Hugging Face's logo

niks-salodkar
/
rl_course_vizdoom_health_gathering_supreme

Reinforcement Learning
sample-factory
TensorBoard
deep-reinforcement-learning
Eval Results
Model card Files Metrics Community
niks-salodkar commited on
Commit
b9b2f20
•
1 Parent(s): 62e2525

Upload . with huggingface_hub

Browse files
Files changed (9) hide show
  1. .gitattributes +1 -0
  2. .summary/0/events.out.tfevents.1679380666.antpc +3 -0
  3. README.md +56 -0
  4. checkpoint_p0/best_000001287_5271552_reward_28.868.pth +3 -0
  5. checkpoint_p0/checkpoint_000001745_7147520.pth +3 -0
  6. checkpoint_p0/checkpoint_000001955_8007680.pth +3 -0
  7. config.json +142 -0
  8. replay.mp4 +3 -0
  9. sf_log.txt +711 -0
.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.1679380666.antpc ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7bbd1b6e747af8824d4343fa6f49f4cfb995a0ecb034923c1b7f12b778736838
3
+ size 242693
README.md ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: sample-factory
3
+ tags:
4
+ - deep-reinforcement-learning
5
+ - reinforcement-learning
6
+ - sample-factory
7
+ model-index:
8
+ - name: APPO
9
+ results:
10
+ - task:
11
+ type: reinforcement-learning
12
+ name: reinforcement-learning
13
+ dataset:
14
+ name: doom_health_gathering_supreme
15
+ type: doom_health_gathering_supreme
16
+ metrics:
17
+ - type: mean_reward
18
+ value: 11.02 +/- 5.36
19
+ name: mean_reward
20
+ verified: false
21
+ ---
22
+
23
+ A(n) **APPO** model trained on the **doom_health_gathering_supreme** environment.
24
+
25
+ This model was trained using Sample-Factory 2.0: https://github.com/alex-petrenko/sample-factory.
26
+ Documentation for how to use Sample-Factory can be found at https://www.samplefactory.dev/
27
+
28
+
29
+ ## Downloading the model
30
+
31
+ After installing Sample-Factory, download the model with:
32
+ ```
33
+ python -m sample_factory.huggingface.load_from_hub -r niks-salodkar/rl_course_vizdoom_health_gathering_supreme
34
+ ```
35
+
36
+
37
+ ## Using the model
38
+
39
+ To run the model after download, use the `enjoy` script corresponding to this environment:
40
+ ```
41
+ python -m <path.to.enjoy.module> --algo=APPO --env=doom_health_gathering_supreme --train_dir=./train_dir --experiment=rl_course_vizdoom_health_gathering_supreme
42
+ ```
43
+
44
+
45
+ You can also upload models to the Hugging Face Hub using the same script with the `--push_to_hub` flag.
46
+ See https://www.samplefactory.dev/10-huggingface/huggingface/ for more details
47
+
48
+ ## Training with this model
49
+
50
+ To continue training with this model, use the `train` script corresponding to this environment:
51
+ ```
52
+ python -m <path.to.train.module> --algo=APPO --env=doom_health_gathering_supreme --train_dir=./train_dir --experiment=rl_course_vizdoom_health_gathering_supreme --restart_behavior=resume --train_for_env_steps=10000000000
53
+ ```
54
+
55
+ Note, you may have to adjust `--train_for_env_steps` to a suitably high number as the experiment will resume at the number of steps it concluded at.
56
+
checkpoint_p0/best_000001287_5271552_reward_28.868.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11d290e214670da580c38c0af59974913aba50fe54e9870fa119aee77515f3cf
3
+ size 34928614
checkpoint_p0/checkpoint_000001745_7147520.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f1ef509f7c2901dd7952c8bf1b744a32089f056741ac4f110dcc4d0558970107
3
+ size 34929028
checkpoint_p0/checkpoint_000001955_8007680.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c3741aee4bdc622de10531657c9adbc3fa437897180228ef63e3f4bea6cb6a3
3
+ size 34929028
config.json ADDED
@@ -0,0 +1,142 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "help": false,
3
+ "algo": "APPO",
4
+ "env": "doom_health_gathering_supreme",
5
+ "experiment": "default_experiment",
6
+ "train_dir": "/home/antpc/Desktop/rl_course/train_dir",
7
+ "restart_behavior": "resume",
8
+ "device": "gpu",
9
+ "seed": null,
10
+ "num_policies": 1,
11
+ "async_rl": true,
12
+ "serial_mode": false,
13
+ "batched_sampling": false,
14
+ "num_batches_to_accumulate": 2,
15
+ "worker_num_splits": 2,
16
+ "policy_workers_per_policy": 1,
17
+ "max_policy_lag": 1000,
18
+ "num_workers": 8,
19
+ "num_envs_per_worker": 4,
20
+ "batch_size": 1024,
21
+ "num_batches_per_epoch": 1,
22
+ "num_epochs": 1,
23
+ "rollout": 32,
24
+ "recurrence": 32,
25
+ "shuffle_minibatches": false,
26
+ "gamma": 0.99,
27
+ "reward_scale": 1.0,
28
+ "reward_clip": 1000.0,
29
+ "value_bootstrap": false,
30
+ "normalize_returns": true,
31
+ "exploration_loss_coeff": 0.001,
32
+ "value_loss_coeff": 0.5,
33
+ "kl_loss_coeff": 0.0,
34
+ "exploration_loss": "symmetric_kl",
35
+ "gae_lambda": 0.95,
36
+ "ppo_clip_ratio": 0.1,
37
+ "ppo_clip_value": 0.2,
38
+ "with_vtrace": false,
39
+ "vtrace_rho": 1.0,
40
+ "vtrace_c": 1.0,
41
+ "optimizer": "adam",
42
+ "adam_eps": 1e-06,
43
+ "adam_beta1": 0.9,
44
+ "adam_beta2": 0.999,
45
+ "max_grad_norm": 4.0,
46
+ "learning_rate": 0.0001,
47
+ "lr_schedule": "constant",
48
+ "lr_schedule_kl_threshold": 0.008,
49
+ "lr_adaptive_min": 1e-06,
50
+ "lr_adaptive_max": 0.01,
51
+ "obs_subtract_mean": 0.0,
52
+ "obs_scale": 255.0,
53
+ "normalize_input": true,
54
+ "normalize_input_keys": null,
55
+ "decorrelate_experience_max_seconds": 0,
56
+ "decorrelate_envs_on_one_worker": true,
57
+ "actor_worker_gpus": [],
58
+ "set_workers_cpu_affinity": true,
59
+ "force_envs_single_thread": false,
60
+ "default_niceness": 0,
61
+ "log_to_file": true,
62
+ "experiment_summaries_interval": 10,
63
+ "flush_summaries_interval": 30,
64
+ "stats_avg": 100,
65
+ "summaries_use_frameskip": true,
66
+ "heartbeat_interval": 20,
67
+ "heartbeat_reporting_interval": 600,
68
+ "train_for_env_steps": 8000000,
69
+ "train_for_seconds": 10000000000,
70
+ "save_every_sec": 120,
71
+ "keep_checkpoints": 2,
72
+ "load_checkpoint_kind": "latest",
73
+ "save_milestones_sec": -1,
74
+ "save_best_every_sec": 5,
75
+ "save_best_metric": "reward",
76
+ "save_best_after": 100000,
77
+ "benchmark": false,
78
+ "encoder_mlp_layers": [
79
+ 512,
80
+ 512
81
+ ],
82
+ "encoder_conv_architecture": "convnet_simple",
83
+ "encoder_conv_mlp_layers": [
84
+ 512
85
+ ],
86
+ "use_rnn": true,
87
+ "rnn_size": 512,
88
+ "rnn_type": "gru",
89
+ "rnn_num_layers": 1,
90
+ "decoder_mlp_layers": [],
91
+ "nonlinearity": "elu",
92
+ "policy_initialization": "orthogonal",
93
+ "policy_init_gain": 1.0,
94
+ "actor_critic_share_weights": true,
95
+ "adaptive_stddev": true,
96
+ "continuous_tanh_scale": 0.0,
97
+ "initial_stddev": 1.0,
98
+ "use_env_info_cache": false,
99
+ "env_gpu_actions": false,
100
+ "env_gpu_observations": true,
101
+ "env_frameskip": 4,
102
+ "env_framestack": 1,
103
+ "pixel_format": "CHW",
104
+ "use_record_episode_statistics": false,
105
+ "with_wandb": false,
106
+ "wandb_user": null,
107
+ "wandb_project": "sample_factory",
108
+ "wandb_group": null,
109
+ "wandb_job_type": "SF",
110
+ "wandb_tags": [],
111
+ "with_pbt": false,
112
+ "pbt_mix_policies_in_one_env": true,
113
+ "pbt_period_env_steps": 5000000,
114
+ "pbt_start_mutation": 20000000,
115
+ "pbt_replace_fraction": 0.3,
116
+ "pbt_mutation_rate": 0.15,
117
+ "pbt_replace_reward_gap": 0.1,
118
+ "pbt_replace_reward_gap_absolute": 1e-06,
119
+ "pbt_optimize_gamma": false,
120
+ "pbt_target_objective": "true_objective",
121
+ "pbt_perturb_min": 1.1,
122
+ "pbt_perturb_max": 1.5,
123
+ "num_agents": -1,
124
+ "num_humans": 0,
125
+ "num_bots": -1,
126
+ "start_bot_difficulty": null,
127
+ "timelimit": null,
128
+ "res_w": 128,
129
+ "res_h": 72,
130
+ "wide_aspect_ratio": false,
131
+ "eval_env_frameskip": 1,
132
+ "fps": 35,
133
+ "command_line": "--env=doom_health_gathering_supreme --num_workers=8 --num_envs_per_worker=4 --train_for_env_steps=8000000",
134
+ "cli_args": {
135
+ "env": "doom_health_gathering_supreme",
136
+ "num_workers": 8,
137
+ "num_envs_per_worker": 4,
138
+ "train_for_env_steps": 8000000
139
+ },
140
+ "git_hash": "unknown",
141
+ "git_repo_name": "not a git repository"
142
+ }
replay.mp4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:248d44e51b4f012ca5cd686bbf1e21b0d00b11173dcd5cf659d6a74f63a48a9e
3
+ size 20850190
sf_log.txt ADDED
@@ -0,0 +1,711 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [2023-03-21 12:07:47,963][23264] Saving configuration to /home/antpc/Desktop/rl_course/train_dir/default_experiment/config.json...
2
+ [2023-03-21 12:07:47,963][23264] Rollout worker 0 uses device cpu
3
+ [2023-03-21 12:07:47,963][23264] Rollout worker 1 uses device cpu
4
+ [2023-03-21 12:07:47,964][23264] Rollout worker 2 uses device cpu
5
+ [2023-03-21 12:07:47,964][23264] Rollout worker 3 uses device cpu
6
+ [2023-03-21 12:07:47,964][23264] Rollout worker 4 uses device cpu
7
+ [2023-03-21 12:07:47,964][23264] Rollout worker 5 uses device cpu
8
+ [2023-03-21 12:07:47,964][23264] Rollout worker 6 uses device cpu
9
+ [2023-03-21 12:07:47,964][23264] Rollout worker 7 uses device cpu
10
+ [2023-03-21 12:07:48,005][23264] Using GPUs [0] for process 0 (actually maps to GPUs [0])
11
+ [2023-03-21 12:07:48,005][23264] InferenceWorker_p0-w0: min num requests: 2
12
+ [2023-03-21 12:07:48,020][23264] Starting all processes...
