Upload . with huggingface_hub
Browse files- .gitattributes +1 -0
- .summary/0/events.out.tfevents.1678279038.michal-H81M-S2H +3 -0
- .summary/0/events.out.tfevents.1678282286.michal-H81M-S2H +3 -0
- README.md +56 -0
- checkpoint_p0/best_000000892_3653632_reward_22.082.pth +3 -0
- checkpoint_p0/checkpoint_000000081_331776.pth +3 -0
- checkpoint_p0/checkpoint_000000978_4005888.pth +3 -0
- config.json +142 -0
- replay.mp4 +3 -0
- sf_log.txt +1052 -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.1678279038.michal-H81M-S2H
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a9b82efe7d17648cf58921c9df807a59cae51c633925601ae4e95e8c994dc4c3
|
3 |
+
size 8894
|
.summary/0/events.out.tfevents.1678282286.michal-H81M-S2H
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:19490d73b4edd3abf8e82aa2026d116475f9de0a069106f63fddab0fa6cfad35
|
3 |
+
size 104215
|
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: 8.85 +/- 2.91
|
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 michal512/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_000000892_3653632_reward_22.082.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dc8edb8ef64f85e4cd0dc6aa8962225fb5aca5eb431de88471f9fc7933b0c076
|
3 |
+
size 34924044
|
checkpoint_p0/checkpoint_000000081_331776.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a0e165aaa4a3b71056af9b8f96b9eda620f79ec570fc7b0a0167746b000e7228
|
3 |
+
size 34923980
|
checkpoint_p0/checkpoint_000000978_4005888.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b750d17d7dad1828db427c1c5e4a67c4030d382b18db4338839a8912f4a1533d
|
3 |
+
size 34924044
|
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/michal/programming/deep-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": 4000000,
|
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=4000000",
|
134 |
+
"cli_args": {
|
135 |
+
"env": "doom_health_gathering_supreme",
|
136 |
+
"num_workers": 8,
|
137 |
+
"num_envs_per_worker": 4,
|
138 |
+
"train_for_env_steps": 4000000
|
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:f176ceed95a756d25b321ddac54033a185ff0ae1330cc0d09616c31708f2a5e6
|
3 |
+
size 16487549
|
sf_log.txt
ADDED
@@ -0,0 +1,1052 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
[2023-03-08 13:37:19,359][669675] Saving configuration to /home/michal/programming/deep-rl-course/train_dir/default_experiment/config.json...
|
2 |
+
[2023-03-08 13:37:19,359][669675] Rollout worker 0 uses device cpu
|
3 |
+
[2023-03-08 13:37:19,360][669675] Rollout worker 1 uses device cpu
|
4 |
+
[2023-03-08 13:37:19,360][669675] Rollout worker 2 uses device cpu
|
5 |
+
[2023-03-08 13:37:19,361][669675] Rollout worker 3 uses device cpu
|
6 |
+
[2023-03-08 13:37:19,361][669675] Rollout worker 4 uses device cpu
|
7 |
+
[2023-03-08 13:37:19,361][669675] Rollout worker 5 uses device cpu
|
8 |
+
[2023-03-08 13:37:19,362][669675] Rollout worker 6 uses device cpu
|
9 |
+
[2023-03-08 13:37:19,362][669675] Rollout worker 7 uses device cpu
|
10 |
+
[2023-03-08 13:37:19,411][669675] Using GPUs [0] for process 0 (actually maps to GPUs [0])
|
11 |
+
[2023-03-08 13:37:19,412][669675] InferenceWorker_p0-w0: min num requests: 2
|
12 |
+
[2023-03-08 13:37:19,430][669675] Starting all processes...
|
13 |
+
[2023-03-08 13:37:19,430][669675] Starting process learner_proc0
|
14 |
+
[2023-03-08 13:37:19,480][669675] Starting all processes...
|
15 |
+
[2023-03-08 13:37:19,484][669675] Starting process inference_proc0-0
|
16 |
+
[2023-03-08 13:37:19,485][669675] Starting process rollout_proc0
|
17 |
+
[2023-03-08 13:37:19,485][669675] Starting process rollout_proc1
|
18 |
+
[2023-03-08 13:37:19,486][669675] Starting process rollout_proc2
|
19 |
+
[2023-03-08 13:37:19,486][669675] Starting process rollout_proc3
|
20 |
+
[2023-03-08 13:37:19,486][669675] Starting process rollout_proc4
|
21 |
+
[2023-03-08 13:37:19,486][669675] Starting process rollout_proc5
|
22 |
+
[2023-03-08 13:37:19,486][669675] Starting process rollout_proc6
|
23 |
+
[2023-03-08 13:37:19,491][669675] Starting process rollout_proc7
|
24 |
+
[2023-03-08 13:37:20,414][670949] Using GPUs [0] for process 0 (actually maps to GPUs [0])
|
25 |
+
[2023-03-08 13:37:20,414][670949] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for learning process 0
|
26 |
+
[2023-03-08 13:37:20,419][670949] Num visible devices: 1
|
27 |
+
[2023-03-08 13:37:20,424][670962] Worker 0 uses CPU cores [0, 1]
|
28 |
+
[2023-03-08 13:37:20,444][670949] Starting seed is not provided
|
29 |
+
[2023-03-08 13:37:20,444][670949] Using GPUs [0] for process 0 (actually maps to GPUs [0])
|
30 |
+
[2023-03-08 13:37:20,445][670949] Initializing actor-critic model on device cuda:0
|
31 |
+
[2023-03-08 13:37:20,445][670949] RunningMeanStd input shape: (3, 72, 128)
|
32 |
+
[2023-03-08 13:37:20,445][670949] RunningMeanStd input shape: (1,)
|
33 |
+
[2023-03-08 13:37:20,462][670949] ConvEncoder: input_channels=3
|
34 |
+
[2023-03-08 13:37:20,464][670965] Worker 2 uses CPU cores [4, 5]
|
35 |
+
[2023-03-08 13:37:20,471][670963] Worker 1 uses CPU cores [2, 3]
|
36 |
+
[2023-03-08 13:37:20,556][670949] Conv encoder output size: 512
|
37 |
+
[2023-03-08 13:37:20,556][670949] Policy head output size: 512
|
38 |
+
[2023-03-08 13:37:20,565][670949] Created Actor Critic model with architecture:
|
39 |
+
[2023-03-08 13:37:20,566][670949] ActorCriticSharedWeights(
|
40 |
+
(obs_normalizer): ObservationNormalizer(
|
41 |
+
(running_mean_std): RunningMeanStdDictInPlace(
|
42 |
+
(running_mean_std): ModuleDict(
|
43 |
+
(obs): RunningMeanStdInPlace()
|
44 |
+
)
|
45 |
+
)
|
46 |
+
)
|
47 |
+
(returns_normalizer): RecursiveScriptModule(original_name=RunningMeanStdInPlace)
|
48 |
+
(encoder): VizdoomEncoder(
|
49 |
+
(basic_encoder): ConvEncoder(
|
50 |
+
(enc): RecursiveScriptModule(
|
51 |
+
original_name=ConvEncoderImpl
|
52 |
+
(conv_head): RecursiveScriptModule(
|
53 |
+
original_name=Sequential
|
54 |
+
(0): RecursiveScriptModule(original_name=Conv2d)
|
55 |
+
(1): RecursiveScriptModule(original_name=ELU)
|
56 |
+
(2): RecursiveScriptModule(original_name=Conv2d)
|
57 |
+
(3): RecursiveScriptModule(original_name=ELU)
|
58 |
+
(4): RecursiveScriptModule(original_name=Conv2d)
|
59 |
+
(5): RecursiveScriptModule(original_name=ELU)
|
60 |
+
)
|
61 |
+
(mlp_layers): RecursiveScriptModule(
|
62 |
+
original_name=Sequential
|
63 |
+
(0): RecursiveScriptModule(original_name=Linear)
|
64 |
+
(1): RecursiveScriptModule(original_name=ELU)
|
65 |
+
)
|
66 |
+
)
|
67 |
+
)
|
68 |
+
)
|
69 |
+
(core): ModelCoreRNN(
|
70 |
+
(core): GRU(512, 512)
|
71 |
+
)
|
72 |
+
(decoder): MlpDecoder(
|
73 |
+
(mlp): Identity()
|
74 |
+
)
|
75 |
+
(critic_linear): Linear(in_features=512, out_features=1, bias=True)
|
76 |
+
(action_parameterization): ActionParameterizationDefault(
|
77 |
+
(distribution_linear): Linear(in_features=512, out_features=5, bias=True)
|
78 |
+
)
|
79 |
+
)
|
80 |
+
[2023-03-08 13:37:20,578][670985] Worker 7 uses CPU cores [14, 15]
|
81 |
+
[2023-03-08 13:37:20,579][670967] Worker 4 uses CPU cores [8, 9]
|
82 |
+
[2023-03-08 13:37:20,583][670969] Worker 6 uses CPU cores [12, 13]
|
83 |
+
[2023-03-08 13:37:20,601][670964] Using GPUs [0] for process 0 (actually maps to GPUs [0])
|
84 |
+
[2023-03-08 13:37:20,601][670964] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for inference process 0
|
85 |
+
[2023-03-08 13:37:20,608][670964] Num visible devices: 1
|
86 |
+
[2023-03-08 13:37:20,625][670968] Worker 5 uses CPU cores [10, 11]
|
87 |
+
[2023-03-08 13:37:20,652][670966] Worker 3 uses CPU cores [6, 7]
|
88 |
+
[2023-03-08 13:37:21,689][670949] Using optimizer <class 'torch.optim.adam.Adam'>
|
89 |
+
[2023-03-08 13:37:21,690][670949] No checkpoints found
|
90 |
+
[2023-03-08 13:37:21,690][670949] Did not load from checkpoint, starting from scratch!
|
91 |
+
[2023-03-08 13:37:21,690][670949] Initialized policy 0 weights for model version 0
|
92 |
+
[2023-03-08 13:37:21,692][670949] LearnerWorker_p0 finished initialization!
