...
201
+ [2023-02-26 09:43:02,823][00198] Decorrelating experience for 64 frames...
202
+ [2023-02-26 09:43:02,919][00195] Decorrelating experience for 64 frames...
203
+ [2023-02-26 09:43:02,930][00197] Decorrelating experience for 64 frames...
204
+ [2023-02-26 09:43:02,962][00194] Decorrelating experience for 96 frames...
205
+ [2023-02-26 09:43:02,963][00190] Decorrelating experience for 96 frames...
206
+ [2023-02-26 09:43:02,979][00201] Decorrelating experience for 96 frames...
207
+ [2023-02-26 09:43:03,086][00195] Decorrelating experience for 96 frames...
208
+ [2023-02-26 09:43:03,093][00198] Decorrelating experience for 96 frames...
209
+ [2023-02-26 09:43:03,097][00193] Decorrelating experience for 96 frames...
210
+ [2023-02-26 09:43:03,253][00191] Decorrelating experience for 96 frames...
211
+ [2023-02-26 09:43:03,268][00197] Decorrelating experience for 96 frames...
212
+ [2023-02-26 09:43:03,367][00141] Signal inference workers to stop experience collection...
213
+ [2023-02-26 09:43:03,369][00189] InferenceWorker_p0-w0: stopping experience collection
214
+ [2023-02-26 09:43:03,439][00199] Decorrelating experience for 64 frames...
215
+ [2023-02-26 09:43:03,601][00199] Decorrelating experience for 96 frames...
216
+ [2023-02-26 09:43:04,082][00141] Signal inference workers to resume experience collection...
217
+ [2023-02-26 09:43:04,083][00189] InferenceWorker_p0-w0: resuming experience collection
218
+ [2023-02-26 09:43:05,239][00189] Updated weights for policy 0, policy_version 10 (0.0205)
219
+ [2023-02-26 09:43:06,097][00189] Updated weights for policy 0, policy_version 20 (0.0005)
220
+ [2023-02-26 09:43:06,558][00141] Stopping Batcher_0...
221
+ [2023-02-26 09:43:06,558][00001] Component Batcher_0 stopped!
222
+ [2023-02-26 09:43:06,558][00001] Component RolloutWorker_w2 process died already! Don't wait for it.
223
+ [2023-02-26 09:43:06,558][00141] Saving /workspace/train_dir/default_experiment/checkpoint_p0/checkpoint_000000026_106496.pth...
224
+ [2023-02-26 09:43:06,566][00191] Stopping RolloutWorker_w0...
225
+ [2023-02-26 09:43:06,566][00001] Component RolloutWorker_w0 stopped!
226
+ [2023-02-26 09:43:06,567][00001] Component RolloutWorker_w1 stopped!
227
+ [2023-02-26 09:43:06,567][00191] Loop rollout_proc0_evt_loop terminating...
228
+ [2023-02-26 09:43:06,567][00190] Stopping RolloutWorker_w1...
229
+ [2023-02-26 09:43:06,567][00001] Component RolloutWorker_w5 stopped!
230
+ [2023-02-26 09:43:06,567][00195] Stopping RolloutWorker_w5...
231
+ [2023-02-26 09:43:06,567][00193] Stopping RolloutWorker_w3...
232
+ [2023-02-26 09:43:06,567][00198] Stopping RolloutWorker_w6...
233
+ [2023-02-26 09:43:06,567][00001] Component RolloutWorker_w6 stopped!
234
+ [2023-02-26 09:43:06,567][00190] Loop rollout_proc1_evt_loop terminating...
235
+ [2023-02-26 09:43:06,567][00196] Stopping RolloutWorker_w4...
236
+ [2023-02-26 09:43:06,567][00200] Stopping RolloutWorker_w11...
237
+ [2023-02-26 09:43:06,567][00001] Component RolloutWorker_w3 stopped!