13
+ [2023-03-21 12:07:48,020][23264] Starting process learner_proc0
14
+ [2023-03-21 12:07:48,688][23264] Starting all processes...
15
+ [2023-03-21 12:07:48,691][23264] Starting process inference_proc0-0
16
+ [2023-03-21 12:07:48,691][23264] Starting process rollout_proc0
17
+ [2023-03-21 12:07:48,691][23332] Using GPUs [0] for process 0 (actually maps to GPUs [0])
18
+ [2023-03-21 12:07:48,692][23332] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for learning process 0
19
+ [2023-03-21 12:07:48,691][23264] Starting process rollout_proc1
20
+ [2023-03-21 12:07:48,700][23332] Num visible devices: 1
21
+ [2023-03-21 12:07:48,693][23264] Starting process rollout_proc2
22
+ [2023-03-21 12:07:48,694][23264] Starting process rollout_proc3
23
+ [2023-03-21 12:07:48,694][23264] Starting process rollout_proc4
24
+ [2023-03-21 12:07:48,696][23264] Starting process rollout_proc5
25
+ [2023-03-21 12:07:48,700][23264] Starting process rollout_proc6
26
+ [2023-03-21 12:07:48,701][23264] Starting process rollout_proc7
27
+ [2023-03-21 12:07:48,744][23332] Starting seed is not provided
28
+ [2023-03-21 12:07:48,745][23332] Using GPUs [0] for process 0 (actually maps to GPUs [0])
29
+ [2023-03-21 12:07:48,745][23332] Initializing actor-critic model on device cuda:0
30
+ [2023-03-21 12:07:48,745][23332] RunningMeanStd input shape: (3, 72, 128)
31
+ [2023-03-21 12:07:48,746][23332] RunningMeanStd input shape: (1,)
32
+ [2023-03-21 12:07:48,758][23332] ConvEncoder: input_channels=3
33
+ [2023-03-21 12:07:48,873][23332] Conv encoder output size: 512
34
+ [2023-03-21 12:07:48,873][23332] Policy head output size: 512
35
+ [2023-03-21 12:07:48,886][23332] Created Actor Critic model with architecture:
36
+ [2023-03-21 12:07:48,886][23332] ActorCriticSharedWeights(
37
+ (obs_normalizer): ObservationNormalizer(
38
+ (running_mean_std): RunningMeanStdDictInPlace(
39
+ (running_mean_std): ModuleDict(
40
+ (obs): RunningMeanStdInPlace()
41
+ )
42
+ )
43
+ )
44
+ (returns_normalizer): RecursiveScriptModule(original_name=RunningMeanStdInPlace)
45
+ (encoder): VizdoomEncoder(
46
+ (basic_encoder): ConvEncoder(
47
+ (enc): RecursiveScriptModule(
48
+ original_name=ConvEncoderImpl
49
+ (conv_head): RecursiveScriptModule(
50
+ original_name=Sequential
51
+ (0): RecursiveScriptModule(original_name=Conv2d)
52
+ (1): RecursiveScriptModule(original_name=ELU)
53
+ (2): RecursiveScriptModule(original_name=Conv2d)
54
+ (3): RecursiveScriptModule(original_name=ELU)
55
+ (4): RecursiveScriptModule(original_name=Conv2d)
56
+ (5): RecursiveScriptModule(original_name=ELU)
57
+ )
58
+ (mlp_layers): RecursiveScriptModule(
59
+ original_name=Sequential
60
+ (0): RecursiveScriptModule(original_name=Linear)
61
+ (1): RecursiveScriptModule(original_name=ELU)
62
+ )
63
+ )
64
+ )
65
+ )
66
+ (core): ModelCoreRNN(
67
+ (core): GRU(512, 512)
68
+ )
69
+ (decoder): MlpDecoder(
70
+ (mlp): Identity()
71
+ )
72
+ (critic_linear): Linear(in_features=512, out_features=1, bias=True)
73
+ (action_parameterization): ActionParameterizationDefault(
74
+ (distribution_linear): Linear(in_features=512, out_features=5, bias=True)
75
+ )
76
+ )
77
+ [2023-03-21 12:07:49,710][23363] Worker 1 uses CPU cores [2, 3]
78
+ [2023-03-21 12:07:49,746][23366] Worker 4 uses CPU cores [8, 9]
79
+ [2023-03-21 12:07:49,850][23365] Worker 3 uses CPU cores [6, 7]
80
+ [2023-03-21 12:07:49,866][23367] Worker 5 uses CPU cores [10, 11]
81
+ [2023-03-21 12:07:49,894][23383] Worker 6 uses CPU cores [12, 13]
82
+ [2023-03-21 12:07:49,902][23361] Worker 0 uses CPU cores [0, 1]
83
+ [2023-03-21 12:07:49,913][23384] Worker 7 uses CPU cores [14, 15]
84
+ [2023-03-21 12:07:49,930][23364] Worker 2 uses CPU cores [4, 5]
85
+ [2023-03-21 12:07:49,995][23362] Using GPUs [0] for process 0 (actually maps to GPUs [0])
86
+ [2023-03-21 12:07:49,995][23362] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for inference process 0
87
+ [2023-03-21 12:07:50,004][23362] Num visible devices: 1
88
+ [2023-03-21 12:07:50,512][23332] Using optimizer <class 'torch.optim.adam.Adam'>
89
+ [2023-03-21 12:07:50,512][23332] No checkpoints found
90
+ [2023-03-21 12:07:50,512][23332] Did not load from checkpoint, starting from scratch!
91
+ [2023-03-21 12:07:50,512][23332] Initialized policy 0 weights for model version 0
92
+ [2023-03-21 12:07:50,513][23332] LearnerWorker_p0 finished initialization!
93
+ [2023-03-21 12:07:50,514][23332] Using GPUs [0] for process 0 (actually maps to GPUs [0])
94
+ [2023-03-21 12:07:50,560][23362] RunningMeanStd input shape: (3, 72, 128)
95
+ [2023-03-21 12:07:50,560][23362] RunningMeanStd input shape: (1,)
96
+ [2023-03-21 12:07:50,568][23362] ConvEncoder: input_channels=3
97
+ [2023-03-21 12:07:50,623][23362] Conv encoder output size: 512
98
+ [2023-03-21 12:07:50,623][23362] Policy head output size: 512
99
+ [2023-03-21 12:07:51,490][23264] 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)
100
+ [2023-03-21 12:07:51,846][23264] Inference worker 0-0 is ready!
101
+ [2023-03-21 12:07:51,846][23264] All inference workers are ready! Signal rollout workers to start!
102
+ [2023-03-21 12:07:51,861][23361] Doom resolution: 160x120, resize resolution: (128, 72)
103
+ [2023-03-21 12:07:51,862][23366] Doom resolution: 160x120, resize resolution: (128, 72)
104
+ [2023-03-21 12:07:51,863][23384] Doom resolution: 160x120, resize resolution: (128, 72)
105
+ [2023-03-21 12:07:51,863][23367] Doom resolution: 160x120, resize resolution: (128, 72)
106
+ [2023-03-21 12:07:51,864][23364] Doom resolution: 160x120, resize resolution: (128, 72)
107
+ [2023-03-21 12:07:51,864][23365] Doom resolution: 160x120, resize resolution: (128, 72)
108
+ [2023-03-21 12:07:51,864][23383] Doom resolution: 160x120, resize resolution: (128, 72)
109
+ [2023-03-21 12:07:51,864][23363] Doom resolution: 160x120, resize resolution: (128, 72)
110
+ [2023-03-21 12:07:52,025][23364] Decorrelating experience for 0 frames...
111
+ [2023-03-21 12:07:52,026][23384] Decorrelating experience for 0 frames...
112
+ [2023-03-21 12:07:52,059][23361] Decorrelating experience for 0 frames...
113
+ [2023-03-21 12:07:52,060][23363] Decorrelating experience for 0 frames...
114
+ [2023-03-21 12:07:52,061][23367] Decorrelating experience for 0 frames...
115
+ [2023-03-21 12:07:52,078][23366] Decorrelating experience for 0 frames...
116
+ [2023-03-21 12:07:52,175][23384] Decorrelating experience for 32 frames...
117
+ [2023-03-21 12:07:52,225][23367] Decorrelating experience for 32 frames...
118
+ [2023-03-21 12:07:52,226][23363] Decorrelating experience for 32 frames...
119
+ [2023-03-21 12:07:52,234][23364] Decorrelating experience for 32 frames...
120
+ [2023-03-21 12:07:52,236][23365] Decorrelating experience for 0 frames...
121
+ [2023-03-21 12:07:52,239][23361] Decorrelating experience for 32 frames...
122
+ [2023-03-21 12:07:52,268][23366] Decorrelating experience for 32 frames...
123
+ [2023-03-21 12:07:52,374][23365] Decorrelating experience for 32 frames...
124
+ [2023-03-21 12:07:52,386][23363] Decorrelating experience for 64 frames...
125
+ [2023-03-21 12:07:52,418][23364] Decorrelating experience for 64 frames...
126
+ [2023-03-21 12:07:52,427][23366] Decorrelating experience for 64 frames...
127
+ [2023-03-21 12:07:52,445][23383] Decorrelating experience for 0 frames...
128
+ [2023-03-21 12:07:52,553][23361] Decorrelating experience for 64 frames...
129
+ [2023-03-21 12:07:52,558][23363] Decorrelating experience for 96 frames...
130
+ [2023-03-21 12:07:52,565][23365] Decorrelating experience for 64 frames...
131
+ [2023-03-21 12:07:52,618][23364] Decorrelating experience for 96 frames...
132
+ [2023-03-21 12:07:52,632][23383] Decorrelating experience for 32 frames...
133
+ [2023-03-21 12:07:52,652][23384] Decorrelating experience for 64 frames...
134
+ [2023-03-21 12:07:52,736][23367] Decorrelating experience for 64 frames...
135
+ [2023-03-21 12:07:52,748][23361] Decorrelating experience for 96 frames...
136
+ [2023-03-21 12:07:52,752][23365] Decorrelating experience for 96 frames...
137
+ [2023-03-21 12:07:52,793][23366] Decorrelating experience for 96 frames...
138
+ [2023-03-21 12:07:52,824][23383] Decorrelating experience for 64 frames...
139
+ [2023-03-21 12:07:52,843][23384] Decorrelating experience for 96 frames...
140
+ [2023-03-21 12:07:52,893][23367] Decorrelating experience for 96 frames...
141
+ [2023-03-21 12:07:52,981][23383] Decorrelating experience for 96 frames...
142
+ [2023-03-21 12:07:53,334][23332] Signal inference workers to stop experience collection...