|
93 |
+
[2023-03-08 13:37:21,692][670949] Using GPUs [0] for process 0 (actually maps to GPUs [0])
|
94 |
+
[2023-03-08 13:37:21,762][670964] RunningMeanStd input shape: (3, 72, 128)
|
95 |
+
[2023-03-08 13:37:21,762][670964] RunningMeanStd input shape: (1,)
|
96 |
+
[2023-03-08 13:37:21,769][670964] ConvEncoder: input_channels=3
|
97 |
+
[2023-03-08 13:37:21,834][670964] Conv encoder output size: 512
|
98 |
+
[2023-03-08 13:37:21,834][670964] Policy head output size: 512
|
99 |
+
[2023-03-08 13:37:22,875][669675] Inference worker 0-0 is ready!
|
100 |
+
[2023-03-08 13:37:22,876][669675] All inference workers are ready! Signal rollout workers to start!
|
101 |
+
[2023-03-08 13:37:22,911][670963] Doom resolution: 160x120, resize resolution: (128, 72)
|
102 |
+
[2023-03-08 13:37:22,914][670965] Doom resolution: 160x120, resize resolution: (128, 72)
|
103 |
+
[2023-03-08 13:37:22,918][670969] Doom resolution: 160x120, resize resolution: (128, 72)
|
104 |
+
[2023-03-08 13:37:22,919][670968] Doom resolution: 160x120, resize resolution: (128, 72)
|
105 |
+
[2023-03-08 13:37:22,928][670985] Doom resolution: 160x120, resize resolution: (128, 72)
|
106 |
+
[2023-03-08 13:37:22,928][670966] Doom resolution: 160x120, resize resolution: (128, 72)
|
107 |
+
[2023-03-08 13:37:22,929][670962] Doom resolution: 160x120, resize resolution: (128, 72)
|
108 |
+
[2023-03-08 13:37:22,929][670967] Doom resolution: 160x120, resize resolution: (128, 72)
|
109 |
+
[2023-03-08 13:37:23,122][670962] Decorrelating experience for 0 frames...
|
110 |
+
[2023-03-08 13:37:23,122][670963] Decorrelating experience for 0 frames...
|
111 |
+
[2023-03-08 13:37:23,122][670985] Decorrelating experience for 0 frames...
|
112 |
+
[2023-03-08 13:37:23,123][670965] Decorrelating experience for 0 frames...
|
113 |
+
[2023-03-08 13:37:23,123][670969] Decorrelating experience for 0 frames...
|
114 |
+
[2023-03-08 13:37:23,257][670969] Decorrelating experience for 32 frames...
|
115 |
+
[2023-03-08 13:37:23,258][670965] Decorrelating experience for 32 frames...
|
116 |
+
[2023-03-08 13:37:23,266][670963] Decorrelating experience for 32 frames...
|
117 |
+
[2023-03-08 13:37:23,272][669675] 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)
|
118 |
+
[2023-03-08 13:37:23,306][670985] Decorrelating experience for 32 frames...
|
119 |
+
[2023-03-08 13:37:23,306][670967] Decorrelating experience for 0 frames...
|
120 |
+
[2023-03-08 13:37:23,346][670966] Decorrelating experience for 0 frames...
|
121 |
+
[2023-03-08 13:37:23,457][670965] Decorrelating experience for 64 frames...
|
122 |
+
[2023-03-08 13:37:23,458][670985] Decorrelating experience for 64 frames...
|
123 |
+
[2023-03-08 13:37:23,466][670967] Decorrelating experience for 32 frames...
|
124 |
+
[2023-03-08 13:37:23,466][670969] Decorrelating experience for 64 frames...
|
125 |
+
[2023-03-08 13:37:23,479][670966] Decorrelating experience for 32 frames...
|
126 |
+
[2023-03-08 13:37:23,544][670962] Decorrelating experience for 32 frames...
|
127 |
+
[2023-03-08 13:37:23,621][670985] Decorrelating experience for 96 frames...
|
128 |
+
[2023-03-08 13:37:23,627][670965] Decorrelating experience for 96 frames...
|
129 |
+
[2023-03-08 13:37:23,635][670967] Decorrelating experience for 64 frames...
|
130 |
+
[2023-03-08 13:37:23,666][670969] Decorrelating experience for 96 frames...
|
131 |
+
[2023-03-08 13:37:23,804][670963] Decorrelating experience for 64 frames...
|
132 |
+
[2023-03-08 13:37:23,829][670966] Decorrelating experience for 64 frames...
|
133 |
+
[2023-03-08 13:37:23,854][670967] Decorrelating experience for 96 frames...
|
134 |
+
[2023-03-08 13:37:23,882][670962] Decorrelating experience for 64 frames...
|
135 |
+
[2023-03-08 13:37:24,039][670968] Decorrelating experience for 0 frames...
|
136 |
+
[2023-03-08 13:37:24,042][670963] Decorrelating experience for 96 frames...
|
137 |
+
[2023-03-08 13:37:24,056][670966] Decorrelating experience for 96 frames...
|
138 |
+
[2023-03-08 13:37:24,099][670962] Decorrelating experience for 96 frames...
|
139 |
+
[2023-03-08 13:37:24,216][670949] Signal inference workers to stop experience collection...
|
140 |
+
[2023-03-08 13:37:24,218][670964] InferenceWorker_p0-w0: stopping experience collection
|
141 |
+
[2023-03-08 13:37:24,232][670968] Decorrelating experience for 32 frames...
|
142 |
+
[2023-03-08 13:37:24,388][670968] Decorrelating experience for 64 frames...
|
143 |
+
[2023-03-08 13:37:24,475][670949] Signal inference workers to resume experience collection...
|
144 |
+
[2023-03-08 13:37:24,475][670964] InferenceWorker_p0-w0: resuming experience collection
|
145 |
+
[2023-03-08 13:37:24,533][670968] Decorrelating experience for 96 frames...
|
146 |
+
[2023-03-08 13:37:25,922][670964] Updated weights for policy 0, policy_version 10 (0.0168)
|
147 |
+
[2023-03-08 13:37:27,103][670964] Updated weights for policy 0, policy_version 20 (0.0006)
|
148 |
+
[2023-03-08 13:37:28,272][669675] Fps is (10 sec: 23756.6, 60 sec: 23756.6, 300 sec: 23756.6). Total num frames: 118784. Throughput: 0: 2183.2. Samples: 10916. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
|
149 |
+
[2023-03-08 13:37:28,273][669675] Avg episode reward: [(0, '4.545')]
|
150 |
+
[2023-03-08 13:37:28,277][670949] Saving new best policy, reward=4.545!
|
151 |
+
[2023-03-08 13:37:28,372][670964] Updated weights for policy 0, policy_version 30 (0.0007)
|
152 |
+
[2023-03-08 13:37:29,596][670964] Updated weights for policy 0, policy_version 40 (0.0006)
|
153 |
+
[2023-03-08 13:37:30,793][670964] Updated weights for policy 0, policy_version 50 (0.0006)
|
154 |
+
[2023-03-08 13:37:32,060][670964] Updated weights for policy 0, policy_version 60 (0.0006)
|
155 |
+
[2023-03-08 13:37:33,231][670964] Updated weights for policy 0, policy_version 70 (0.0006)
|
156 |
+
[2023-03-08 13:37:33,272][669675] Fps is (10 sec: 28672.1, 60 sec: 28672.1, 300 sec: 28672.1). Total num frames: 286720. Throughput: 0: 6086.0. Samples: 60860. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0)
|
157 |
+
[2023-03-08 13:37:33,273][669675] Avg episode reward: [(0, '4.602')]
|
158 |
+
[2023-03-08 13:37:33,274][670949] Saving new best policy, reward=4.602!
|
159 |
+
[2023-03-08 13:37:34,475][670964] Updated weights for policy 0, policy_version 80 (0.0006)
|
160 |
+
[2023-03-08 13:37:34,573][670969] EvtLoop [rollout_proc6_evt_loop, process=rollout_proc6] unhandled exception in slot='advance_rollouts' connected to emitter=Emitter(object_id='InferenceWorker_p0-w0', signal_name='advance6'), args=(0, 0)
|
161 |
+
Traceback (most recent call last):
|
162 |
+
File "/home/michal/anaconda3/envs/deep-rl/lib/python3.9/site-packages/signal_slot/signal_slot.py", line 355, in _process_signal
|
163 |
+
slot_callable(*args)
|
164 |
+
File "/home/michal/anaconda3/envs/deep-rl/lib/python3.9/site-packages/sample_factory/algo/sampling/rollout_worker.py", line 241, in advance_rollouts
|
165 |
+
complete_rollouts, episodic_stats = runner.advance_rollouts(policy_id, self.timing)
|
166 |
+
File "/home/michal/anaconda3/envs/deep-rl/lib/python3.9/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 634, in advance_rollouts
|
167 |
+
new_obs, rewards, terminated, truncated, infos = e.step(actions)
|
168 |
+
File "/home/michal/anaconda3/envs/deep-rl/lib/python3.9/site-packages/gym/core.py", line 319, in step
|
169 |
+
return self.env.step(action)
|
170 |
+
File "/home/michal/anaconda3/envs/deep-rl/lib/python3.9/site-packages/sample_factory/algo/utils/make_env.py", line 129, in step
|
171 |
+
obs, rew, terminated, truncated, info = self.env.step(action)
|
172 |
+
File "/home/michal/anaconda3/envs/deep-rl/lib/python3.9/site-packages/sample_factory/algo/utils/make_env.py", line 115, in step
|
173 |
+
obs, rew, terminated, truncated, info = self.env.step(action)
|
174 |
+
File "/home/michal/anaconda3/envs/deep-rl/lib/python3.9/site-packages/sf_examples/vizdoom/doom/wrappers/scenario_wrappers/gathering_reward_shaping.py", line 33, in step
|
175 |
+
observation, reward, terminated, truncated, info = self.env.step(action)
|
176 |
+
File "/home/michal/anaconda3/envs/deep-rl/lib/python3.9/site-packages/gym/core.py", line 384, in step
|
177 |
+
observation, reward, terminated, truncated, info = self.env.step(action)
|
178 |
+
File "/home/michal/anaconda3/envs/deep-rl/lib/python3.9/site-packages/sample_factory/envs/env_wrappers.py", line 88, in step
|
179 |
+
obs, reward, terminated, truncated, info = self.env.step(action)
|
180 |
+
File "/home/michal/anaconda3/envs/deep-rl/lib/python3.9/site-packages/gym/core.py", line 319, in step
|
181 |
+
return self.env.step(action)
|
182 |
+
File "/home/michal/anaconda3/envs/deep-rl/lib/python3.9/site-packages/sf_examples/vizdoom/doom/wrappers/multiplayer_stats.py", line 54, in step
|
183 |
+
obs, reward, terminated, truncated, info = self.env.step(action)
|
184 |
+
File "/home/michal/anaconda3/envs/deep-rl/lib/python3.9/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 452, in step
|
185 |
+
reward = self.game.make_action(actions_flattened, self.skip_frames)
|
186 |
+
vizdoom.vizdoom.SignalException: Signal SIGINT received. ViZDoom instance has been closed.