238
+ [2023-02-26 09:43:06,567][00195] Loop rollout_proc5_evt_loop terminating...
239
+ [2023-02-26 09:43:06,567][00201] Stopping RolloutWorker_w10...
240
+ [2023-02-26 09:43:06,567][00193] Loop rollout_proc3_evt_loop terminating...
241
+ [2023-02-26 09:43:06,567][00197] Stopping RolloutWorker_w8...
242
+ [2023-02-26 09:43:06,567][00196] Loop rollout_proc4_evt_loop terminating...
243
+ [2023-02-26 09:43:06,567][00194] Stopping RolloutWorker_w7...
244
+ [2023-02-26 09:43:06,567][00001] Component RolloutWorker_w11 stopped!
245
+ [2023-02-26 09:43:06,567][00199] Stopping RolloutWorker_w9...
246
+ [2023-02-26 09:43:06,567][00198] Loop rollout_proc6_evt_loop terminating...
247
+ [2023-02-26 09:43:06,567][00201] Loop rollout_proc10_evt_loop terminating...
248
+ [2023-02-26 09:43:06,567][00001] Component RolloutWorker_w4 stopped!
249
+ [2023-02-26 09:43:06,558][00141] Loop batcher_evt_loop terminating...
250
+ [2023-02-26 09:43:06,567][00197] Loop rollout_proc8_evt_loop terminating...
251
+ [2023-02-26 09:43:06,567][00200] Loop rollout_proc11_evt_loop terminating...
252
+ [2023-02-26 09:43:06,567][00194] Loop rollout_proc7_evt_loop terminating...
253
+ [2023-02-26 09:43:06,567][00001] Component RolloutWorker_w10 stopped!
254
+ [2023-02-26 09:43:06,567][00001] Component RolloutWorker_w8 stopped!
255
+ [2023-02-26 09:43:06,567][00199] Loop rollout_proc9_evt_loop terminating...
256
+ [2023-02-26 09:43:06,567][00001] Component RolloutWorker_w9 stopped!
257
+ [2023-02-26 09:43:06,568][00001] Component RolloutWorker_w7 stopped!
258
+ [2023-02-26 09:43:06,568][00189] Weights refcount: 2 0
259
+ [2023-02-26 09:43:06,569][00189] Stopping InferenceWorker_p0-w0...
260
+ [2023-02-26 09:43:06,569][00001] Component InferenceWorker_p0-w0 stopped!
261
+ [2023-02-26 09:43:06,569][00189] Loop inference_proc0-0_evt_loop terminating...
262
+ [2023-02-26 09:43:06,604][00141] Saving new best policy, reward=4.390!
263
+ [2023-02-26 09:43:06,642][00141] Saving /workspace/train_dir/default_experiment/checkpoint_p0/checkpoint_000000026_106496.pth...
264
+ [2023-02-26 09:43:06,703][00141] Stopping LearnerWorker_p0...
265
+ [2023-02-26 09:43:06,704][00141] Loop learner_proc0_evt_loop terminating...
266
+ [2023-02-26 09:43:06,704][00001] Component LearnerWorker_p0 stopped!
267
+ [2023-02-26 09:43:06,704][00001] Waiting for process learner_proc0 to stop...
268
+ [2023-02-26 09:43:07,461][00001] Waiting for process inference_proc0-0 to join...
269
+ [2023-02-26 09:43:07,461][00001] Waiting for process rollout_proc0 to join...
270
+ [2023-02-26 09:43:07,462][00001] Waiting for process rollout_proc1 to join...
271
+ [2023-02-26 09:43:07,462][00001] Waiting for process rollout_proc2 to join...
272
+ [2023-02-26 09:43:07,462][00001] Waiting for process rollout_proc3 to join...
273
+ [2023-02-26 09:43:07,462][00001] Waiting for process rollout_proc4 to join...
274
+ [2023-02-26 09:43:07,462][00001] Waiting for process rollout_proc5 to join...