143
+ [2023-03-21 12:07:53,337][23362] InferenceWorker_p0-w0: stopping experience collection
144
+ [2023-03-21 12:07:54,059][23332] Signal inference workers to resume experience collection...
145
+ [2023-03-21 12:07:54,060][23362] InferenceWorker_p0-w0: resuming experience collection
146
+ [2023-03-21 12:07:55,468][23362] Updated weights for policy 0, policy_version 10 (0.0185)
147
+ [2023-03-21 12:07:56,490][23264] Fps is (10 sec: 13926.6, 60 sec: 13926.6, 300 sec: 13926.6). Total num frames: 69632. Throughput: 0: 1115.2. Samples: 5576. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0)
148
+ [2023-03-21 12:07:56,490][23264] Avg episode reward: [(0, '4.399')]
149
+ [2023-03-21 12:07:56,754][23362] Updated weights for policy 0, policy_version 20 (0.0007)
150
+ [2023-03-21 12:07:58,045][23362] Updated weights for policy 0, policy_version 30 (0.0006)
151
+ [2023-03-21 12:07:59,348][23362] Updated weights for policy 0, policy_version 40 (0.0006)
152
+ [2023-03-21 12:08:00,646][23362] Updated weights for policy 0, policy_version 50 (0.0006)
153
+ [2023-03-21 12:08:01,490][23264] Fps is (10 sec: 22937.7, 60 sec: 22937.7, 300 sec: 22937.7). Total num frames: 229376. Throughput: 0: 5343.4. Samples: 53434. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
154
+ [2023-03-21 12:08:01,490][23264] Avg episode reward: [(0, '4.422')]
155
+ [2023-03-21 12:08:01,490][23332] Saving new best policy, reward=4.422!
156
+ [2023-03-21 12:08:01,931][23362] Updated weights for policy 0, policy_version 60 (0.0006)
157
+ [2023-03-21 12:08:03,249][23362] Updated weights for policy 0, policy_version 70 (0.0007)
158
+ [2023-03-21 12:08:04,554][23362] Updated weights for policy 0, policy_version 80 (0.0006)
159
+ [2023-03-21 12:08:05,847][23362] Updated weights for policy 0, policy_version 90 (0.0006)
160
+ [2023-03-21 12:08:06,490][23264] Fps is (10 sec: 31539.2, 60 sec: 25668.4, 300 sec: 25668.4). Total num frames: 385024. Throughput: 0: 5141.4. Samples: 77120. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
161
+ [2023-03-21 12:08:06,490][23264] Avg episode reward: [(0, '4.528')]
162
+ [2023-03-21 12:08:06,498][23332] Saving new best policy, reward=4.512!
163
+ [2023-03-21 12:08:07,191][23362] Updated weights for policy 0, policy_version 100 (0.0007)
164
+ [2023-03-21 12:08:08,002][23264] Heartbeat connected on Batcher_0
165
+ [2023-03-21 12:08:08,003][23264] Heartbeat connected on LearnerWorker_p0
166
+ [2023-03-21 12:08:08,008][23264] Heartbeat connected on InferenceWorker_p0-w0
167
+ [2023-03-21 12:08:08,009][23264] Heartbeat connected on RolloutWorker_w0
168
+ [2023-03-21 12:08:08,011][23264] Heartbeat connected on RolloutWorker_w1
169
+ [2023-03-21 12:08:08,012][23264] Heartbeat connected on RolloutWorker_w2
170
+ [2023-03-21 12:08:08,013][23264] Heartbeat connected on RolloutWorker_w3
171
+ [2023-03-21 12:08:08,015][23264] Heartbeat connected on RolloutWorker_w4
172
+ [2023-03-21 12:08:08,017][23264] Heartbeat connected on RolloutWorker_w5
173
+ [2023-03-21 12:08:08,018][23264] Heartbeat connected on RolloutWorker_w6
174
+ [2023-03-21 12:08:08,022][23264] Heartbeat connected on RolloutWorker_w7
175
+ [2023-03-21 12:08:08,497][23362] Updated weights for policy 0, policy_version 110 (0.0007)
176
+ [2023-03-21 12:08:09,815][23362] Updated weights for policy 0, policy_version 120 (0.0006)
177
+ [2023-03-21 12:08:11,084][23362] Updated weights for policy 0, policy_version 130 (0.0006)
178
+ [2023-03-21 12:08:11,490][23264] Fps is (10 sec: 31539.2, 60 sec: 27238.5, 300 sec: 27238.5). Total num frames: 544768. Throughput: 0: 6191.7. Samples: 123834. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
179
+ [2023-03-21 12:08:11,490][23264] Avg episode reward: [(0, '4.622')]
180
+ [2023-03-21 12:08:11,490][23332] Saving new best policy, reward=4.622!
181
+ [2023-03-21 12:08:12,437][23362] Updated weights for policy 0, policy_version 140 (0.0007)
182
+ [2023-03-21 12:08:13,745][23362] Updated weights for policy 0, policy_version 150 (0.0006)
183
+ [2023-03-21 12:08:15,051][23362] Updated weights for policy 0, policy_version 160 (0.0007)
184
+ [2023-03-21 12:08:16,339][23362] Updated weights for policy 0, policy_version 170 (0.0006)
185
+ [2023-03-21 12:08:16,490][23264] Fps is (10 sec: 31539.0, 60 sec: 28016.6, 300 sec: 28016.6). Total num frames: 700416. Throughput: 0: 6834.1. Samples: 170852. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0)
186
+ [2023-03-21 12:08:16,490][23264] Avg episode reward: [(0, '4.658')]
187
+ [2023-03-21 12:08:16,492][23332] Saving new best policy, reward=4.658!
188
+ [2023-03-21 12:08:17,691][23362] Updated weights for policy 0, policy_version 180 (0.0007)
189
+ [2023-03-21 12:08:19,005][23362] Updated weights for policy 0, policy_version 190 (0.0006)
190
+ [2023-03-21 12:08:20,340][23362] Updated weights for policy 0, policy_version 200 (0.0007)
191
+ [2023-03-21 12:08:21,490][23264] Fps is (10 sec: 30719.9, 60 sec: 28398.9, 300 sec: 28398.9). Total num frames: 851968. Throughput: 0: 6470.0. Samples: 194100. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
192
+ [2023-03-21 12:08:21,490][23264] Avg episode reward: [(0, '4.958')]
193
+ [2023-03-21 12:08:21,497][23332] Saving new best policy, reward=4.958!
194
+ [2023-03-21 12:08:21,635][23362] Updated weights for policy 0, policy_version 210 (0.0006)
195
+ [2023-03-21 12:08:23,015][23362] Updated weights for policy 0, policy_version 220 (0.0007)
196
+ [2023-03-21 12:08:24,362][23362] Updated weights for policy 0, policy_version 230 (0.0007)
197
+ [2023-03-21 12:08:25,704][23362] Updated weights for policy 0, policy_version 240 (0.0007)
198
+ [2023-03-21 12:08:26,490][23264] Fps is (10 sec: 30310.4, 60 sec: 28672.0, 300 sec: 28672.0). Total num frames: 1003520. Throughput: 0: 6855.1. Samples: 239928. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
199
+ [2023-03-21 12:08:26,490][23264] Avg episode reward: [(0, '5.006')]
200
+ [2023-03-21 12:08:26,517][23332] Saving new best policy, reward=5.006!
201
+ [2023-03-21 12:08:27,127][23362] Updated weights for policy 0, policy_version 250 (0.0007)
202
+ [2023-03-21 12:08:28,514][23362] Updated weights for policy 0, policy_version 260 (0.0007)
203
+ [2023-03-21 12:08:29,862][23362] Updated weights for policy 0, policy_version 270 (0.0006)
204
+ [2023-03-21 12:08:31,188][23362] Updated weights for policy 0, policy_version 280 (0.0006)
205
+ [2023-03-21 12:08:31,489][23264] Fps is (10 sec: 30310.6, 60 sec: 28876.9, 300 sec: 28876.9). Total num frames: 1155072. Throughput: 0: 7117.0. Samples: 284678. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
206
+ [2023-03-21 12:08:31,490][23264] Avg episode reward: [(0, '5.682')]
207
+ [2023-03-21 12:08:31,490][23332] Saving new best policy, reward=5.682!
208
+ [2023-03-21 12:08:32,551][23362] Updated weights for policy 0, policy_version 290 (0.0007)
209
+ [2023-03-21 12:08:33,987][23362] Updated weights for policy 0, policy_version 300 (0.0007)
210
+ [2023-03-21 12:08:35,414][23362] Updated weights for policy 0, policy_version 310 (0.0007)
211
+ [2023-03-21 12:08:36,489][23264] Fps is (10 sec: 29901.0, 60 sec: 28945.1, 300 sec: 28945.1). Total num frames: 1302528. Throughput: 0: 6817.4. Samples: 306784. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
212
+ [2023-03-21 12:08:36,490][23264] Avg episode reward: [(0, '7.299')]
213
+ [2023-03-21 12:08:36,493][23332] Saving new best policy, reward=7.299!
214
+ [2023-03-21 12:08:36,776][23362] Updated weights for policy 0, policy_version 320 (0.0007)
215
+ [2023-03-21 12:08:38,126][23362] Updated weights for policy 0, policy_version 330 (0.0006)
216
+ [2023-03-21 12:08:39,441][23362] Updated weights for policy 0, policy_version 340 (0.0006)
217
+ [2023-03-21 12:08:40,735][23362] Updated weights for policy 0, policy_version 350 (0.0006)
218
+ [2023-03-21 12:08:41,490][23264] Fps is (10 sec: 29900.7, 60 sec: 29081.6, 300 sec: 29081.6). Total num frames: 1454080. Throughput: 0: 7699.8. Samples: 352068. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0)
219
+ [2023-03-21 12:08:41,490][23264] Avg episode reward: [(0, '8.136')]
220
+ [2023-03-21 12:08:41,490][23332] Saving new best policy, reward=8.136!
221
+ [2023-03-21 12:08:42,130][23362] Updated weights for policy 0, policy_version 360 (0.0007)
222
+ [2023-03-21 12:08:43,501][23362] Updated weights for policy 0, policy_version 370 (0.0007)
223
+ [2023-03-21 12:08:44,867][23362] Updated weights for policy 0, policy_version 380 (0.0007)
224
+ [2023-03-21 12:08:46,180][23362] Updated weights for policy 0, policy_version 390 (0.0007)
225
+ [2023-03-21 12:08:46,490][23264] Fps is (10 sec: 30310.3, 60 sec: 29193.3, 300 sec: 29193.3). Total num frames: 1605632. Throughput: 0: 7648.2. Samples: 397602. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
226
+ [2023-03-21 12:08:46,490][23264] Avg episode reward: [(0, '10.632')]
227
+ [2023-03-21 12:08:46,492][23332] Saving new best policy, reward=10.632!