|
187 |
+
[2023-03-08 13:37:34,575][670969] Unhandled exception Signal SIGINT received. ViZDoom instance has been closed. in evt loop rollout_proc6_evt_loop
|
188 |
+
[2023-03-08 13:37:34,577][670965] EvtLoop [rollout_proc2_evt_loop, process=rollout_proc2] unhandled exception in slot='advance_rollouts' connected to emitter=Emitter(object_id='InferenceWorker_p0-w0', signal_name='advance2'), args=(1, 0)
|
189 |
+
Traceback (most recent call last):
|
190 |
+
File "/home/michal/anaconda3/envs/deep-rl/lib/python3.9/site-packages/signal_slot/signal_slot.py", line 355, in _process_signal
|
191 |
+
slot_callable(*args)
|
192 |
+
File "/home/michal/anaconda3/envs/deep-rl/lib/python3.9/site-packages/sample_factory/algo/sampling/rollout_worker.py", line 241, in advance_rollouts
|
193 |
+
complete_rollouts, episodic_stats = runner.advance_rollouts(policy_id, self.timing)
|
194 |
+
File "/home/michal/anaconda3/envs/deep-rl/lib/python3.9/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 634, in advance_rollouts
|
195 |
+
new_obs, rewards, terminated, truncated, infos = e.step(actions)
|
196 |
+
File "/home/michal/anaconda3/envs/deep-rl/lib/python3.9/site-packages/gym/core.py", line 319, in step
|
197 |
+
return self.env.step(action)
|
198 |
+
File "/home/michal/anaconda3/envs/deep-rl/lib/python3.9/site-packages/sample_factory/algo/utils/make_env.py", line 129, in step
|
199 |
+
obs, rew, terminated, truncated, info = self.env.step(action)
|
200 |
+
File "/home/michal/anaconda3/envs/deep-rl/lib/python3.9/site-packages/sample_factory/algo/utils/make_env.py", line 115, in step
|
201 |
+
obs, rew, terminated, truncated, info = self.env.step(action)
|
202 |
+
File "/home/michal/anaconda3/envs/deep-rl/lib/python3.9/site-packages/sf_examples/vizdoom/doom/wrappers/scenario_wrappers/gathering_reward_shaping.py", line 33, in step
|
203 |
+
observation, reward, terminated, truncated, info = self.env.step(action)
|
204 |
+
File "/home/michal/anaconda3/envs/deep-rl/lib/python3.9/site-packages/gym/core.py", line 384, in step
|
205 |
+
observation, reward, terminated, truncated, info = self.env.step(action)
|
206 |
+
File "/home/michal/anaconda3/envs/deep-rl/lib/python3.9/site-packages/sample_factory/envs/env_wrappers.py", line 88, in step
|
207 |
+
obs, reward, terminated, truncated, info = self.env.step(action)
|
208 |
+
File "/home/michal/anaconda3/envs/deep-rl/lib/python3.9/site-packages/gym/core.py", line 319, in step
|
209 |
+
return self.env.step(action)
|
210 |
+
File "/home/michal/anaconda3/envs/deep-rl/lib/python3.9/site-packages/sf_examples/vizdoom/doom/wrappers/multiplayer_stats.py", line 54, in step
|
211 |
+
obs, reward, terminated, truncated, info = self.env.step(action)
|
212 |
+
File "/home/michal/anaconda3/envs/deep-rl/lib/python3.9/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 452, in step
|
213 |
+
reward = self.game.make_action(actions_flattened, self.skip_frames)
|
214 |
+
vizdoom.vizdoom.SignalException: Signal SIGINT received. ViZDoom instance has been closed.
|
215 |
+
[2023-03-08 13:37:34,577][670963] EvtLoop [rollout_proc1_evt_loop, process=rollout_proc1] unhandled exception in slot='advance_rollouts' connected to emitter=Emitter(object_id='InferenceWorker_p0-w0', signal_name='advance1'), args=(1, 0)
|
216 |
+
Traceback (most recent call last):
|
217 |
+
File "/home/michal/anaconda3/envs/deep-rl/lib/python3.9/site-packages/signal_slot/signal_slot.py", line 355, in _process_signal
|
218 |
+
slot_callable(*args)
|
219 |
+
File "/home/michal/anaconda3/envs/deep-rl/lib/python3.9/site-packages/sample_factory/algo/sampling/rollout_worker.py", line 241, in advance_rollouts
|
220 |
+
complete_rollouts, episodic_stats = runner.advance_rollouts(policy_id, self.timing)
|
221 |
+
File "/home/michal/anaconda3/envs/deep-rl/lib/python3.9/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 634, in advance_rollouts
|
222 |
+
new_obs, rewards, terminated, truncated, infos = e.step(actions)
|
223 |
+
File "/home/michal/anaconda3/envs/deep-rl/lib/python3.9/site-packages/gym/core.py", line 319, in step
|
224 |
+
return self.env.step(action)
|
225 |
+
File "/home/michal/anaconda3/envs/deep-rl/lib/python3.9/site-packages/sample_factory/algo/utils/make_env.py", line 129, in step
|
226 |
+
obs, rew, terminated, truncated, info = self.env.step(action)
|
227 |
+
File "/home/michal/anaconda3/envs/deep-rl/lib/python3.9/site-packages/sample_factory/algo/utils/make_env.py", line 115, in step
|
228 |
+
obs, rew, terminated, truncated, info = self.env.step(action)
|
229 |
+
File "/home/michal/anaconda3/envs/deep-rl/lib/python3.9/site-packages/sf_examples/vizdoom/doom/wrappers/scenario_wrappers/gathering_reward_shaping.py", line 33, in step
|
230 |
+
observation, reward, terminated, truncated, info = self.env.step(action)
|
231 |
+
File "/home/michal/anaconda3/envs/deep-rl/lib/python3.9/site-packages/gym/core.py", line 384, in step
|
232 |
+
observation, reward, terminated, truncated, info = self.env.step(action)
|
233 |
+
File "/home/michal/anaconda3/envs/deep-rl/lib/python3.9/site-packages/sample_factory/envs/env_wrappers.py", line 88, in step
|
234 |
+
obs, reward, terminated, truncated, info = self.env.step(action)
|
235 |
+
File "/home/michal/anaconda3/envs/deep-rl/lib/python3.9/site-packages/gym/core.py", line 319, in step
|
236 |
+
return self.env.step(action)
|
237 |
+
File "/home/michal/anaconda3/envs/deep-rl/lib/python3.9/site-packages/sf_examples/vizdoom/doom/wrappers/multiplayer_stats.py", line 54, in step
|
238 |
+
obs, reward, terminated, truncated, info = self.env.step(action)
|
239 |
+
File "/home/michal/anaconda3/envs/deep-rl/lib/python3.9/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 452, in step
|
240 |
+
reward = self.game.make_action(actions_flattened, self.skip_frames)
|
241 |
+
vizdoom.vizdoom.SignalException: Signal SIGINT received. ViZDoom instance has been closed.
|
242 |
+
[2023-03-08 13:37:34,579][670965] Unhandled exception Signal SIGINT received. ViZDoom instance has been closed. in evt loop rollout_proc2_evt_loop
|
243 |
+
[2023-03-08 13:37:34,579][670963] Unhandled exception Signal SIGINT received. ViZDoom instance has been closed. in evt loop rollout_proc1_evt_loop
|
244 |
+
[2023-03-08 13:37:34,579][670968] EvtLoop [rollout_proc5_evt_loop, process=rollout_proc5] unhandled exception in slot='advance_rollouts' connected to emitter=Emitter(object_id='InferenceWorker_p0-w0', signal_name='advance5'), args=(0, 0)
|
245 |
+
Traceback (most recent call last):
|
246 |
+
File "/home/michal/anaconda3/envs/deep-rl/lib/python3.9/site-packages/signal_slot/signal_slot.py", line 355, in _process_signal
|
247 |
+
slot_callable(*args)
|
248 |
+
File "/home/michal/anaconda3/envs/deep-rl/lib/python3.9/site-packages/sample_factory/algo/sampling/rollout_worker.py", line 241, in advance_rollouts
|
249 |
+
complete_rollouts, episodic_stats = runner.advance_rollouts(policy_id, self.timing)
|
250 |
+
File "/home/michal/anaconda3/envs/deep-rl/lib/python3.9/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 634, in advance_rollouts
|
251 |
+
new_obs, rewards, terminated, truncated, infos = e.step(actions)
|
252 |
+
File "/home/michal/anaconda3/envs/deep-rl/lib/python3.9/site-packages/gym/core.py", line 319, in step
|
253 |
+
return self.env.step(action)
|
254 |
+
File "/home/michal/anaconda3/envs/deep-rl/lib/python3.9/site-packages/sample_factory/algo/utils/make_env.py", line 129, in step
|
255 |
+
obs, rew, terminated, truncated, info = self.env.step(action)
|
256 |
+
File "/home/michal/anaconda3/envs/deep-rl/lib/python3.9/site-packages/sample_factory/algo/utils/make_env.py", line 115, in step
|
257 |
+
obs, rew, terminated, truncated, info = self.env.step(action)
|
258 |
+
File "/home/michal/anaconda3/envs/deep-rl/lib/python3.9/site-packages/sf_examples/vizdoom/doom/wrappers/scenario_wrappers/gathering_reward_shaping.py", line 33, in step
|
259 |
+
observation, reward, terminated, truncated, info = self.env.step(action)
|
260 |
+
File "/home/michal/anaconda3/envs/deep-rl/lib/python3.9/site-packages/gym/core.py", line 384, in step
|
261 |
+
observation, reward, terminated, truncated, info = self.env.step(action)
|
262 |
+
File "/home/michal/anaconda3/envs/deep-rl/lib/python3.9/site-packages/sample_factory/envs/env_wrappers.py", line 88, in step
|
263 |
+
obs, reward, terminated, truncated, info = self.env.step(action)
|
264 |
+
File "/home/michal/anaconda3/envs/deep-rl/lib/python3.9/site-packages/gym/core.py", line 319, in step
|
265 |
+
return self.env.step(action)
|
266 |
+
File "/home/michal/anaconda3/envs/deep-rl/lib/python3.9/site-packages/sf_examples/vizdoom/doom/wrappers/multiplayer_stats.py", line 54, in step
|
267 |
+
obs, reward, terminated, truncated, info = self.env.step(action)
|
268 |
+
File "/home/michal/anaconda3/envs/deep-rl/lib/python3.9/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 452, in step
|
269 |
+
reward = self.game.make_action(actions_flattened, self.skip_frames)
|
270 |
+
vizdoom.vizdoom.SignalException: Signal SIGINT received. ViZDoom instance has been closed.