275
+ [2023-02-26 09:43:07,462][00001] Waiting for process rollout_proc6 to join...
276
+ [2023-02-26 09:43:07,463][00001] Waiting for process rollout_proc7 to join...
277
+ [2023-02-26 09:43:07,463][00001] Waiting for process rollout_proc8 to join...
278
+ [2023-02-26 09:43:07,463][00001] Waiting for process rollout_proc9 to join...
279
+ [2023-02-26 09:43:07,463][00001] Waiting for process rollout_proc10 to join...
280
+ [2023-02-26 09:43:07,463][00001] Waiting for process rollout_proc11 to join...
281
+ [2023-02-26 09:43:07,463][00001] Batcher 0 profile tree view:
282
+ batching: 0.1532, releasing_batches: 0.0007
283
+ [2023-02-26 09:43:07,463][00001] InferenceWorker_p0-w0 profile tree view:
284
  wait_policy: 0.0000
285
+ wait_policy_total: 0.9246
286
+ update_model: 0.2322
287
+ weight_update: 0.0005
288
+ one_step: 0.0009
289
+ handle_policy_step: 2.4041
290
+ deserialize: 0.0945, stack: 0.0118, obs_to_device_normalize: 0.5173, forward: 1.1504, send_messages: 0.1664
291
+ prepare_outputs: 0.3547
292
+ to_cpu: 0.2425
293
+ [2023-02-26 09:43:07,464][00001] Learner 0 profile tree view:
294
+ misc: 0.0001, prepare_batch: 1.1979
295
+ train: 0.5128
296
+ epoch_init: 0.0001, minibatch_init: 0.0001, losses_postprocess: 0.0027, kl_divergence: 0.0064, after_optimizer: 0.0502
297
+ calculate_losses: 0.1581
298
+ losses_init: 0.0001, forward_head: 0.0361, bptt_initial: 0.0827, tail: 0.0069, advantages_returns: 0.0020, losses: 0.0138
299
+ bptt: 0.0144
300
+ bptt_forward_core: 0.0138
301
+ update: 0.2902
302
+ clip: 0.0156
303
+ [2023-02-26 09:43:07,464][00001] RolloutWorker_w0 profile tree view:
304
+ wait_for_trajectories: 0.0017, enqueue_policy_requests: 0.0823, env_step: 1.3537, overhead: 0.0853, complete_rollouts: 0.0022
305
+ save_policy_outputs: 0.0952
306
+ split_output_tensors: 0.0459
307
+ [2023-02-26 09:43:07,464][00001] RolloutWorker_w11 profile tree view:
308
+ wait_for_trajectories: 0.0022, enqueue_policy_requests: 0.0930, env_step: 1.6281, overhead: 0.0987, complete_rollouts: 0.0027
309
+ save_policy_outputs: 0.1110
310
+ split_output_tensors: 0.0534
311
+ [2023-02-26 09:43:07,464][00001] Loop Runner_EvtLoop terminating...
312
+ [2023-02-26 09:43:07,464][00001] Runner profile tree view:
313
+ main_loop: 8.8811
314
+ [2023-02-26 09:43:07,465][00001] Collected {0: 106496}, FPS: 11991.3
315
+ [2023-02-26 09:43:07,475][00001] Loading existing experiment configuration from /workspace/train_dir/default_experiment/config.json
316
+ [2023-02-26 09:43:07,475][00001] Overriding arg 'num_workers' with value 1 passed from command line
317
+ [2023-02-26 09:43:07,475][00001] Adding new argument 'no_render'=True that is not in the saved config file!
318
+ [2023-02-26 09:43:07,475][00001] Adding new argument 'save_video'=True that is not in the saved config file!
319
+ [2023-02-26 09:43:07,475][00001] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file!
320
+ [2023-02-26 09:43:07,475][00001] Adding new argument 'video_name'=None that is not in the saved config file!