228
+ [2023-03-21 12:08:47,586][23362] Updated weights for policy 0, policy_version 400 (0.0007)
229
+ [2023-03-21 12:08:48,950][23362] Updated weights for policy 0, policy_version 410 (0.0007)
230
+ [2023-03-21 12:08:50,286][23362] Updated weights for policy 0, policy_version 420 (0.0006)
231
+ [2023-03-21 12:08:51,490][23264] Fps is (10 sec: 29900.8, 60 sec: 29218.2, 300 sec: 29218.2). Total num frames: 1753088. Throughput: 0: 7617.7. Samples: 419918. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
232
+ [2023-03-21 12:08:51,490][23264] Avg episode reward: [(0, '13.298')]
233
+ [2023-03-21 12:08:51,497][23332] Saving new best policy, reward=13.298!
234
+ [2023-03-21 12:08:51,645][23362] Updated weights for policy 0, policy_version 430 (0.0007)
235
+ [2023-03-21 12:08:53,016][23362] Updated weights for policy 0, policy_version 440 (0.0007)
236
+ [2023-03-21 12:08:54,416][23362] Updated weights for policy 0, policy_version 450 (0.0007)
237
+ [2023-03-21 12:08:55,791][23362] Updated weights for policy 0, policy_version 460 (0.0007)
238
+ [2023-03-21 12:08:56,490][23264] Fps is (10 sec: 29900.7, 60 sec: 30583.4, 300 sec: 29302.2). Total num frames: 1904640. Throughput: 0: 7575.3. Samples: 464724. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
239
+ [2023-03-21 12:08:56,490][23264] Avg episode reward: [(0, '16.158')]
240
+ [2023-03-21 12:08:56,493][23332] Saving new best policy, reward=16.158!
241
+ [2023-03-21 12:08:57,177][23362] Updated weights for policy 0, policy_version 470 (0.0006)
242
+ [2023-03-21 12:08:58,562][23362] Updated weights for policy 0, policy_version 480 (0.0007)
243
+ [2023-03-21 12:08:59,926][23362] Updated weights for policy 0, policy_version 490 (0.0006)
244
+ [2023-03-21 12:09:01,309][23362] Updated weights for policy 0, policy_version 500 (0.0007)
245
+ [2023-03-21 12:09:01,490][23264] Fps is (10 sec: 29900.8, 60 sec: 30378.7, 300 sec: 29315.7). Total num frames: 2052096. Throughput: 0: 7526.1. Samples: 509524. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
246
+ [2023-03-21 12:09:01,490][23264] Avg episode reward: [(0, '15.498')]
247
+ [2023-03-21 12:09:02,633][23362] Updated weights for policy 0, policy_version 510 (0.0007)
248
+ [2023-03-21 12:09:03,969][23362] Updated weights for policy 0, policy_version 520 (0.0007)
249
+ [2023-03-21 12:09:05,326][23362] Updated weights for policy 0, policy_version 530 (0.0007)
250
+ [2023-03-21 12:09:06,489][23264] Fps is (10 sec: 29901.0, 60 sec: 30310.4, 300 sec: 29382.0). Total num frames: 2203648. Throughput: 0: 7516.2. Samples: 532328. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
251
+ [2023-03-21 12:09:06,490][23264] Avg episode reward: [(0, '16.303')]
252
+ [2023-03-21 12:09:06,492][23332] Saving new best policy, reward=16.303!
253
+ [2023-03-21 12:09:06,716][23362] Updated weights for policy 0, policy_version 540 (0.0007)
254
+ [2023-03-21 12:09:08,130][23362] Updated weights for policy 0, policy_version 550 (0.0007)
255
+ [2023-03-21 12:09:09,517][23362] Updated weights for policy 0, policy_version 560 (0.0006)
256
+ [2023-03-21 12:09:10,886][23362] Updated weights for policy 0, policy_version 570 (0.0007)
257
+ [2023-03-21 12:09:11,489][23264] Fps is (10 sec: 29900.9, 60 sec: 30105.6, 300 sec: 29388.8). Total num frames: 2351104. Throughput: 0: 7483.2. Samples: 576670. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
258
+ [2023-03-21 12:09:11,490][23264] Avg episode reward: [(0, '20.481')]
259
+ [2023-03-21 12:09:11,490][23332] Saving new best policy, reward=20.481!
260
+ [2023-03-21 12:09:12,217][23362] Updated weights for policy 0, policy_version 580 (0.0007)
261
+ [2023-03-21 12:09:13,531][23362] Updated weights for policy 0, policy_version 590 (0.0006)
262
+ [2023-03-21 12:09:14,917][23362] Updated weights for policy 0, policy_version 600 (0.0007)
263
+ [2023-03-21 12:09:16,298][23362] Updated weights for policy 0, policy_version 610 (0.0007)
264
+ [2023-03-21 12:09:16,490][23264] Fps is (10 sec: 29900.6, 60 sec: 30037.3, 300 sec: 29443.0). Total num frames: 2502656. Throughput: 0: 7496.2. Samples: 622008. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
265
+ [2023-03-21 12:09:16,490][23264] Avg episode reward: [(0, '21.688')]
266
+ [2023-03-21 12:09:16,492][23332] Saving new best policy, reward=21.688!
267
+ [2023-03-21 12:09:17,718][23362] Updated weights for policy 0, policy_version 620 (0.0007)
268
+ [2023-03-21 12:09:19,104][23362] Updated weights for policy 0, policy_version 630 (0.0007)
269
+ [2023-03-21 12:09:20,476][23362] Updated weights for policy 0, policy_version 640 (0.0007)
270
+ [2023-03-21 12:09:21,490][23264] Fps is (10 sec: 29900.6, 60 sec: 29969.1, 300 sec: 29445.7). Total num frames: 2650112. Throughput: 0: 7490.1. Samples: 643840. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
271
+ [2023-03-21 12:09:21,490][23264] Avg episode reward: [(0, '20.951')]
272
+ [2023-03-21 12:09:21,846][23362] Updated weights for policy 0, policy_version 650 (0.0007)
273
+ [2023-03-21 12:09:23,224][23362] Updated weights for policy 0, policy_version 660 (0.0007)
274
+ [2023-03-21 12:09:24,501][23362] Updated weights for policy 0, policy_version 670 (0.0006)
275
+ [2023-03-21 12:09:25,824][23362] Updated weights for policy 0, policy_version 680 (0.0006)
276
+ [2023-03-21 12:09:26,490][23264] Fps is (10 sec: 30310.5, 60 sec: 30037.4, 300 sec: 29534.3). Total num frames: 2805760. Throughput: 0: 7497.3. Samples: 689446. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
277
+ [2023-03-21 12:09:26,490][23264] Avg episode reward: [(0, '21.432')]
278
+ [2023-03-21 12:09:27,129][23362] Updated weights for policy 0, policy_version 690 (0.0006)
279
+ [2023-03-21 12:09:28,442][23362] Updated weights for policy 0, policy_version 700 (0.0007)
280
+ [2023-03-21 12:09:29,768][23362] Updated weights for policy 0, policy_version 710 (0.0006)
281
+ [2023-03-21 12:09:31,046][23362] Updated weights for policy 0, policy_version 720 (0.0006)
282
+ [2023-03-21 12:09:31,490][23264] Fps is (10 sec: 31129.6, 60 sec: 30105.6, 300 sec: 29614.1). Total num frames: 2961408. Throughput: 0: 7532.7. Samples: 736574. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
283
+ [2023-03-21 12:09:31,490][23264] Avg episode reward: [(0, '21.771')]
284
+ [2023-03-21 12:09:31,490][23332] Saving new best policy, reward=21.771!
285
+ [2023-03-21 12:09:32,388][23362] Updated weights for policy 0, policy_version 730 (0.0006)
286
+ [2023-03-21 12:09:33,740][23362] Updated weights for policy 0, policy_version 740 (0.0007)
287
+ [2023-03-21 12:09:35,062][23362] Updated weights for policy 0, policy_version 750 (0.0006)
288
+ [2023-03-21 12:09:36,347][23362] Updated weights for policy 0, policy_version 760 (0.0007)
289
+ [2023-03-21 12:09:36,490][23264] Fps is (10 sec: 31129.6, 60 sec: 30242.1, 300 sec: 29686.3). Total num frames: 3117056. Throughput: 0: 7546.8. Samples: 759524. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
290
+ [2023-03-21 12:09:36,490][23264] Avg episode reward: [(0, '26.696')]
291
+ [2023-03-21 12:09:36,493][23332] Saving new best policy, reward=26.696!
292
+ [2023-03-21 12:09:37,723][23362] Updated weights for policy 0, policy_version 770 (0.0007)
293
+ [2023-03-21 12:09:39,101][23362] Updated weights for policy 0, policy_version 780 (0.0007)
294
+ [2023-03-21 12:09:40,460][23362] Updated weights for policy 0, policy_version 790 (0.0006)
295
+ [2023-03-21 12:09:41,490][23264] Fps is (10 sec: 30310.4, 60 sec: 30173.9, 300 sec: 29677.4). Total num frames: 3264512. Throughput: 0: 7563.3. Samples: 805072. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
296
+ [2023-03-21 12:09:41,490][23264] Avg episode reward: [(0, '25.249')]
297
+ [2023-03-21 12:09:41,786][23362] Updated weights for policy 0, policy_version 800 (0.0006)
298
+ [2023-03-21 12:09:43,106][23362] Updated weights for policy 0, policy_version 810 (0.0006)
299
+ [2023-03-21 12:09:44,435][23362] Updated weights for policy 0, policy_version 820 (0.0006)
300
+ [2023-03-21 12:09:45,761][23362] Updated weights for policy 0, policy_version 830 (0.0006)
301
+ [2023-03-21 12:09:46,490][23264] Fps is (10 sec: 30310.2, 60 sec: 30242.1, 300 sec: 29740.5). Total num frames: 3420160. Throughput: 0: 7593.7. Samples: 851242. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0)
302
+ [2023-03-21 12:09:46,490][23264] Avg episode reward: [(0, '24.136')]
303
+ [2023-03-21 12:09:46,493][23332] Saving /home/antpc/Desktop/rl_course/train_dir/default_experiment/checkpoint_p0/checkpoint_000000835_3420160.pth...