|
271 |
+
[2023-03-08 13:37:34,580][670985] EvtLoop [rollout_proc7_evt_loop, process=rollout_proc7] unhandled exception in slot='advance_rollouts' connected to emitter=Emitter(object_id='InferenceWorker_p0-w0', signal_name='advance7'), args=(0, 0)
|
272 |
+
Traceback (most recent call last):
|
273 |
+
File "/home/michal/anaconda3/envs/deep-rl/lib/python3.9/site-packages/signal_slot/signal_slot.py", line 355, in _process_signal
|
274 |
+
slot_callable(*args)
|
275 |
+
File "/home/michal/anaconda3/envs/deep-rl/lib/python3.9/site-packages/sample_factory/algo/sampling/rollout_worker.py", line 241, in advance_rollouts
|
276 |
+
complete_rollouts, episodic_stats = runner.advance_rollouts(policy_id, self.timing)
|
277 |
+
File "/home/michal/anaconda3/envs/deep-rl/lib/python3.9/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 634, in advance_rollouts
|
278 |
+
new_obs, rewards, terminated, truncated, infos = e.step(actions)
|
279 |
+
File "/home/michal/anaconda3/envs/deep-rl/lib/python3.9/site-packages/gym/core.py", line 319, in step
|
280 |
+
return self.env.step(action)
|
281 |
+
File "/home/michal/anaconda3/envs/deep-rl/lib/python3.9/site-packages/sample_factory/algo/utils/make_env.py", line 129, in step
|
282 |
+
obs, rew, terminated, truncated, info = self.env.step(action)
|
283 |
+
File "/home/michal/anaconda3/envs/deep-rl/lib/python3.9/site-packages/sample_factory/algo/utils/make_env.py", line 115, in step
|
284 |
+
obs, rew, terminated, truncated, info = self.env.step(action)
|
285 |
+
File "/home/michal/anaconda3/envs/deep-rl/lib/python3.9/site-packages/sf_examples/vizdoom/doom/wrappers/scenario_wrappers/gathering_reward_shaping.py", line 33, in step
|
286 |
+
observation, reward, terminated, truncated, info = self.env.step(action)
|
287 |
+
File "/home/michal/anaconda3/envs/deep-rl/lib/python3.9/site-packages/gym/core.py", line 384, in step
|
288 |
+
observation, reward, terminated, truncated, info = self.env.step(action)
|
289 |
+
File "/home/michal/anaconda3/envs/deep-rl/lib/python3.9/site-packages/sample_factory/envs/env_wrappers.py", line 88, in step
|
290 |
+
obs, reward, terminated, truncated, info = self.env.step(action)
|
291 |
+
File "/home/michal/anaconda3/envs/deep-rl/lib/python3.9/site-packages/gym/core.py", line 319, in step
|
292 |
+
return self.env.step(action)
|
293 |
+
File "/home/michal/anaconda3/envs/deep-rl/lib/python3.9/site-packages/sf_examples/vizdoom/doom/wrappers/multiplayer_stats.py", line 54, in step
|
294 |
+
obs, reward, terminated, truncated, info = self.env.step(action)
|
295 |
+
File "/home/michal/anaconda3/envs/deep-rl/lib/python3.9/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 452, in step
|
296 |
+
reward = self.game.make_action(actions_flattened, self.skip_frames)
|
297 |
+
vizdoom.vizdoom.SignalException: Signal SIGINT received. ViZDoom instance has been closed.
|
298 |
+
[2023-03-08 13:37:34,581][670968] Unhandled exception Signal SIGINT received. ViZDoom instance has been closed. in evt loop rollout_proc5_evt_loop
|
299 |
+
[2023-03-08 13:37:34,581][670985] Unhandled exception Signal SIGINT received. ViZDoom instance has been closed. in evt loop rollout_proc7_evt_loop
|
300 |
+
[2023-03-08 13:37:34,580][669675] Keyboard interrupt detected in the event loop EvtLoop [Runner_EvtLoop, process=main process 669675], exiting...
|
301 |
+
[2023-03-08 13:37:34,580][670966] EvtLoop [rollout_proc3_evt_loop, process=rollout_proc3] unhandled exception in slot='advance_rollouts' connected to emitter=Emitter(object_id='InferenceWorker_p0-w0', signal_name='advance3'), args=(0, 0)
|
302 |
+
Traceback (most recent call last):
|
303 |
+
File "/home/michal/anaconda3/envs/deep-rl/lib/python3.9/site-packages/signal_slot/signal_slot.py", line 355, in _process_signal
|
304 |
+
slot_callable(*args)
|
305 |
+
File "/home/michal/anaconda3/envs/deep-rl/lib/python3.9/site-packages/sample_factory/algo/sampling/rollout_worker.py", line 241, in advance_rollouts
|
306 |
+
complete_rollouts, episodic_stats = runner.advance_rollouts(policy_id, self.timing)
|
307 |
+
File "/home/michal/anaconda3/envs/deep-rl/lib/python3.9/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 634, in advance_rollouts
|
308 |
+
new_obs, rewards, terminated, truncated, infos = e.step(actions)
|
309 |
+
File "/home/michal/anaconda3/envs/deep-rl/lib/python3.9/site-packages/gym/core.py", line 319, in step
|
310 |
+
return self.env.step(action)
|
311 |
+
File "/home/michal/anaconda3/envs/deep-rl/lib/python3.9/site-packages/sample_factory/algo/utils/make_env.py", line 129, in step
|
312 |
+
obs, rew, terminated, truncated, info = self.env.step(action)
|
313 |
+
File "/home/michal/anaconda3/envs/deep-rl/lib/python3.9/site-packages/sample_factory/algo/utils/make_env.py", line 115, in step
|
314 |
+
obs, rew, terminated, truncated, info = self.env.step(action)
|
315 |
+
File "/home/michal/anaconda3/envs/deep-rl/lib/python3.9/site-packages/sf_examples/vizdoom/doom/wrappers/scenario_wrappers/gathering_reward_shaping.py", line 33, in step
|
316 |
+
observation, reward, terminated, truncated, info = self.env.step(action)
|
317 |
+
File "/home/michal/anaconda3/envs/deep-rl/lib/python3.9/site-packages/gym/core.py", line 384, in step
|
318 |
+
observation, reward, terminated, truncated, info = self.env.step(action)
|
319 |
+
File "/home/michal/anaconda3/envs/deep-rl/lib/python3.9/site-packages/sample_factory/envs/env_wrappers.py", line 88, in step
|
320 |
+
obs, reward, terminated, truncated, info = self.env.step(action)
|
321 |
+
File "/home/michal/anaconda3/envs/deep-rl/lib/python3.9/site-packages/gym/core.py", line 319, in step
|
322 |
+
return self.env.step(action)
|
323 |
+
File "/home/michal/anaconda3/envs/deep-rl/lib/python3.9/site-packages/sf_examples/vizdoom/doom/wrappers/multiplayer_stats.py", line 54, in step
|
324 |
+
obs, reward, terminated, truncated, info = self.env.step(action)
|
325 |
+
File "/home/michal/anaconda3/envs/deep-rl/lib/python3.9/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 452, in step
|
326 |
+
reward = self.game.make_action(actions_flattened, self.skip_frames)
|
327 |
+
vizdoom.vizdoom.SignalException: Signal SIGINT received. ViZDoom instance has been closed.
|
328 |
+
[2023-03-08 13:37:34,582][670966] Unhandled exception Signal SIGINT received. ViZDoom instance has been closed. in evt loop rollout_proc3_evt_loop
|
329 |
+
[2023-03-08 13:37:34,582][670967] EvtLoop [rollout_proc4_evt_loop, process=rollout_proc4] unhandled exception in slot='advance_rollouts' connected to emitter=Emitter(object_id='InferenceWorker_p0-w0', signal_name='advance4'), args=(1, 0)
|
330 |
+
Traceback (most recent call last):
|
331 |
+
File "/home/michal/anaconda3/envs/deep-rl/lib/python3.9/site-packages/signal_slot/signal_slot.py", line 355, in _process_signal
|
332 |
+
slot_callable(*args)
|
333 |
+
File "/home/michal/anaconda3/envs/deep-rl/lib/python3.9/site-packages/sample_factory/algo/sampling/rollout_worker.py", line 241, in advance_rollouts
|
334 |
+
complete_rollouts, episodic_stats = runner.advance_rollouts(policy_id, self.timing)
|
335 |
+
File "/home/michal/anaconda3/envs/deep-rl/lib/python3.9/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 634, in advance_rollouts
|
336 |
+
new_obs, rewards, terminated, truncated, infos = e.step(actions)
|
337 |
+
File "/home/michal/anaconda3/envs/deep-rl/lib/python3.9/site-packages/gym/core.py", line 319, in step
|
338 |
+
return self.env.step(action)
|
339 |
+
File "/home/michal/anaconda3/envs/deep-rl/lib/python3.9/site-packages/sample_factory/algo/utils/make_env.py", line 129, in step
|
340 |
+
obs, rew, terminated, truncated, info = self.env.step(action)
|
341 |
+
File "/home/michal/anaconda3/envs/deep-rl/lib/python3.9/site-packages/sample_factory/algo/utils/make_env.py", line 115, in step
|
342 |
+
obs, rew, terminated, truncated, info = self.env.step(action)
|
343 |
+
File "/home/michal/anaconda3/envs/deep-rl/lib/python3.9/site-packages/sf_examples/vizdoom/doom/wrappers/scenario_wrappers/gathering_reward_shaping.py", line 33, in step
|
344 |
+
observation, reward, terminated, truncated, info = self.env.step(action)
|
345 |
+
File "/home/michal/anaconda3/envs/deep-rl/lib/python3.9/site-packages/gym/core.py", line 384, in step
|
346 |
+
observation, reward, terminated, truncated, info = self.env.step(action)
|
347 |
+
File "/home/michal/anaconda3/envs/deep-rl/lib/python3.9/site-packages/sample_factory/envs/env_wrappers.py", line 88, in step
|
348 |
+
obs, reward, terminated, truncated, info = self.env.step(action)
|
349 |
+
File "/home/michal/anaconda3/envs/deep-rl/lib/python3.9/site-packages/gym/core.py", line 319, in step
|
350 |
+
return self.env.step(action)
|
351 |
+
File "/home/michal/anaconda3/envs/deep-rl/lib/python3.9/site-packages/sf_examples/vizdoom/doom/wrappers/multiplayer_stats.py", line 54, in step
|
352 |
+
obs, reward, terminated, truncated, info = self.env.step(action)
|
353 |
+
File "/home/michal/anaconda3/envs/deep-rl/lib/python3.9/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 452, in step
|
354 |
+
reward = self.game.make_action(actions_flattened, self.skip_frames)
|
355 |
+
vizdoom.vizdoom.SignalException: Signal SIGINT received. ViZDoom instance has been closed.