321
+ [2023-02-26 09:43:07,476][00001] Adding new argument 'max_num_frames'=100000 that is not in the saved config file!
322
+ [2023-02-26 09:43:07,476][00001] Adding new argument 'max_num_episodes'=10 that is not in the saved config file!
323
+ [2023-02-26 09:43:07,476][00001] Adding new argument 'push_to_hub'=True that is not in the saved config file!
324
+ [2023-02-26 09:43:07,476][00001] Adding new argument 'hf_repository'='chavicoski/vizdoom_health_gathering_supreme' that is not in the saved config file!
325
+ [2023-02-26 09:43:07,476][00001] Adding new argument 'policy_index'=0 that is not in the saved config file!
326
+ [2023-02-26 09:43:07,476][00001] Adding new argument 'eval_deterministic'=False that is not in the saved config file!
327
+ [2023-02-26 09:43:07,476][00001] Adding new argument 'train_script'=None that is not in the saved config file!
328
+ [2023-02-26 09:43:07,476][00001] Adding new argument 'enjoy_script'=None that is not in the saved config file!
329
+ [2023-02-26 09:43:07,476][00001] Using frameskip 1 and render_action_repeat=4 for evaluation
330
+ [2023-02-26 09:43:07,482][00001] Doom resolution: 160x120, resize resolution: (128, 72)
331
+ [2023-02-26 09:43:07,483][00001] RunningMeanStd input shape: (3, 72, 128)
332
+ [2023-02-26 09:43:07,483][00001] RunningMeanStd input shape: (1,)
333
+ [2023-02-26 09:43:07,495][00001] ConvEncoder: input_channels=3
334
+ [2023-02-26 09:43:07,584][00001] Conv encoder output size: 512
335
+ [2023-02-26 09:43:07,584][00001] Policy head output size: 512
336
+ [2023-02-26 09:43:08,855][00001] Loading state from checkpoint /workspace/train_dir/default_experiment/checkpoint_p0/checkpoint_000000026_106496.pth...
337
+ [2023-02-26 09:43:09,479][00001] Num frames 100...
338
+ [2023-02-26 09:43:09,581][00001] Num frames 200...
339
+ [2023-02-26 09:43:09,683][00001] Num frames 300...
340
+ [2023-02-26 09:43:09,785][00001] Num frames 400...
341
+ [2023-02-26 09:43:09,888][00001] Avg episode rewards: #0: 5.480, true rewards: #0: 4.480
342
+ [2023-02-26 09:43:09,888][00001] Avg episode reward: 5.480, avg true_objective: 4.480
343
+ [2023-02-26 09:43:09,958][00001] Num frames 500...
344
+ [2023-02-26 09:43:10,064][00001] Num frames 600...
345
+ [2023-02-26 09:43:10,166][00001] Num frames 700...
346
+ [2023-02-26 09:43:10,266][00001] Num frames 800...
347
+ [2023-02-26 09:43:10,347][00001] Avg episode rewards: #0: 4.660, true rewards: #0: 4.160
348
+ [2023-02-26 09:43:10,347][00001] Avg episode reward: 4.660, avg true_objective: 4.160
349
+ [2023-02-26 09:43:10,435][00001] Num frames 900...
350
+ [2023-02-26 09:43:10,533][00001] Num frames 1000...
351
+ [2023-02-26 09:43:10,628][00001] Num frames 1100...
352
+ [2023-02-26 09:43:10,730][00001] Num frames 1200...
353
+ [2023-02-26 09:43:10,831][00001] Avg episode rewards: #0: 4.827, true rewards: #0: 4.160
354
+ [2023-02-26 09:43:10,832][00001] Avg episode reward: 4.827, avg true_objective: 4.160
355
+ [2023-02-26 09:43:10,895][00001] Num frames 1300...
356
+ [2023-02-26 09:43:10,988][00001] Num frames 1400...
357
+ [2023-02-26 09:43:11,081][00001] Num frames 1500...