304
+ [2023-03-21 12:09:47,117][23362] Updated weights for policy 0, policy_version 840 (0.0007)
305
+ [2023-03-21 12:09:48,478][23362] Updated weights for policy 0, policy_version 850 (0.0006)
306
+ [2023-03-21 12:09:49,785][23362] Updated weights for policy 0, policy_version 860 (0.0007)
307
+ [2023-03-21 12:09:51,117][23362] Updated weights for policy 0, policy_version 870 (0.0006)
308
+ [2023-03-21 12:09:51,490][23264] Fps is (10 sec: 30720.1, 60 sec: 30310.4, 300 sec: 29764.3). Total num frames: 3571712. Throughput: 0: 7596.4. Samples: 874168. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
309
+ [2023-03-21 12:09:51,490][23264] Avg episode reward: [(0, '23.190')]
310
+ [2023-03-21 12:09:52,475][23362] Updated weights for policy 0, policy_version 880 (0.0006)
311
+ [2023-03-21 12:09:54,011][23362] Updated weights for policy 0, policy_version 890 (0.0007)
312
+ [2023-03-21 12:09:55,605][23362] Updated weights for policy 0, policy_version 900 (0.0007)
313
+ [2023-03-21 12:09:56,490][23264] Fps is (10 sec: 29081.7, 60 sec: 30105.6, 300 sec: 29687.8). Total num frames: 3710976. Throughput: 0: 7569.7. Samples: 917306. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0)
314
+ [2023-03-21 12:09:56,490][23264] Avg episode reward: [(0, '23.791')]
315
+ [2023-03-21 12:09:57,046][23362] Updated weights for policy 0, policy_version 910 (0.0007)
316
+ [2023-03-21 12:09:58,423][23362] Updated weights for policy 0, policy_version 920 (0.0006)
317
+ [2023-03-21 12:09:59,784][23362] Updated weights for policy 0, policy_version 930 (0.0007)
318
+ [2023-03-21 12:10:01,108][23362] Updated weights for policy 0, policy_version 940 (0.0006)
319
+ [2023-03-21 12:10:01,490][23264] Fps is (10 sec: 28671.9, 60 sec: 30105.6, 300 sec: 29680.2). Total num frames: 3858432. Throughput: 0: 7539.2. Samples: 961274. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
320
+ [2023-03-21 12:10:01,490][23264] Avg episode reward: [(0, '24.487')]
321
+ [2023-03-21 12:10:02,447][23362] Updated weights for policy 0, policy_version 950 (0.0006)
322
+ [2023-03-21 12:10:03,820][23362] Updated weights for policy 0, policy_version 960 (0.0007)
323
+ [2023-03-21 12:10:05,195][23362] Updated weights for policy 0, policy_version 970 (0.0007)
324
+ [2023-03-21 12:10:06,490][23264] Fps is (10 sec: 29900.8, 60 sec: 30105.6, 300 sec: 29703.6). Total num frames: 4009984. Throughput: 0: 7559.0. Samples: 983994. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
325
+ [2023-03-21 12:10:06,490][23264] Avg episode reward: [(0, '24.296')]
326
+ [2023-03-21 12:10:06,530][23362] Updated weights for policy 0, policy_version 980 (0.0006)
327
+ [2023-03-21 12:10:07,839][23362] Updated weights for policy 0, policy_version 990 (0.0007)
328
+ [2023-03-21 12:10:09,124][23362] Updated weights for policy 0, policy_version 1000 (0.0007)
329
+ [2023-03-21 12:10:10,466][23362] Updated weights for policy 0, policy_version 1010 (0.0007)
330
+ [2023-03-21 12:10:11,490][23264] Fps is (10 sec: 30720.1, 60 sec: 30242.1, 300 sec: 29754.5). Total num frames: 4165632. Throughput: 0: 7571.6. Samples: 1030168. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
331
+ [2023-03-21 12:10:11,490][23264] Avg episode reward: [(0, '26.925')]
332
+ [2023-03-21 12:10:11,490][23332] Saving new best policy, reward=26.925!
333
+ [2023-03-21 12:10:11,820][23362] Updated weights for policy 0, policy_version 1020 (0.0007)
334
+ [2023-03-21 12:10:13,191][23362] Updated weights for policy 0, policy_version 1030 (0.0007)
335
+ [2023-03-21 12:10:14,546][23362] Updated weights for policy 0, policy_version 1040 (0.0007)
336
+ [2023-03-21 12:10:15,835][23362] Updated weights for policy 0, policy_version 1050 (0.0006)
337
+ [2023-03-21 12:10:16,489][23264] Fps is (10 sec: 31129.9, 60 sec: 30310.5, 300 sec: 29802.0). Total num frames: 4321280. Throughput: 0: 7544.5. Samples: 1076076. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
338
+ [2023-03-21 12:10:16,490][23264] Avg episode reward: [(0, '28.370')]
339
+ [2023-03-21 12:10:16,492][23332] Saving new best policy, reward=28.370!
340
+ [2023-03-21 12:10:17,194][23362] Updated weights for policy 0, policy_version 1060 (0.0007)
341
+ [2023-03-21 12:10:18,503][23362] Updated weights for policy 0, policy_version 1070 (0.0006)
342
+ [2023-03-21 12:10:19,781][23362] Updated weights for policy 0, policy_version 1080 (0.0007)
343
+ [2023-03-21 12:10:21,061][23362] Updated weights for policy 0, policy_version 1090 (0.0006)
344
+ [2023-03-21 12:10:21,490][23264] Fps is (10 sec: 31129.6, 60 sec: 30446.9, 300 sec: 29846.2). Total num frames: 4476928. Throughput: 0: 7552.0. Samples: 1099362. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
345
+ [2023-03-21 12:10:21,490][23264] Avg episode reward: [(0, '26.373')]
346
+ [2023-03-21 12:10:22,343][23362] Updated weights for policy 0, policy_version 1100 (0.0006)
347
+ [2023-03-21 12:10:23,645][23362] Updated weights for policy 0, policy_version 1110 (0.0007)
348
+ [2023-03-21 12:10:24,957][23362] Updated weights for policy 0, policy_version 1120 (0.0006)
349
+ [2023-03-21 12:10:26,233][23362] Updated weights for policy 0, policy_version 1130 (0.0006)
350
+ [2023-03-21 12:10:26,490][23264] Fps is (10 sec: 31538.9, 60 sec: 30515.2, 300 sec: 29914.0). Total num frames: 4636672. Throughput: 0: 7594.3. Samples: 1146816. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
351
+ [2023-03-21 12:10:26,490][23264] Avg episode reward: [(0, '24.247')]
352
+ [2023-03-21 12:10:27,517][23362] Updated weights for policy 0, policy_version 1140 (0.0006)
353
+ [2023-03-21 12:10:28,810][23362] Updated weights for policy 0, policy_version 1150 (0.0006)
354
+ [2023-03-21 12:10:30,079][23362] Updated weights for policy 0, policy_version 1160 (0.0006)
355
+ [2023-03-21 12:10:31,371][23362] Updated weights for policy 0, policy_version 1170 (0.0006)
356
+ [2023-03-21 12:10:31,489][23264] Fps is (10 sec: 31539.3, 60 sec: 30515.2, 300 sec: 29952.0). Total num frames: 4792320. Throughput: 0: 7627.9. Samples: 1194496. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
357
+ [2023-03-21 12:10:31,490][23264] Avg episode reward: [(0, '24.420')]
358
+ [2023-03-21 12:10:32,657][23362] Updated weights for policy 0, policy_version 1180 (0.0006)
359
+ [2023-03-21 12:10:33,940][23362] Updated weights for policy 0, policy_version 1190 (0.0006)
360
+ [2023-03-21 12:10:35,262][23362] Updated weights for policy 0, policy_version 1200 (0.0007)
361
+ [2023-03-21 12:10:36,490][23264] Fps is (10 sec: 31539.1, 60 sec: 30583.5, 300 sec: 30012.5). Total num frames: 4952064. Throughput: 0: 7649.0. Samples: 1218372. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
362
+ [2023-03-21 12:10:36,490][23264] Avg episode reward: [(0, '26.496')]
363
+ [2023-03-21 12:10:36,557][23362] Updated weights for policy 0, policy_version 1210 (0.0007)
364
+ [2023-03-21 12:10:37,902][23362] Updated weights for policy 0, policy_version 1220 (0.0006)
365
+ [2023-03-21 12:10:39,211][23362] Updated weights for policy 0, policy_version 1230 (0.0007)
366
+ [2023-03-21 12:10:40,496][23362] Updated weights for policy 0, policy_version 1240 (0.0006)
367
+ [2023-03-21 12:10:41,490][23264] Fps is (10 sec: 31539.1, 60 sec: 30720.0, 300 sec: 30045.4). Total num frames: 5107712. Throughput: 0: 7731.7. Samples: 1265232. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
368
+ [2023-03-21 12:10:41,490][23264] Avg episode reward: [(0, '25.147')]
369
+ [2023-03-21 12:10:41,782][23362] Updated weights for policy 0, policy_version 1250 (0.0006)
370
+ [2023-03-21 12:10:43,055][23362] Updated weights for policy 0, policy_version 1260 (0.0006)
371
+ [2023-03-21 12:10:44,340][23362] Updated weights for policy 0, policy_version 1270 (0.0006)
372
+ [2023-03-21 12:10:45,602][23362] Updated weights for policy 0, policy_version 1280 (0.0006)
373
+ [2023-03-21 12:10:46,490][23264] Fps is (10 sec: 31539.3, 60 sec: 30788.3, 300 sec: 30099.8). Total num frames: 5267456. Throughput: 0: 7824.9. Samples: 1313396. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
374
+ [2023-03-21 12:10:46,490][23264] Avg episode reward: [(0, '28.868')]
375
+ [2023-03-21 12:10:46,501][23332] Saving new best policy, reward=28.868!