|
356 |
+
[2023-03-08 13:37:34,585][670949] Stopping Batcher_0...
|
357 |
+
[2023-03-08 13:37:34,585][670949] Loop batcher_evt_loop terminating...
|
358 |
+
[2023-03-08 13:37:34,584][669675] Runner profile tree view:
|
359 |
+
main_loop: 15.1547
|
360 |
+
[2023-03-08 13:37:34,587][670967] Unhandled exception Signal SIGINT received. ViZDoom instance has been closed. in evt loop rollout_proc4_evt_loop
|
361 |
+
[2023-03-08 13:37:34,586][669675] Collected {0: 327680}, FPS: 21622.4
|
362 |
+
[2023-03-08 13:37:34,597][670949] Saving /home/michal/programming/deep-rl-course/train_dir/default_experiment/checkpoint_p0/checkpoint_000000081_331776.pth...
|
363 |
+
[2023-03-08 13:37:34,600][670962] EvtLoop [rollout_proc0_evt_loop, process=rollout_proc0] unhandled exception in slot='advance_rollouts' connected to emitter=Emitter(object_id='InferenceWorker_p0-w0', signal_name='advance0'), args=(1, 0)
|
364 |
+
Traceback (most recent call last):
|
365 |
+
File "/home/michal/anaconda3/envs/deep-rl/lib/python3.9/site-packages/signal_slot/signal_slot.py", line 355, in _process_signal
|
366 |
+
slot_callable(*args)
|
367 |
+
File "/home/michal/anaconda3/envs/deep-rl/lib/python3.9/site-packages/sample_factory/algo/sampling/rollout_worker.py", line 241, in advance_rollouts
|
368 |
+
complete_rollouts, episodic_stats = runner.advance_rollouts(policy_id, self.timing)
|
369 |
+
File "/home/michal/anaconda3/envs/deep-rl/lib/python3.9/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 634, in advance_rollouts
|
370 |
+
new_obs, rewards, terminated, truncated, infos = e.step(actions)
|
371 |
+
File "/home/michal/anaconda3/envs/deep-rl/lib/python3.9/site-packages/gym/core.py", line 319, in step
|
372 |
+
return self.env.step(action)
|
373 |
+
File "/home/michal/anaconda3/envs/deep-rl/lib/python3.9/site-packages/sample_factory/algo/utils/make_env.py", line 129, in step
|
374 |
+
obs, rew, terminated, truncated, info = self.env.step(action)
|
375 |
+
File "/home/michal/anaconda3/envs/deep-rl/lib/python3.9/site-packages/sample_factory/algo/utils/make_env.py", line 115, in step
|
376 |
+
obs, rew, terminated, truncated, info = self.env.step(action)
|
377 |
+
File "/home/michal/anaconda3/envs/deep-rl/lib/python3.9/site-packages/sf_examples/vizdoom/doom/wrappers/scenario_wrappers/gathering_reward_shaping.py", line 33, in step
|
378 |
+
observation, reward, terminated, truncated, info = self.env.step(action)
|
379 |
+
File "/home/michal/anaconda3/envs/deep-rl/lib/python3.9/site-packages/gym/core.py", line 384, in step
|
380 |
+
observation, reward, terminated, truncated, info = self.env.step(action)
|
381 |
+
File "/home/michal/anaconda3/envs/deep-rl/lib/python3.9/site-packages/sample_factory/envs/env_wrappers.py", line 88, in step
|
382 |
+
obs, reward, terminated, truncated, info = self.env.step(action)
|
383 |
+
File "/home/michal/anaconda3/envs/deep-rl/lib/python3.9/site-packages/gym/core.py", line 319, in step
|
384 |
+
return self.env.step(action)
|
385 |
+
File "/home/michal/anaconda3/envs/deep-rl/lib/python3.9/site-packages/sf_examples/vizdoom/doom/wrappers/multiplayer_stats.py", line 54, in step
|
386 |
+
obs, reward, terminated, truncated, info = self.env.step(action)
|
387 |
+
File "/home/michal/anaconda3/envs/deep-rl/lib/python3.9/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 452, in step
|
388 |
+
reward = self.game.make_action(actions_flattened, self.skip_frames)
|
389 |
+
vizdoom.vizdoom.SignalException: Signal SIGINT received. ViZDoom instance has been closed.
|
390 |
+
[2023-03-08 13:37:34,602][670962] Unhandled exception Signal SIGINT received. ViZDoom instance has been closed. in evt loop rollout_proc0_evt_loop
|
391 |
+
[2023-03-08 13:37:34,654][670964] Weights refcount: 2 0
|
392 |
+
[2023-03-08 13:37:34,661][670964] Stopping InferenceWorker_p0-w0...
|
393 |
+
[2023-03-08 13:37:34,662][670964] Loop inference_proc0-0_evt_loop terminating...
|
394 |
+
[2023-03-08 13:37:34,697][670949] Stopping LearnerWorker_p0...
|
395 |
+
[2023-03-08 13:37:34,697][670949] Loop learner_proc0_evt_loop terminating...
|
396 |
+
[2023-03-08 14:31:27,767][671990] Saving configuration to /home/michal/programming/deep-rl-course/train_dir/default_experiment/config.json...
|
397 |
+
[2023-03-08 14:31:27,768][671990] Rollout worker 0 uses device cpu
|
398 |
+
[2023-03-08 14:31:27,768][671990] Rollout worker 1 uses device cpu
|
399 |
+
[2023-03-08 14:31:27,768][671990] Rollout worker 2 uses device cpu
|
400 |
+
[2023-03-08 14:31:27,768][671990] Rollout worker 3 uses device cpu
|
401 |
+
[2023-03-08 14:31:27,769][671990] Rollout worker 4 uses device cpu
|
402 |
+
[2023-03-08 14:31:27,769][671990] Rollout worker 5 uses device cpu
|
403 |
+
[2023-03-08 14:31:27,769][671990] Rollout worker 6 uses device cpu
|
404 |
+
[2023-03-08 14:31:27,770][671990] Rollout worker 7 uses device cpu
|
405 |
+
[2023-03-08 14:31:27,820][671990] Using GPUs [0] for process 0 (actually maps to GPUs [0])
|
406 |
+
[2023-03-08 14:31:27,821][671990] InferenceWorker_p0-w0: min num requests: 2
|
407 |
+
[2023-03-08 14:31:27,841][671990] Starting all processes...
|
408 |
+
[2023-03-08 14:31:27,842][671990] Starting process learner_proc0
|
409 |
+
[2023-03-08 14:31:27,891][671990] Starting all processes...