358
+ [2023-02-26 09:43:11,176][00001] Num frames 1600...
359
+ [2023-02-26 09:43:11,260][00001] Avg episode rewards: #0: 4.580, true rewards: #0: 4.080
360
+ [2023-02-26 09:43:11,260][00001] Avg episode reward: 4.580, avg true_objective: 4.080
361
+ [2023-02-26 09:43:11,340][00001] Num frames 1700...
362
+ [2023-02-26 09:43:11,433][00001] Num frames 1800...
363
+ [2023-02-26 09:43:11,526][00001] Num frames 1900...
364
+ [2023-02-26 09:43:11,618][00001] Num frames 2000...
365
+ [2023-02-26 09:43:11,685][00001] Avg episode rewards: #0: 4.432, true rewards: #0: 4.032
366
+ [2023-02-26 09:43:11,685][00001] Avg episode reward: 4.432, avg true_objective: 4.032
367
+ [2023-02-26 09:43:11,778][00001] Num frames 2100...
368
+ [2023-02-26 09:43:11,871][00001] Num frames 2200...
369
+ [2023-02-26 09:43:11,974][00001] Num frames 2300...
370
+ [2023-02-26 09:43:12,072][00001] Num frames 2400...
371
+ [2023-02-26 09:43:12,158][00001] Avg episode rewards: #0: 4.387, true rewards: #0: 4.053
372
+ [2023-02-26 09:43:12,158][00001] Avg episode reward: 4.387, avg true_objective: 4.053
373
+ [2023-02-26 09:43:12,238][00001] Num frames 2500...
374
+ [2023-02-26 09:43:12,335][00001] Num frames 2600...
375
+ [2023-02-26 09:43:12,437][00001] Num frames 2700...
376
+ [2023-02-26 09:43:12,541][00001] Num frames 2800...
377
+ [2023-02-26 09:43:12,610][00001] Avg episode rewards: #0: 4.309, true rewards: #0: 4.023
378
+ [2023-02-26 09:43:12,610][00001] Avg episode reward: 4.309, avg true_objective: 4.023
379
+ [2023-02-26 09:43:12,702][00001] Num frames 2900...
380
+ [2023-02-26 09:43:12,794][00001] Num frames 3000...
381
+ [2023-02-26 09:43:12,886][00001] Num frames 3100...
382
+ [2023-02-26 09:43:12,981][00001] Num frames 3200...
383
+ [2023-02-26 09:43:13,032][00001] Avg episode rewards: #0: 4.250, true rewards: #0: 4.000
384
+ [2023-02-26 09:43:13,032][00001] Avg episode reward: 4.250, avg true_objective: 4.000
385
+ [2023-02-26 09:43:13,152][00001] Num frames 3300...
386
+ [2023-02-26 09:43:13,254][00001] Num frames 3400...
387
+ [2023-02-26 09:43:13,356][00001] Num frames 3500...
388
+ [2023-02-26 09:43:13,487][00001] Avg episode rewards: #0: 4.204, true rewards: #0: 3.982
389
+ [2023-02-26 09:43:13,487][00001] Avg episode reward: 4.204, avg true_objective: 3.982
390
+ [2023-02-26 09:43:13,507][00001] Num frames 3600...
391
+ [2023-02-26 09:43:13,625][00001] Num frames 3700...
392
+ [2023-02-26 09:43:13,728][00001] Num frames 3800...
393
+ [2023-02-26 09:43:13,830][00001] Num frames 3900...
394
+ [2023-02-26 09:43:13,953][00001] Avg episode rewards: #0: 4.168, true rewards: #0: 3.968
395
+ [2023-02-26 09:43:13,953][00001] Avg episode reward: 4.168, avg true_objective: 3.968
396
+ [2023-02-26 09:43:17,804][00001] Replay video saved to /workspace/train_dir/default_experiment/replay.mp4!