376
+ [2023-03-21 12:10:46,944][23362] Updated weights for policy 0, policy_version 1290 (0.0007)
377
+ [2023-03-21 12:10:48,278][23362] Updated weights for policy 0, policy_version 1300 (0.0007)
378
+ [2023-03-21 12:10:49,594][23362] Updated weights for policy 0, policy_version 1310 (0.0007)
379
+ [2023-03-21 12:10:50,928][23362] Updated weights for policy 0, policy_version 1320 (0.0007)
380
+ [2023-03-21 12:10:51,490][23264] Fps is (10 sec: 31539.1, 60 sec: 30856.5, 300 sec: 30128.4). Total num frames: 5423104. Throughput: 0: 7828.4. Samples: 1336274. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
381
+ [2023-03-21 12:10:51,490][23264] Avg episode reward: [(0, '25.935')]
382
+ [2023-03-21 12:10:52,219][23362] Updated weights for policy 0, policy_version 1330 (0.0006)
383
+ [2023-03-21 12:10:53,559][23362] Updated weights for policy 0, policy_version 1340 (0.0006)
384
+ [2023-03-21 12:10:54,841][23362] Updated weights for policy 0, policy_version 1350 (0.0006)
385
+ [2023-03-21 12:10:56,151][23362] Updated weights for policy 0, policy_version 1360 (0.0007)
386
+ [2023-03-21 12:10:56,490][23264] Fps is (10 sec: 31129.5, 60 sec: 31129.6, 300 sec: 30155.4). Total num frames: 5578752. Throughput: 0: 7843.5. Samples: 1383124. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
387
+ [2023-03-21 12:10:56,490][23264] Avg episode reward: [(0, '26.315')]
388
+ [2023-03-21 12:10:57,481][23362] Updated weights for policy 0, policy_version 1370 (0.0006)
389
+ [2023-03-21 12:10:58,821][23362] Updated weights for policy 0, policy_version 1380 (0.0006)
390
+ [2023-03-21 12:11:00,134][23362] Updated weights for policy 0, policy_version 1390 (0.0006)
391
+ [2023-03-21 12:11:01,399][23362] Updated weights for policy 0, policy_version 1400 (0.0006)
392
+ [2023-03-21 12:11:01,490][23264] Fps is (10 sec: 31129.6, 60 sec: 31266.2, 300 sec: 30181.1). Total num frames: 5734400. Throughput: 0: 7861.1. Samples: 1429826. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
393
+ [2023-03-21 12:11:01,490][23264] Avg episode reward: [(0, '27.340')]
394
+ [2023-03-21 12:11:02,685][23362] Updated weights for policy 0, policy_version 1410 (0.0007)
395
+ [2023-03-21 12:11:03,988][23362] Updated weights for policy 0, policy_version 1420 (0.0006)
396
+ [2023-03-21 12:11:05,293][23362] Updated weights for policy 0, policy_version 1430 (0.0007)
397
+ [2023-03-21 12:11:06,490][23264] Fps is (10 sec: 31129.7, 60 sec: 31334.4, 300 sec: 30205.4). Total num frames: 5890048. Throughput: 0: 7873.6. Samples: 1453674. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
398
+ [2023-03-21 12:11:06,490][23264] Avg episode reward: [(0, '26.217')]
399
+ [2023-03-21 12:11:06,648][23362] Updated weights for policy 0, policy_version 1440 (0.0007)
400
+ [2023-03-21 12:11:07,985][23362] Updated weights for policy 0, policy_version 1450 (0.0007)
401
+ [2023-03-21 12:11:09,272][23362] Updated weights for policy 0, policy_version 1460 (0.0007)
402
+ [2023-03-21 12:11:10,585][23362] Updated weights for policy 0, policy_version 1470 (0.0006)
403
+ [2023-03-21 12:11:11,489][23264] Fps is (10 sec: 31129.7, 60 sec: 31334.4, 300 sec: 30228.5). Total num frames: 6045696. Throughput: 0: 7852.1. Samples: 1500162. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
404
+ [2023-03-21 12:11:11,490][23264] Avg episode reward: [(0, '24.863')]
405
+ [2023-03-21 12:11:11,888][23362] Updated weights for policy 0, policy_version 1480 (0.0006)
406
+ [2023-03-21 12:11:13,181][23362] Updated weights for policy 0, policy_version 1490 (0.0006)
407
+ [2023-03-21 12:11:14,525][23362] Updated weights for policy 0, policy_version 1500 (0.0006)
408
+ [2023-03-21 12:11:15,838][23362] Updated weights for policy 0, policy_version 1510 (0.0006)
409
+ [2023-03-21 12:11:16,490][23264] Fps is (10 sec: 31539.2, 60 sec: 31402.6, 300 sec: 30270.4). Total num frames: 6205440. Throughput: 0: 7834.9. Samples: 1547066. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
410
+ [2023-03-21 12:11:16,490][23264] Avg episode reward: [(0, '28.077')]
411
+ [2023-03-21 12:11:17,146][23362] Updated weights for policy 0, policy_version 1520 (0.0006)
412
+ [2023-03-21 12:11:18,454][23362] Updated weights for policy 0, policy_version 1530 (0.0006)
413
+ [2023-03-21 12:11:19,772][23362] Updated weights for policy 0, policy_version 1540 (0.0006)
414
+ [2023-03-21 12:11:21,098][23362] Updated weights for policy 0, policy_version 1550 (0.0006)
415
+ [2023-03-21 12:11:21,490][23264] Fps is (10 sec: 31539.2, 60 sec: 31402.7, 300 sec: 30290.9). Total num frames: 6361088. Throughput: 0: 7823.7. Samples: 1570438. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
416
+ [2023-03-21 12:11:21,490][23264] Avg episode reward: [(0, '27.708')]
417
+ [2023-03-21 12:11:22,396][23362] Updated weights for policy 0, policy_version 1560 (0.0006)
418
+ [2023-03-21 12:11:23,712][23362] Updated weights for policy 0, policy_version 1570 (0.0006)
419
+ [2023-03-21 12:11:25,012][23362] Updated weights for policy 0, policy_version 1580 (0.0006)
420
+ [2023-03-21 12:11:26,298][23362] Updated weights for policy 0, policy_version 1590 (0.0006)
421
+ [2023-03-21 12:11:26,490][23264] Fps is (10 sec: 31129.7, 60 sec: 31334.4, 300 sec: 30310.4). Total num frames: 6516736. Throughput: 0: 7831.0. Samples: 1617628. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0)
422
+ [2023-03-21 12:11:26,490][23264] Avg episode reward: [(0, '26.281')]
423
+ [2023-03-21 12:11:27,615][23362] Updated weights for policy 0, policy_version 1600 (0.0006)
424
+ [2023-03-21 12:11:28,923][23362] Updated weights for policy 0, policy_version 1610 (0.0006)
425
+ [2023-03-21 12:11:30,220][23362] Updated weights for policy 0, policy_version 1620 (0.0006)
426
+ [2023-03-21 12:11:31,489][23264] Fps is (10 sec: 31539.5, 60 sec: 31402.7, 300 sec: 30347.7). Total num frames: 6676480. Throughput: 0: 7810.1. Samples: 1664852. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
427
+ [2023-03-21 12:11:31,490][23264] Avg episode reward: [(0, '25.423')]
428
+ [2023-03-21 12:11:31,490][23362] Updated weights for policy 0, policy_version 1630 (0.0006)
429
+ [2023-03-21 12:11:32,806][23362] Updated weights for policy 0, policy_version 1640 (0.0006)
430
+ [2023-03-21 12:11:34,123][23362] Updated weights for policy 0, policy_version 1650 (0.0007)
431
+ [2023-03-21 12:11:35,453][23362] Updated weights for policy 0, policy_version 1660 (0.0007)
432
+ [2023-03-21 12:11:36,490][23264] Fps is (10 sec: 31539.2, 60 sec: 31334.4, 300 sec: 30365.0). Total num frames: 6832128. Throughput: 0: 7821.6. Samples: 1688248. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
433
+ [2023-03-21 12:11:36,490][23264] Avg episode reward: [(0, '25.938')]
434
+ [2023-03-21 12:11:36,742][23362] Updated weights for policy 0, policy_version 1670 (0.0006)
435
+ [2023-03-21 12:11:38,046][23362] Updated weights for policy 0, policy_version 1680 (0.0006)
436
+ [2023-03-21 12:11:39,343][23362] Updated weights for policy 0, policy_version 1690 (0.0006)
437
+ [2023-03-21 12:11:40,646][23362] Updated weights for policy 0, policy_version 1700 (0.0007)
438
+ [2023-03-21 12:11:41,489][23264] Fps is (10 sec: 31129.4, 60 sec: 31334.4, 300 sec: 30381.6). Total num frames: 6987776. Throughput: 0: 7827.4. Samples: 1735356. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
439
+ [2023-03-21 12:11:41,490][23264] Avg episode reward: [(0, '26.805')]
440
+ [2023-03-21 12:11:41,941][23362] Updated weights for policy 0, policy_version 1710 (0.0007)
441
+ [2023-03-21 12:11:43,229][23362] Updated weights for policy 0, policy_version 1720 (0.0006)
442
+ [2023-03-21 12:11:44,518][23362] Updated weights for policy 0, policy_version 1730 (0.0006)
443
+ [2023-03-21 12:11:45,793][23362] Updated weights for policy 0, policy_version 1740 (0.0006)
444
+ [2023-03-21 12:11:46,489][23264] Fps is (10 sec: 31539.3, 60 sec: 31334.4, 300 sec: 30415.0). Total num frames: 7147520. Throughput: 0: 7845.4. Samples: 1782870. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0)
445
+ [2023-03-21 12:11:46,490][23264] Avg episode reward: [(0, '24.793')]
446
+ [2023-03-21 12:11:46,493][23332] Saving /home/antpc/Desktop/rl_course/train_dir/default_experiment/checkpoint_p0/checkpoint_000001745_7147520.pth...
447
+ [2023-03-21 12:11:47,126][23362] Updated weights for policy 0, policy_version 1750 (0.0006)
448
+ [2023-03-21 12:11:48,461][23362] Updated weights for policy 0, policy_version 1760 (0.0007)
449
+ [2023-03-21 12:11:49,773][23362] Updated weights for policy 0, policy_version 1770 (0.0007)
450
+ [2023-03-21 12:11:51,095][23362] Updated weights for policy 0, policy_version 1780 (0.0007)
451
+ [2023-03-21 12:11:51,490][23264] Fps is (10 sec: 31539.1, 60 sec: 31334.4, 300 sec: 30429.9). Total num frames: 7303168. Throughput: 0: 7826.7. Samples: 1805876. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
452
+ [2023-03-21 12:11:51,490][23264] Avg episode reward: [(0, '25.244')]
453
+ [2023-03-21 12:11:52,389][23362] Updated weights for policy 0, policy_version 1790 (0.0007)
454
+ [2023-03-21 12:11:53,710][23362] Updated weights for policy 0, policy_version 1800 (0.0006)
455
+ [2023-03-21 12:11:55,003][23362] Updated weights for policy 0, policy_version 1810 (0.0007)
456
+ [2023-03-21 12:11:56,304][23362] Updated weights for policy 0, policy_version 1820 (0.0007)
457
+ [2023-03-21 12:11:56,489][23264] Fps is (10 sec: 31129.6, 60 sec: 31334.4, 300 sec: 30444.2). Total num frames: 7458816. Throughput: 0: 7835.7. Samples: 1852768. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
458
+ [2023-03-21 12:11:56,490][23264] Avg episode reward: [(0, '23.761')]
459
+ [2023-03-21 12:11:57,571][23362] Updated weights for policy 0, policy_version 1830 (0.0006)
460
+ [2023-03-21 12:11:58,883][23362] Updated weights for policy 0, policy_version 1840 (0.0007)
461
+ [2023-03-21 12:12:00,179][23362] Updated weights for policy 0, policy_version 1850 (0.0007)
462
+ [2023-03-21 12:12:01,462][23362] Updated weights for policy 0, policy_version 1860 (0.0006)
463
+ [2023-03-21 12:12:01,490][23264] Fps is (10 sec: 31539.2, 60 sec: 31402.7, 300 sec: 30474.2). Total num frames: 7618560. Throughput: 0: 7847.4. Samples: 1900198. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
464
+ [2023-03-21 12:12:01,490][23264] Avg episode reward: [(0, '26.039')]
465
+ [2023-03-21 12:12:02,775][23362] Updated weights for policy 0, policy_version 1870 (0.0007)
466
+ [2023-03-21 12:12:04,067][23362] Updated weights for policy 0, policy_version 1880 (0.0006)
467
+ [2023-03-21 12:12:05,354][23362] Updated weights for policy 0, policy_version 1890 (0.0006)
468
+ [2023-03-21 12:12:06,490][23264] Fps is (10 sec: 31539.1, 60 sec: 31402.7, 300 sec: 30487.1). Total num frames: 7774208. Throughput: 0: 7855.2. Samples: 1923924. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
469
+ [2023-03-21 12:12:06,490][23264] Avg episode reward: [(0, '26.110')]
470
+ [2023-03-21 12:12:06,652][23362] Updated weights for policy 0, policy_version 1900 (0.0006)
471
+ [2023-03-21 12:12:07,929][23362] Updated weights for policy 0, policy_version 1910 (0.0006)
472
+ [2023-03-21 12:12:09,218][23362] Updated weights for policy 0, policy_version 1920 (0.0007)
473
+ [2023-03-21 12:12:10,504][23362] Updated weights for policy 0, policy_version 1930 (0.0006)
474
+ [2023-03-21 12:12:11,489][23264] Fps is (10 sec: 31539.3, 60 sec: 31470.9, 300 sec: 30515.2). Total num frames: 7933952. Throughput: 0: 7869.9. Samples: 1971772. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
475
+ [2023-03-21 12:12:11,490][23264] Avg episode reward: [(0, '24.129')]
476
+ [2023-03-21 12:12:11,801][23362] Updated weights for policy 0, policy_version 1940 (0.0007)
477
+ [2023-03-21 12:12:13,064][23362] Updated weights for policy 0, policy_version 1950 (0.0006)
478
+ [2023-03-21 12:12:13,720][23264] Component Batcher_0 stopped!