|
410 |
+
[2023-03-08 14:31:27,895][671990] Starting process inference_proc0-0
|
411 |
+
[2023-03-08 14:31:27,896][671990] Starting process rollout_proc0
|
412 |
+
[2023-03-08 14:31:27,896][671990] Starting process rollout_proc1
|
413 |
+
[2023-03-08 14:31:27,896][671990] Starting process rollout_proc2
|
414 |
+
[2023-03-08 14:31:27,897][671990] Starting process rollout_proc3
|
415 |
+
[2023-03-08 14:31:27,899][671990] Starting process rollout_proc4
|
416 |
+
[2023-03-08 14:31:27,899][671990] Starting process rollout_proc5
|
417 |
+
[2023-03-08 14:31:27,899][671990] Starting process rollout_proc6
|
418 |
+
[2023-03-08 14:31:27,904][671990] Starting process rollout_proc7
|
419 |
+
[2023-03-08 14:31:28,692][682716] Using GPUs [0] for process 0 (actually maps to GPUs [0])
|
420 |
+
[2023-03-08 14:31:28,692][682716] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for learning process 0
|
421 |
+
[2023-03-08 14:31:28,705][682716] Num visible devices: 1
|
422 |
+
[2023-03-08 14:31:28,732][682716] Starting seed is not provided
|
423 |
+
[2023-03-08 14:31:28,732][682716] Using GPUs [0] for process 0 (actually maps to GPUs [0])
|
424 |
+
[2023-03-08 14:31:28,732][682716] Initializing actor-critic model on device cuda:0
|
425 |
+
[2023-03-08 14:31:28,733][682716] RunningMeanStd input shape: (3, 72, 128)
|
426 |
+
[2023-03-08 14:31:28,733][682716] RunningMeanStd input shape: (1,)
|
427 |
+
[2023-03-08 14:31:28,745][682716] ConvEncoder: input_channels=3
|
428 |
+
[2023-03-08 14:31:28,799][682729] Using GPUs [0] for process 0 (actually maps to GPUs [0])
|
429 |
+
[2023-03-08 14:31:28,799][682729] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for inference process 0
|
430 |
+
[2023-03-08 14:31:28,803][682729] Num visible devices: 1
|
431 |
+
[2023-03-08 14:31:28,820][682747] Worker 3 uses CPU cores [6, 7]
|
432 |
+
[2023-03-08 14:31:28,826][682746] Worker 1 uses CPU cores [2, 3]
|
433 |
+
[2023-03-08 14:31:28,828][682749] Worker 4 uses CPU cores [8, 9]
|
434 |
+
[2023-03-08 14:31:28,829][682730] Worker 0 uses CPU cores [0, 1]
|
435 |
+
[2023-03-08 14:31:28,829][682748] Worker 2 uses CPU cores [4, 5]
|
436 |
+
[2023-03-08 14:31:28,845][682716] Conv encoder output size: 512
|
437 |
+
[2023-03-08 14:31:28,846][682716] Policy head output size: 512
|
438 |
+
[2023-03-08 14:31:28,854][682716] Created Actor Critic model with architecture:
|
439 |
+
[2023-03-08 14:31:28,855][682716] ActorCriticSharedWeights(
|
440 |
+
(obs_normalizer): ObservationNormalizer(
|
441 |
+
(running_mean_std): RunningMeanStdDictInPlace(
|
442 |
+
(running_mean_std): ModuleDict(
|
443 |
+
(obs): RunningMeanStdInPlace()
|
444 |
+
)
|
445 |
+
)
|
446 |
+
)
|
447 |
+
(returns_normalizer): RecursiveScriptModule(original_name=RunningMeanStdInPlace)
|
448 |
+
(encoder): VizdoomEncoder(
|
449 |
+
(basic_encoder): ConvEncoder(
|
450 |
+
(enc): RecursiveScriptModule(
|
451 |
+
original_name=ConvEncoderImpl
|
452 |
+
(conv_head): RecursiveScriptModule(
|
453 |
+
original_name=Sequential
|
454 |
+
(0): RecursiveScriptModule(original_name=Conv2d)
|
455 |
+
(1): RecursiveScriptModule(original_name=ELU)
|
456 |
+
(2): RecursiveScriptModule(original_name=Conv2d)
|
457 |
+
(3): RecursiveScriptModule(original_name=ELU)
|
458 |
+
(4): RecursiveScriptModule(original_name=Conv2d)
|
459 |
+
(5): RecursiveScriptModule(original_name=ELU)
|
460 |
+
)
|
461 |
+
(mlp_layers): RecursiveScriptModule(
|
462 |
+
original_name=Sequential
|
463 |
+
(0): RecursiveScriptModule(original_name=Linear)
|
464 |
+
(1): RecursiveScriptModule(original_name=ELU)
|
465 |
+
)
|
466 |
+
)
|
467 |
+
)
|
468 |
+
)
|
469 |
+
(core): ModelCoreRNN(
|
470 |
+
(core): GRU(512, 512)
|
471 |
+
)
|
472 |
+
(decoder): MlpDecoder(
|
473 |
+
(mlp): Identity()
|
474 |
+
)
|
475 |
+
(critic_linear): Linear(in_features=512, out_features=1, bias=True)
|
476 |
+
(action_parameterization): ActionParameterizationDefault(
|
477 |
+
(distribution_linear): Linear(in_features=512, out_features=5, bias=True)
|
478 |
+
)
|
479 |
+
)
|
480 |
+
[2023-03-08 14:31:28,857][682752] Worker 7 uses CPU cores [14, 15]
|
481 |
+
[2023-03-08 14:31:28,878][682751] Worker 6 uses CPU cores [12, 13]
|
482 |
+
[2023-03-08 14:31:28,925][682750] Worker 5 uses CPU cores [10, 11]
|
483 |
+
[2023-03-08 14:31:29,909][682716] Using optimizer <class 'torch.optim.adam.Adam'>
|
484 |
+
[2023-03-08 14:31:29,910][682716] Loading state from checkpoint /home/michal/programming/deep-rl-course/train_dir/default_experiment/checkpoint_p0/checkpoint_000000081_331776.pth...
|
485 |
+
[2023-03-08 14:31:29,925][682716] Loading model from checkpoint
|
486 |
+
[2023-03-08 14:31:29,927][682716] Loaded experiment state at self.train_step=81, self.env_steps=331776
|
487 |
+
[2023-03-08 14:31:29,928][682716] Initialized policy 0 weights for model version 81
|
488 |
+
[2023-03-08 14:31:29,929][682716] LearnerWorker_p0 finished initialization!
|
489 |
+
[2023-03-08 14:31:29,929][682716] Using GPUs [0] for process 0 (actually maps to GPUs [0])
|
490 |
+
[2023-03-08 14:31:29,991][682729] RunningMeanStd input shape: (3, 72, 128)
|
491 |
+
[2023-03-08 14:31:29,992][682729] RunningMeanStd input shape: (1,)
|
492 |
+
[2023-03-08 14:31:29,998][682729] ConvEncoder: input_channels=3
|
493 |
+
[2023-03-08 14:31:30,058][682729] Conv encoder output size: 512
|
494 |
+
[2023-03-08 14:31:30,058][682729] Policy head output size: 512
|
495 |
+
[2023-03-08 14:31:30,993][671990] Inference worker 0-0 is ready!
|
496 |
+
[2023-03-08 14:31:30,994][671990] All inference workers are ready! Signal rollout workers to start!
|
497 |
+
[2023-03-08 14:31:31,028][682747] Doom resolution: 160x120, resize resolution: (128, 72)
|
498 |
+
[2023-03-08 14:31:31,028][682746] Doom resolution: 160x120, resize resolution: (128, 72)
|
499 |
+
[2023-03-08 14:31:31,029][682750] Doom resolution: 160x120, resize resolution: (128, 72)
|
500 |
+
[2023-03-08 14:31:31,029][682752] Doom resolution: 160x120, resize resolution: (128, 72)
|
501 |
+
[2023-03-08 14:31:31,040][682730] Doom resolution: 160x120, resize resolution: (128, 72)
|
502 |
+
[2023-03-08 14:31:31,040][682749] Doom resolution: 160x120, resize resolution: (128, 72)
|
503 |
+
[2023-03-08 14:31:31,040][682751] Doom resolution: 160x120, resize resolution: (128, 72)
|
504 |
+
[2023-03-08 14:31:31,041][682748] Doom resolution: 160x120, resize resolution: (128, 72)
|
505 |
+
[2023-03-08 14:31:31,217][682752] Decorrelating experience for 0 frames...
|
506 |
+
[2023-03-08 14:31:31,218][682748] Decorrelating experience for 0 frames...
|
507 |
+
[2023-03-08 14:31:31,220][682750] Decorrelating experience for 0 frames...
|
508 |
+
[2023-03-08 14:31:31,220][682746] Decorrelating experience for 0 frames...
|
509 |
+
[2023-03-08 14:31:31,345][682746] Decorrelating experience for 32 frames...
|
510 |
+
[2023-03-08 14:31:31,345][682752] Decorrelating experience for 32 frames...
|
511 |
+
[2023-03-08 14:31:31,345][682750] Decorrelating experience for 32 frames...
|
512 |
+
[2023-03-08 14:31:31,351][682751] Decorrelating experience for 0 frames...
|
513 |
+
[2023-03-08 14:31:31,409][682748] Decorrelating experience for 32 frames...
|
514 |
+
[2023-03-08 14:31:31,507][682751] Decorrelating experience for 32 frames...
|
515 |
+
[2023-03-08 14:31:31,508][682750] Decorrelating experience for 64 frames...
|
516 |
+
[2023-03-08 14:31:31,553][682747] Decorrelating experience for 0 frames...
|
517 |
+
[2023-03-08 14:31:31,563][682752] Decorrelating experience for 64 frames...
|
518 |
+
[2023-03-08 14:31:31,568][682746] Decorrelating experience for 64 frames...
|
519 |
+
[2023-03-08 14:31:31,661][682751] Decorrelating experience for 64 frames...
|
520 |
+
[2023-03-08 14:31:31,710][682752] Decorrelating experience for 96 frames...
|
521 |
+
[2023-03-08 14:31:31,710][682730] Decorrelating experience for 0 frames...
|
522 |
+
[2023-03-08 14:31:31,711][682750] Decorrelating experience for 96 frames...
|
523 |
+
[2023-03-08 14:31:31,725][682746] Decorrelating experience for 96 frames...
|
524 |
+
[2023-03-08 14:31:31,800][671990] Fps is (10 sec: nan, 60 sec: nan, 300 sec: nan). Total num frames: 331776. Throughput: 0: nan. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0)
|
525 |
+
[2023-03-08 14:31:31,830][682751] Decorrelating experience for 96 frames...
|
526 |
+
[2023-03-08 14:31:31,864][682749] Decorrelating experience for 0 frames...
|
527 |
+
[2023-03-08 14:31:31,866][682747] Decorrelating experience for 32 frames...
|
528 |
+
[2023-03-08 14:31:32,054][682747] Decorrelating experience for 64 frames...
|
529 |
+
[2023-03-08 14:31:32,072][682730] Decorrelating experience for 32 frames...
|
530 |
+
[2023-03-08 14:31:32,077][682749] Decorrelating experience for 32 frames...
|
531 |
+
[2023-03-08 14:31:32,211][682716] Signal inference workers to stop experience collection...
|
532 |
+
[2023-03-08 14:31:32,214][682729] InferenceWorker_p0-w0: stopping experience collection
|
533 |
+
[2023-03-08 14:31:32,246][682747] Decorrelating experience for 96 frames...
|
534 |
+
[2023-03-08 14:31:32,253][682730] Decorrelating experience for 64 frames...
|
535 |
+
[2023-03-08 14:31:32,256][682749] Decorrelating experience for 64 frames...
|
536 |
+
[2023-03-08 14:31:32,286][682748] Decorrelating experience for 64 frames...
|
537 |
+
[2023-03-08 14:31:32,372][682716] Signal inference workers to resume experience collection...
|
538 |
+
[2023-03-08 14:31:32,372][682729] InferenceWorker_p0-w0: resuming experience collection
|
539 |
+
[2023-03-08 14:31:32,434][682748] Decorrelating experience for 96 frames...
|
540 |
+
[2023-03-08 14:31:32,453][682749] Decorrelating experience for 96 frames...
|
541 |
+
[2023-03-08 14:31:32,454][682730] Decorrelating experience for 96 frames...