479
+ [2023-03-21 12:12:13,720][23332] Stopping Batcher_0...
480
+ [2023-03-21 12:12:13,720][23332] Loop batcher_evt_loop terminating...
481
+ [2023-03-21 12:12:13,720][23332] Saving /home/antpc/Desktop/rl_course/train_dir/default_experiment/checkpoint_p0/checkpoint_000001955_8007680.pth...
482
+ [2023-03-21 12:12:13,726][23364] Stopping RolloutWorker_w2...
483
+ [2023-03-21 12:12:13,726][23264] Component RolloutWorker_w2 stopped!
484
+ [2023-03-21 12:12:13,726][23384] Stopping RolloutWorker_w7...
485
+ [2023-03-21 12:12:13,726][23361] Stopping RolloutWorker_w0...
486
+ [2023-03-21 12:12:13,726][23364] Loop rollout_proc2_evt_loop terminating...
487
+ [2023-03-21 12:12:13,726][23384] Loop rollout_proc7_evt_loop terminating...
488
+ [2023-03-21 12:12:13,726][23361] Loop rollout_proc0_evt_loop terminating...
489
+ [2023-03-21 12:12:13,726][23264] Component RolloutWorker_w7 stopped!
490
+ [2023-03-21 12:12:13,726][23366] Stopping RolloutWorker_w4...
491
+ [2023-03-21 12:12:13,726][23264] Component RolloutWorker_w0 stopped!
492
+ [2023-03-21 12:12:13,726][23363] Stopping RolloutWorker_w1...
493
+ [2023-03-21 12:12:13,726][23367] Stopping RolloutWorker_w5...
494
+ [2023-03-21 12:12:13,727][23264] Component RolloutWorker_w4 stopped!
495
+ [2023-03-21 12:12:13,727][23366] Loop rollout_proc4_evt_loop terminating...
496
+ [2023-03-21 12:12:13,727][23264] Component RolloutWorker_w1 stopped!
497
+ [2023-03-21 12:12:13,727][23367] Loop rollout_proc5_evt_loop terminating...
498
+ [2023-03-21 12:12:13,727][23363] Loop rollout_proc1_evt_loop terminating...
499
+ [2023-03-21 12:12:13,727][23264] Component RolloutWorker_w5 stopped!
500
+ [2023-03-21 12:12:13,733][23365] Stopping RolloutWorker_w3...
501
+ [2023-03-21 12:12:13,733][23264] Component RolloutWorker_w3 stopped!
502
+ [2023-03-21 12:12:13,733][23365] Loop rollout_proc3_evt_loop terminating...
503
+ [2023-03-21 12:12:13,734][23362] Weights refcount: 2 0
504
+ [2023-03-21 12:12:13,735][23362] Stopping InferenceWorker_p0-w0...
505
+ [2023-03-21 12:12:13,735][23264] Component InferenceWorker_p0-w0 stopped!
506
+ [2023-03-21 12:12:13,735][23362] Loop inference_proc0-0_evt_loop terminating...
507
+ [2023-03-21 12:12:13,737][23383] Stopping RolloutWorker_w6...
508
+ [2023-03-21 12:12:13,737][23264] Component RolloutWorker_w6 stopped!
509
+ [2023-03-21 12:12:13,738][23383] Loop rollout_proc6_evt_loop terminating...
510
+ [2023-03-21 12:12:13,764][23332] Removing /home/antpc/Desktop/rl_course/train_dir/default_experiment/checkpoint_p0/checkpoint_000000835_3420160.pth
511
+ [2023-03-21 12:12:13,769][23332] Saving /home/antpc/Desktop/rl_course/train_dir/default_experiment/checkpoint_p0/checkpoint_000001955_8007680.pth...
512
+ [2023-03-21 12:12:13,835][23332] Stopping LearnerWorker_p0...
513
+ [2023-03-21 12:12:13,835][23264] Component LearnerWorker_p0 stopped!
514
+ [2023-03-21 12:12:13,836][23332] Loop learner_proc0_evt_loop terminating...
515
+ [2023-03-21 12:12:13,836][23264] Waiting for process learner_proc0 to stop...
516
+ [2023-03-21 12:12:14,433][23264] Waiting for process inference_proc0-0 to join...
517
+ [2023-03-21 12:12:14,433][23264] Waiting for process rollout_proc0 to join...
518
+ [2023-03-21 12:12:14,434][23264] Waiting for process rollout_proc1 to join...
519
+ [2023-03-21 12:12:14,434][23264] Waiting for process rollout_proc2 to join...
520
+ [2023-03-21 12:12:14,434][23264] Waiting for process rollout_proc3 to join...
521
+ [2023-03-21 12:12:14,434][23264] Waiting for process rollout_proc4 to join...
522
+ [2023-03-21 12:12:14,434][23264] Waiting for process rollout_proc5 to join...
523
+ [2023-03-21 12:12:14,434][23264] Waiting for process rollout_proc6 to join...
524
+ [2023-03-21 12:12:14,434][23264] Waiting for process rollout_proc7 to join...
525
+ [2023-03-21 12:12:14,434][23264] Batcher 0 profile tree view:
526
+ batching: 13.5546, releasing_batches: 0.0305
527
+ [2023-03-21 12:12:14,435][23264] InferenceWorker_p0-w0 profile tree view:
528
+ wait_policy: 0.0000
529
+ wait_policy_total: 3.8298
530
+ update_model: 3.9375
531
+ weight_update: 0.0007
532
+ one_step: 0.0019
533
+ handle_policy_step: 240.2654
534
+ deserialize: 10.3571, stack: 1.3895, obs_to_device_normalize: 62.6308, forward: 103.8704, send_messages: 14.3477
535
+ prepare_outputs: 38.2395
536
+ to_cpu: 26.8497
537
+ [2023-03-21 12:12:14,435][23264] Learner 0 profile tree view:
538
+ misc: 0.0074, prepare_batch: 12.9347
539
+ train: 38.8463
540
+ epoch_init: 0.0068, minibatch_init: 0.0089, losses_postprocess: 0.2985, kl_divergence: 0.2877, after_optimizer: 10.1432
541
+ calculate_losses: 17.7054
542
+ losses_init: 0.0038, forward_head: 1.2325, bptt_initial: 12.7581, tail: 0.6975, advantages_returns: 0.1941, losses: 1.2239
543
+ bptt: 1.3730
544
+ bptt_forward_core: 1.3189
545
+ update: 9.9149
546
+ clip: 1.2032
547
+ [2023-03-21 12:12:14,435][23264] RolloutWorker_w0 profile tree view:
548
+ wait_for_trajectories: 0.1727, enqueue_policy_requests: 10.1575, env_step: 130.0109, overhead: 11.9517, complete_rollouts: 0.3140
549
+ save_policy_outputs: 10.6131
550
+ split_output_tensors: 5.2450
551
+ [2023-03-21 12:12:14,435][23264] RolloutWorker_w7 profile tree view:
552
+ wait_for_trajectories: 0.1715, enqueue_policy_requests: 10.4371, env_step: 132.1329, overhead: 12.2068, complete_rollouts: 0.3086
553
+ save_policy_outputs: 10.8866
554
+ split_output_tensors: 5.3324
555
+ [2023-03-21 12:12:14,435][23264] Loop Runner_EvtLoop terminating...
556
+ [2023-03-21 12:12:14,435][23264] Runner profile tree view:
557
+ main_loop: 266.4156
558
+ [2023-03-21 12:12:14,435][23264] Collected {0: 8007680}, FPS: 30057.1
559
+ [2023-03-21 12:12:14,440][23264] Loading existing experiment configuration from /home/antpc/Desktop/rl_course/train_dir/default_experiment/config.json
560
+ [2023-03-21 12:12:14,440][23264] Overriding arg 'num_workers' with value 1 passed from command line
561
+ [2023-03-21 12:12:14,440][23264] Adding new argument 'no_render'=True that is not in the saved config file!
562
+ [2023-03-21 12:12:14,440][23264] Adding new argument 'save_video'=True that is not in the saved config file!
563
+ [2023-03-21 12:12:14,440][23264] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file!
564
+ [2023-03-21 12:12:14,440][23264] Adding new argument 'video_name'=None that is not in the saved config file!
565
+ [2023-03-21 12:12:14,440][23264] Adding new argument 'max_num_frames'=1000000000.0 that is not in the saved config file!
566
+ [2023-03-21 12:12:14,440][23264] Adding new argument 'max_num_episodes'=10 that is not in the saved config file!
567
+ [2023-03-21 12:12:14,440][23264] Adding new argument 'push_to_hub'=False that is not in the saved config file!
568
+ [2023-03-21 12:12:14,440][23264] Adding new argument 'hf_repository'=None that is not in the saved config file!
569
+ [2023-03-21 12:12:14,440][23264] Adding new argument 'policy_index'=0 that is not in the saved config file!
570
+ [2023-03-21 12:12:14,440][23264] Adding new argument 'eval_deterministic'=False that is not in the saved config file!
571
+ [2023-03-21 12:12:14,440][23264] Adding new argument 'train_script'=None that is not in the saved config file!
572
+ [2023-03-21 12:12:14,440][23264] Adding new argument 'enjoy_script'=None that is not in the saved config file!
573
+ [2023-03-21 12:12:14,441][23264] Using frameskip 1 and render_action_repeat=4 for evaluation
574
+ [2023-03-21 12:12:14,445][23264] Doom resolution: 160x120, resize resolution: (128, 72)
575
+ [2023-03-21 12:12:14,446][23264] RunningMeanStd input shape: (3, 72, 128)
576
+ [2023-03-21 12:12:14,446][23264] RunningMeanStd input shape: (1,)
577
+ [2023-03-21 12:12:14,453][23264] ConvEncoder: input_channels=3
578
+ [2023-03-21 12:12:14,539][23264] Conv encoder output size: 512
579
+ [2023-03-21 12:12:14,539][23264] Policy head output size: 512
580
+ [2023-03-21 12:12:15,798][23264] Loading state from checkpoint /home/antpc/Desktop/rl_course/train_dir/default_experiment/checkpoint_p0/checkpoint_000001955_8007680.pth...
581
+ [2023-03-21 12:12:16,386][23264] Num frames 100...
582
+ [2023-03-21 12:12:16,443][23264] Num frames 200...
583
+ [2023-03-21 12:12:16,502][23264] Num frames 300...
584
+ [2023-03-21 12:12:16,560][23264] Num frames 400...
585
+ [2023-03-21 12:12:16,619][23264] Num frames 500...
586
+ [2023-03-21 12:12:16,677][23264] Num frames 600...
587
+ [2023-03-21 12:12:16,754][23264] Avg episode rewards: #0: 12.370, true rewards: #0: 6.370
588
+ [2023-03-21 12:12:16,754][23264] Avg episode reward: 12.370, avg true_objective: 6.370
589
+ [2023-03-21 12:12:16,793][23264] Num frames 700...
590
+ [2023-03-21 12:12:16,849][23264] Num frames 800...
591
+ [2023-03-21 12:12:16,905][23264] Num frames 900...
592
+ [2023-03-21 12:12:17,008][23264] Avg episode rewards: #0: 8.445, true rewards: #0: 4.945
593
+ [2023-03-21 12:12:17,009][23264] Avg episode reward: 8.445, avg true_objective: 4.945
594
+ [2023-03-21 12:12:17,018][23264] Num frames 1000...
595
+ [2023-03-21 12:12:17,076][23264] Num frames 1100...
596
+ [2023-03-21 12:12:17,133][23264] Num frames 1200...
597
+ [2023-03-21 12:12:17,189][23264] Num frames 1300...
598
+ [2023-03-21 12:12:17,251][23264] Num frames 1400...
599
+ [2023-03-21 12:12:17,313][23264] Num frames 1500...
600
+ [2023-03-21 12:12:17,377][23264] Num frames 1600...
601
+ [2023-03-21 12:12:17,436][23264] Num frames 1700...
602
+ [2023-03-21 12:12:17,496][23264] Num frames 1800...
603
+ [2023-03-21 12:12:17,553][23264] Num frames 1900...
604
+ [2023-03-21 12:12:17,609][23264] Num frames 2000...
605
+ [2023-03-21 12:12:17,666][23264] Num frames 2100...
606
+ [2023-03-21 12:12:17,723][23264] Num frames 2200...
607
+ [2023-03-21 12:12:17,780][23264] Num frames 2300...
608
+ [2023-03-21 12:12:17,838][23264] Num frames 2400...
609
+ [2023-03-21 12:12:17,895][23264] Num frames 2500...
610
+ [2023-03-21 12:12:17,963][23264] Avg episode rewards: #0: 18.753, true rewards: #0: 8.420
611
+ [2023-03-21 12:12:17,963][23264] Avg episode reward: 18.753, avg true_objective: 8.420
612
+ [2023-03-21 12:12:18,007][23264] Num frames 2600...
613
+ [2023-03-21 12:12:18,066][23264] Num frames 2700...
614
+ [2023-03-21 12:12:18,124][23264] Num frames 2800...
615
+ [2023-03-21 12:12:18,181][23264] Num frames 2900...
616
+ [2023-03-21 12:12:18,238][23264] Num frames 3000...
617
+ [2023-03-21 12:12:18,297][23264] Num frames 3100...
618
+ [2023-03-21 12:12:18,354][23264] Num frames 3200...
619
+ [2023-03-21 12:12:18,412][23264] Num frames 3300...
620
+ [2023-03-21 12:12:18,469][23264] Num frames 3400...
621
+ [2023-03-21 12:12:18,536][23264] Avg episode rewards: #0: 18.805, true rewards: #0: 8.555
622
+ [2023-03-21 12:12:18,536][23264] Avg episode reward: 18.805, avg true_objective: 8.555
623
+ [2023-03-21 12:12:18,590][23264] Num frames 3500...
624
+ [2023-03-21 12:12:18,647][23264] Num frames 3600...
625
+ [2023-03-21 12:12:18,704][23264] Num frames 3700...
626
+ [2023-03-21 12:12:18,763][23264] Num frames 3800...
627
+ [2023-03-21 12:12:18,822][23264] Num frames 3900...
628
+ [2023-03-21 12:12:18,880][23264] Num frames 4000...
629
+ [2023-03-21 12:12:18,938][23264] Num frames 4100...
630
+ [2023-03-21 12:12:18,996][23264] Num frames 4200...
631
+ [2023-03-21 12:12:19,055][23264] Num frames 4300...
632
+ [2023-03-21 12:12:19,114][23264] Num frames 4400...
633
+ [2023-03-21 12:12:19,172][23264] Num frames 4500...
634
+ [2023-03-21 12:12:19,230][23264] Num frames 4600...
635
+ [2023-03-21 12:12:19,288][23264] Num frames 4700...
636
+ [2023-03-21 12:12:19,347][23264] Num frames 4800...
637
+ [2023-03-21 12:12:19,407][23264] Num frames 4900...
638
+ [2023-03-21 12:12:19,466][23264] Num frames 5000...
639
+ [2023-03-21 12:12:19,524][23264] Num frames 5100...
640
+ [2023-03-21 12:12:19,583][23264] Num frames 5200...
641
+ [2023-03-21 12:12:19,642][23264] Num frames 5300...
642
+ [2023-03-21 12:12:19,701][23264] Num frames 5400...
643
+ [2023-03-21 12:12:19,760][23264] Num frames 5500...
644
+ [2023-03-21 12:12:19,826][23264] Avg episode rewards: #0: 26.644, true rewards: #0: 11.044
645
+ [2023-03-21 12:12:19,826][23264] Avg episode reward: 26.644, avg true_objective: 11.044
646
+ [2023-03-21 12:12:19,873][23264] Num frames 5600...
647
+ [2023-03-21 12:12:19,933][23264] Num frames 5700...
648
+ [2023-03-21 12:12:19,991][23264] Num frames 5800...
649
+ [2023-03-21 12:12:20,049][23264] Num frames 5900...
650
+ [2023-03-21 12:12:20,106][23264] Num frames 6000...
651
+ [2023-03-21 12:12:20,163][23264] Num frames 6100...
652
+ [2023-03-21 12:12:20,221][23264] Num frames 6200...
653
+ [2023-03-21 12:12:20,279][23264] Num frames 6300...
654
+ [2023-03-21 12:12:20,337][23264] Num frames 6400...
655
+ [2023-03-21 12:12:20,394][23264] Num frames 6500...
656
+ [2023-03-21 12:12:20,451][23264] Num frames 6600...
657
+ [2023-03-21 12:12:20,548][23264] Avg episode rewards: #0: 26.623, true rewards: #0: 11.123
658
+ [2023-03-21 12:12:20,548][23264] Avg episode reward: 26.623, avg true_objective: 11.123
659
+ [2023-03-21 12:12:20,570][23264] Num frames 6700...
660
+ [2023-03-21 12:12:20,627][23264] Num frames 6800...
661
+ [2023-03-21 12:12:20,685][23264] Num frames 6900...
662
+ [2023-03-21 12:12:20,742][23264] Num frames 7000...
663
+ [2023-03-21 12:12:20,799][23264] Num frames 7100...
664
+ [2023-03-21 12:12:20,857][23264] Num frames 7200...
665
+ [2023-03-21 12:12:20,914][23264] Num frames 7300...
666
+ [2023-03-21 12:12:20,972][23264] Num frames 7400...
667
+ [2023-03-21 12:12:21,031][23264] Num frames 7500...
668
+ [2023-03-21 12:12:21,090][23264] Num frames 7600...
669
+ [2023-03-21 12:12:21,144][23264] Avg episode rewards: #0: 26.003, true rewards: #0: 10.860
670
+ [2023-03-21 12:12:21,144][23264] Avg episode reward: 26.003, avg true_objective: 10.860
671
+ [2023-03-21 12:12:21,203][23264] Num frames 7700...
672
+ [2023-03-21 12:12:21,262][23264] Num frames 7800...
673
+ [2023-03-21 12:12:21,321][23264] Num frames 7900...
674
+ [2023-03-21 12:12:21,379][23264] Num frames 8000...
675
+ [2023-03-21 12:12:21,436][23264] Num frames 8100...
676
+ [2023-03-21 12:12:21,493][23264] Num frames 8200...
677
+ [2023-03-21 12:12:21,551][23264] Num frames 8300...
678
+ [2023-03-21 12:12:21,609][23264] Num frames 8400...
679
+ [2023-03-21 12:12:21,663][23264] Avg episode rewards: #0: 24.877, true rewards: #0: 10.502
680
+ [2023-03-21 12:12:21,663][23264] Avg episode reward: 24.877, avg true_objective: 10.502
681
+ [2023-03-21 12:12:21,721][23264] Num frames 8500...
682
+ [2023-03-21 12:12:21,779][23264] Num frames 8600...
683
+ [2023-03-21 12:12:21,837][23264] Num frames 8700...
684
+ [2023-03-21 12:12:21,895][23264] Num frames 8800...
685
+ [2023-03-21 12:12:21,953][23264] Num frames 8900...
686
+ [2023-03-21 12:12:22,011][23264] Num frames 9000...
687
+ [2023-03-21 12:12:22,075][23264] Num frames 9100...
688
+ [2023-03-21 12:12:22,133][23264] Num frames 9200...
689
+ [2023-03-21 12:12:22,191][23264] Num frames 9300...
690
+ [2023-03-21 12:12:22,251][23264] Num frames 9400...
691
+ [2023-03-21 12:12:22,310][23264] Num frames 9500...
692
+ [2023-03-21 12:12:22,369][23264] Num frames 9600...
693
+ [2023-03-21 12:12:22,428][23264] Num frames 9700...
694
+ [2023-03-21 12:12:22,491][23264] Num frames 9800...
695
+ [2023-03-21 12:12:22,549][23264] Num frames 9900...
696
+ [2023-03-21 12:12:22,608][23264] Num frames 10000...
697
+ [2023-03-21 12:12:22,667][23264] Num frames 10100...
698
+ [2023-03-21 12:12:22,727][23264] Num frames 10200...
699
+ [2023-03-21 12:12:22,813][23264] Avg episode rewards: #0: 28.284, true rewards: #0: 11.396
700
+ [2023-03-21 12:12:22,814][23264] Avg episode reward: 28.284, avg true_objective: 11.396
701
+ [2023-03-21 12:12:22,847][23264] Num frames 10300...
702
+ [2023-03-21 12:12:22,905][23264] Num frames 10400...
703
+ [2023-03-21 12:12:22,963][23264] Num frames 10500...
704
+ [2023-03-21 12:12:23,028][23264] Num frames 10600...
705
+ [2023-03-21 12:12:23,087][23264] Num frames 10700...
706
+ [2023-03-21 12:12:23,144][23264] Num frames 10800...
707
+ [2023-03-21 12:12:23,202][23264] Num frames 10900...
708
+ [2023-03-21 12:12:23,261][23264] Num frames 11000...
709
+ [2023-03-21 12:12:23,323][23264] Avg episode rewards: #0: 27.015, true rewards: #0: 11.015
710
+ [2023-03-21 12:12:23,323][23264] Avg episode reward: 27.015, avg true_objective: 11.015
711
+ [2023-03-21 12:12:35,089][23264] Replay video saved to /home/antpc/Desktop/rl_course/train_dir/default_experiment/replay.mp4!