|
542 |
+
[2023-03-08 14:31:33,655][682729] Updated weights for policy 0, policy_version 91 (0.0140)
|
543 |
+
[2023-03-08 14:31:34,792][682729] Updated weights for policy 0, policy_version 101 (0.0005)
|
544 |
+
[2023-03-08 14:31:35,898][682729] Updated weights for policy 0, policy_version 111 (0.0005)
|
545 |
+
[2023-03-08 14:31:36,800][671990] Fps is (10 sec: 31129.4, 60 sec: 31129.4, 300 sec: 31129.4). Total num frames: 487424. Throughput: 0: 2831.6. Samples: 14158. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
|
546 |
+
[2023-03-08 14:31:36,801][671990] Avg episode reward: [(0, '4.411')]
|
547 |
+
[2023-03-08 14:31:36,994][682729] Updated weights for policy 0, policy_version 121 (0.0006)
|
548 |
+
[2023-03-08 14:31:38,163][682729] Updated weights for policy 0, policy_version 131 (0.0006)
|
549 |
+
[2023-03-08 14:31:39,276][682729] Updated weights for policy 0, policy_version 141 (0.0006)
|
550 |
+
[2023-03-08 14:31:40,399][682729] Updated weights for policy 0, policy_version 151 (0.0005)
|
551 |
+
[2023-03-08 14:31:41,488][682729] Updated weights for policy 0, policy_version 161 (0.0006)
|
552 |
+
[2023-03-08 14:31:41,800][671990] Fps is (10 sec: 33587.2, 60 sec: 33587.2, 300 sec: 33587.2). Total num frames: 667648. Throughput: 0: 6863.0. Samples: 68630. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
|
553 |
+
[2023-03-08 14:31:41,801][671990] Avg episode reward: [(0, '4.328')]
|
554 |
+
[2023-03-08 14:31:42,632][682729] Updated weights for policy 0, policy_version 171 (0.0006)
|
555 |
+
[2023-03-08 14:31:43,767][682729] Updated weights for policy 0, policy_version 181 (0.0006)
|
556 |
+
[2023-03-08 14:31:44,894][682729] Updated weights for policy 0, policy_version 191 (0.0005)
|
557 |
+
[2023-03-08 14:31:46,000][682729] Updated weights for policy 0, policy_version 201 (0.0006)
|
558 |
+
[2023-03-08 14:31:46,800][671990] Fps is (10 sec: 36454.3, 60 sec: 34679.3, 300 sec: 34679.3). Total num frames: 851968. Throughput: 0: 8238.5. Samples: 123578. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
|
559 |
+
[2023-03-08 14:31:46,801][671990] Avg episode reward: [(0, '4.684')]
|
560 |
+
[2023-03-08 14:31:46,804][682716] Saving new best policy, reward=4.684!
|
561 |
+
[2023-03-08 14:31:47,159][682729] Updated weights for policy 0, policy_version 211 (0.0006)
|
562 |
+
[2023-03-08 14:31:47,814][671990] Heartbeat connected on Batcher_0
|
563 |
+
[2023-03-08 14:31:47,824][671990] Heartbeat connected on InferenceWorker_p0-w0
|
564 |
+
[2023-03-08 14:31:47,825][671990] Heartbeat connected on RolloutWorker_w0
|
565 |
+
[2023-03-08 14:31:47,828][671990] Heartbeat connected on RolloutWorker_w1
|
566 |
+
[2023-03-08 14:31:47,830][671990] Heartbeat connected on RolloutWorker_w2
|
567 |
+
[2023-03-08 14:31:47,832][671990] Heartbeat connected on RolloutWorker_w3
|
568 |
+
[2023-03-08 14:31:47,835][671990] Heartbeat connected on RolloutWorker_w4
|
569 |
+
[2023-03-08 14:31:47,837][671990] Heartbeat connected on RolloutWorker_w5
|
570 |
+
[2023-03-08 14:31:47,839][671990] Heartbeat connected on RolloutWorker_w6
|
571 |
+
[2023-03-08 14:31:47,840][671990] Heartbeat connected on LearnerWorker_p0
|
572 |
+
[2023-03-08 14:31:47,845][671990] Heartbeat connected on RolloutWorker_w7
|
573 |
+
[2023-03-08 14:31:48,287][682729] Updated weights for policy 0, policy_version 221 (0.0006)
|
574 |
+
[2023-03-08 14:31:49,409][682729] Updated weights for policy 0, policy_version 231 (0.0006)
|
575 |
+
[2023-03-08 14:31:50,502][682729] Updated weights for policy 0, policy_version 241 (0.0005)
|
576 |
+
[2023-03-08 14:31:51,642][682729] Updated weights for policy 0, policy_version 251 (0.0005)
|
577 |
+
[2023-03-08 14:31:51,800][671990] Fps is (10 sec: 36453.9, 60 sec: 35020.6, 300 sec: 35020.6). Total num frames: 1032192. Throughput: 0: 7529.3. Samples: 150588. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
|
578 |
+
[2023-03-08 14:31:51,801][671990] Avg episode reward: [(0, '4.603')]
|
579 |
+
[2023-03-08 14:31:52,750][682729] Updated weights for policy 0, policy_version 261 (0.0006)
|
580 |
+
[2023-03-08 14:31:53,928][682729] Updated weights for policy 0, policy_version 271 (0.0005)
|
581 |
+
[2023-03-08 14:31:55,044][682729] Updated weights for policy 0, policy_version 281 (0.0006)
|
582 |
+
[2023-03-08 14:31:56,141][682729] Updated weights for policy 0, policy_version 291 (0.0006)
|
583 |
+
[2023-03-08 14:31:56,800][671990] Fps is (10 sec: 36044.9, 60 sec: 35225.5, 300 sec: 35225.5). Total num frames: 1212416. Throughput: 0: 8215.5. Samples: 205388. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
|
584 |
+
[2023-03-08 14:31:56,801][671990] Avg episode reward: [(0, '4.862')]
|
585 |
+
[2023-03-08 14:31:56,808][682716] Saving new best policy, reward=4.862!
|
586 |
+
[2023-03-08 14:31:57,261][682729] Updated weights for policy 0, policy_version 301 (0.0006)
|
587 |
+
[2023-03-08 14:31:58,382][682729] Updated weights for policy 0, policy_version 311 (0.0005)
|
588 |
+
[2023-03-08 14:31:59,477][682729] Updated weights for policy 0, policy_version 321 (0.0005)
|
589 |
+
[2023-03-08 14:32:00,577][682729] Updated weights for policy 0, policy_version 331 (0.0006)
|
590 |
+
[2023-03-08 14:32:01,700][682729] Updated weights for policy 0, policy_version 341 (0.0005)
|
591 |
+
[2023-03-08 14:32:01,800][671990] Fps is (10 sec: 36454.7, 60 sec: 35498.6, 300 sec: 35498.6). Total num frames: 1396736. Throughput: 0: 8691.4. Samples: 260742. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
|
592 |
+
[2023-03-08 14:32:01,802][671990] Avg episode reward: [(0, '5.818')]
|
593 |
+
[2023-03-08 14:32:01,815][682716] Saving new best policy, reward=5.818!
|
594 |
+
[2023-03-08 14:32:02,784][682729] Updated weights for policy 0, policy_version 351 (0.0006)
|
595 |
+
[2023-03-08 14:32:03,870][682729] Updated weights for policy 0, policy_version 361 (0.0006)
|
596 |
+
[2023-03-08 14:32:04,975][682729] Updated weights for policy 0, policy_version 371 (0.0006)
|
597 |
+
[2023-03-08 14:32:06,069][682729] Updated weights for policy 0, policy_version 381 (0.0005)
|
598 |
+
[2023-03-08 14:32:06,800][671990] Fps is (10 sec: 37273.5, 60 sec: 35810.7, 300 sec: 35810.7). Total num frames: 1585152. Throughput: 0: 8248.6. Samples: 288702. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
|
599 |
+
[2023-03-08 14:32:06,801][671990] Avg episode reward: [(0, '6.887')]
|
600 |
+
[2023-03-08 14:32:06,819][682716] Saving new best policy, reward=6.887!
|
601 |
+
[2023-03-08 14:32:07,149][682729] Updated weights for policy 0, policy_version 391 (0.0006)
|
602 |
+
[2023-03-08 14:32:08,242][682729] Updated weights for policy 0, policy_version 401 (0.0006)
|
603 |
+
[2023-03-08 14:32:09,314][682729] Updated weights for policy 0, policy_version 411 (0.0005)
|
604 |
+
[2023-03-08 14:32:10,390][682729] Updated weights for policy 0, policy_version 421 (0.0005)
|
605 |
+
[2023-03-08 14:32:11,471][682729] Updated weights for policy 0, policy_version 431 (0.0005)
|
606 |
+
[2023-03-08 14:32:11,800][671990] Fps is (10 sec: 37683.4, 60 sec: 36044.8, 300 sec: 36044.8). Total num frames: 1773568. Throughput: 0: 8632.1. Samples: 345284. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
|
607 |
+
[2023-03-08 14:32:11,801][671990] Avg episode reward: [(0, '8.134')]
|
608 |
+
[2023-03-08 14:32:11,808][682716] Saving new best policy, reward=8.134!
|
609 |
+
[2023-03-08 14:32:12,592][682729] Updated weights for policy 0, policy_version 441 (0.0005)
|
610 |
+
[2023-03-08 14:32:13,668][682729] Updated weights for policy 0, policy_version 451 (0.0006)
|
611 |
+
[2023-03-08 14:32:14,758][682729] Updated weights for policy 0, policy_version 461 (0.0006)
|
612 |
+
[2023-03-08 14:32:15,855][682729] Updated weights for policy 0, policy_version 471 (0.0006)
|
613 |
+
[2023-03-08 14:32:16,800][671990] Fps is (10 sec: 37683.3, 60 sec: 36226.8, 300 sec: 36226.8). Total num frames: 1961984. Throughput: 0: 8923.7. Samples: 401566. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
|
614 |
+
[2023-03-08 14:32:16,801][671990] Avg episode reward: [(0, '10.635')]
|
615 |
+
[2023-03-08 14:32:16,829][682716] Saving new best policy, reward=10.635!
|
616 |
+
[2023-03-08 14:32:16,956][682729] Updated weights for policy 0, policy_version 481 (0.0006)
|
617 |
+
[2023-03-08 14:32:18,149][682729] Updated weights for policy 0, policy_version 491 (0.0006)
|
618 |
+
[2023-03-08 14:32:19,411][682729] Updated weights for policy 0, policy_version 501 (0.0006)
|
619 |
+
[2023-03-08 14:32:20,531][682729] Updated weights for policy 0, policy_version 511 (0.0005)
|
620 |
+
[2023-03-08 14:32:21,649][682729] Updated weights for policy 0, policy_version 521 (0.0005)
|
621 |
+
[2023-03-08 14:32:21,800][671990] Fps is (10 sec: 36454.4, 60 sec: 36126.7, 300 sec: 36126.7). Total num frames: 2138112. Throughput: 0: 9176.1. Samples: 427084. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
|
622 |
+
[2023-03-08 14:32:21,801][671990] Avg episode reward: [(0, '14.048')]
|
623 |
+
[2023-03-08 14:32:21,802][682716] Saving new best policy, reward=14.048!
|
624 |
+
[2023-03-08 14:32:22,938][682729] Updated weights for policy 0, policy_version 531 (0.0006)
|
625 |
+
[2023-03-08 14:32:24,157][682729] Updated weights for policy 0, policy_version 541 (0.0006)
|
626 |
+
[2023-03-08 14:32:25,360][682729] Updated weights for policy 0, policy_version 551 (0.0006)
|
627 |
+
[2023-03-08 14:32:26,488][682729] Updated weights for policy 0, policy_version 561 (0.0006)
|
628 |
+
[2023-03-08 14:32:26,800][671990] Fps is (10 sec: 34406.1, 60 sec: 35895.8, 300 sec: 35895.8). Total num frames: 2306048. Throughput: 0: 9121.2. Samples: 479086. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
|
629 |
+
[2023-03-08 14:32:26,801][671990] Avg episode reward: [(0, '14.162')]
|
630 |
+
[2023-03-08 14:32:26,805][682716] Saving new best policy, reward=14.162!
|
631 |
+
[2023-03-08 14:32:27,751][682729] Updated weights for policy 0, policy_version 571 (0.0006)
|
632 |
+
[2023-03-08 14:32:29,007][682729] Updated weights for policy 0, policy_version 581 (0.0005)
|
633 |
+
[2023-03-08 14:32:30,571][682729] Updated weights for policy 0, policy_version 591 (0.0007)
|
634 |
+
[2023-03-08 14:32:31,800][671990] Fps is (10 sec: 31538.7, 60 sec: 35362.1, 300 sec: 35362.1). Total num frames: 2453504. Throughput: 0: 8947.1. Samples: 526198. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
|
635 |
+
[2023-03-08 14:32:31,801][671990] Avg episode reward: [(0, '19.425')]
|
636 |
+
[2023-03-08 14:32:31,803][682716] Saving new best policy, reward=19.425!
|
637 |
+
[2023-03-08 14:32:32,014][682729] Updated weights for policy 0, policy_version 601 (0.0006)
|
638 |
+
[2023-03-08 14:32:33,354][682729] Updated weights for policy 0, policy_version 611 (0.0006)
|
639 |
+
[2023-03-08 14:32:34,646][682729] Updated weights for policy 0, policy_version 621 (0.0006)
|
640 |
+
[2023-03-08 14:32:35,933][682729] Updated weights for policy 0, policy_version 631 (0.0006)
|
641 |
+
[2023-03-08 14:32:36,800][671990] Fps is (10 sec: 30720.3, 60 sec: 35430.4, 300 sec: 35099.6). Total num frames: 2613248. Throughput: 0: 8840.9. Samples: 548426. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
|
642 |
+
[2023-03-08 14:32:36,802][671990] Avg episode reward: [(0, '16.826')]
|
643 |
+
[2023-03-08 14:32:37,081][682729] Updated weights for policy 0, policy_version 641 (0.0006)
|
644 |
+
[2023-03-08 14:32:38,247][682729] Updated weights for policy 0, policy_version 651 (0.0006)
|
645 |
+
[2023-03-08 14:32:39,376][682729] Updated weights for policy 0, policy_version 661 (0.0006)
|
646 |
+
[2023-03-08 14:32:40,533][682729] Updated weights for policy 0, policy_version 671 (0.0006)
|
647 |
+
[2023-03-08 14:32:41,800][671990] Fps is (10 sec: 33177.9, 60 sec: 35293.8, 300 sec: 35050.0). Total num frames: 2785280. Throughput: 0: 8779.0. Samples: 600442. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
|
648 |
+
[2023-03-08 14:32:41,802][671990] Avg episode reward: [(0, '17.019')]
|
649 |
+
[2023-03-08 14:32:41,871][682729] Updated weights for policy 0, policy_version 681 (0.0006)
|
650 |
+
[2023-03-08 14:32:43,289][682729] Updated weights for policy 0, policy_version 691 (0.0006)
|
651 |
+
[2023-03-08 14:32:44,689][682729] Updated weights for policy 0, policy_version 701 (0.0006)
|
652 |
+
[2023-03-08 14:32:45,913][682729] Updated weights for policy 0, policy_version 711 (0.0006)
|
653 |
+
[2023-03-08 14:32:46,800][671990] Fps is (10 sec: 32358.4, 60 sec: 34747.8, 300 sec: 34734.1). Total num frames: 2936832. Throughput: 0: 8576.5. Samples: 646684. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
|
654 |
+
[2023-03-08 14:32:46,801][671990] Avg episode reward: [(0, '22.064')]
|
655 |
+
[2023-03-08 14:32:46,804][682716] Saving new best policy, reward=22.064!
|
656 |
+
[2023-03-08 14:32:47,146][682729] Updated weights for policy 0, policy_version 721 (0.0006)
|
657 |
+
[2023-03-08 14:32:48,272][682729] Updated weights for policy 0, policy_version 731 (0.0006)
|
658 |
+
[2023-03-08 14:32:49,718][682729] Updated weights for policy 0, policy_version 741 (0.0006)
|
659 |
+
[2023-03-08 14:32:50,891][682729] Updated weights for policy 0, policy_version 751 (0.0006)
|
660 |
+
[2023-03-08 14:32:51,800][671990] Fps is (10 sec: 31948.6, 60 sec: 34543.0, 300 sec: 34662.4). Total num frames: 3104768. Throughput: 0: 8507.7. Samples: 671550. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
|
661 |
+
[2023-03-08 14:32:51,801][671990] Avg episode reward: [(0, '18.601')]
|
662 |
+
[2023-03-08 14:32:52,025][682729] Updated weights for policy 0, policy_version 761 (0.0006)
|
663 |
+
[2023-03-08 14:32:53,121][682729] Updated weights for policy 0, policy_version 771 (0.0005)
|
664 |
+
[2023-03-08 14:32:54,273][682729] Updated weights for policy 0, policy_version 781 (0.0006)
|
665 |
+
[2023-03-08 14:32:55,412][682729] Updated weights for policy 0, policy_version 791 (0.0006)
|
666 |
+
[2023-03-08 14:32:56,591][682729] Updated weights for policy 0, policy_version 801 (0.0006)
|
667 |
+
[2023-03-08 14:32:56,800][671990] Fps is (10 sec: 34816.0, 60 sec: 34542.9, 300 sec: 34743.7). Total num frames: 3284992. Throughput: 0: 8419.5. Samples: 724162. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
|
668 |
+
[2023-03-08 14:32:56,801][671990] Avg episode reward: [(0, '19.367')]
|
669 |
+
[2023-03-08 14:32:57,697][682729] Updated weights for policy 0, policy_version 811 (0.0006)
|
670 |
+
[2023-03-08 14:32:58,813][682729] Updated weights for policy 0, policy_version 821 (0.0006)
|
671 |
+
[2023-03-08 14:32:59,899][682729] Updated weights for policy 0, policy_version 831 (0.0006)
|
672 |
+
[2023-03-08 14:33:00,985][682729] Updated weights for policy 0, policy_version 841 (0.0005)
|
673 |
+
[2023-03-08 14:33:01,800][671990] Fps is (10 sec: 36864.3, 60 sec: 34611.2, 300 sec: 34907.0). Total num frames: 3473408. Throughput: 0: 8390.0. Samples: 779116. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
|
674 |
+
[2023-03-08 14:33:01,801][671990] Avg episode reward: [(0, '20.222')]
|
675 |
+
[2023-03-08 14:33:02,102][682729] Updated weights for policy 0, policy_version 851 (0.0006)
|
676 |
+
[2023-03-08 14:33:03,243][682729] Updated weights for policy 0, policy_version 861 (0.0006)
|
677 |
+
[2023-03-08 14:33:04,400][682729] Updated weights for policy 0, policy_version 871 (0.0006)
|
678 |
+
[2023-03-08 14:33:05,506][682729] Updated weights for policy 0, policy_version 881 (0.0005)
|
679 |
+
[2023-03-08 14:33:06,672][682729] Updated weights for policy 0, policy_version 891 (0.0006)
|
680 |
+
[2023-03-08 14:33:06,800][671990] Fps is (10 sec: 36863.6, 60 sec: 34474.6, 300 sec: 34966.9). Total num frames: 3653632. Throughput: 0: 8430.3. Samples: 806450. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
|
681 |
+
[2023-03-08 14:33:06,801][671990] Avg episode reward: [(0, '22.082')]
|
682 |
+
[2023-03-08 14:33:06,805][682716] Saving new best policy, reward=22.082!
|
683 |
+
[2023-03-08 14:33:07,783][682729] Updated weights for policy 0, policy_version 901 (0.0005)
|
684 |
+
[2023-03-08 14:33:08,924][682729] Updated weights for policy 0, policy_version 911 (0.0006)
|
685 |
+
[2023-03-08 14:33:10,055][682729] Updated weights for policy 0, policy_version 921 (0.0005)
|
686 |
+
[2023-03-08 14:33:11,179][682729] Updated weights for policy 0, policy_version 931 (0.0006)
|
687 |
+
[2023-03-08 14:33:11,800][671990] Fps is (10 sec: 36045.0, 60 sec: 34338.2, 300 sec: 35020.8). Total num frames: 3833856. Throughput: 0: 8478.0. Samples: 860594. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0)
|
688 |
+
[2023-03-08 14:33:11,801][671990] Avg episode reward: [(0, '20.605')]
|
689 |
+
[2023-03-08 14:33:12,236][682729] Updated weights for policy 0, policy_version 941 (0.0006)
|
690 |
+
[2023-03-08 14:33:13,344][682729] Updated weights for policy 0, policy_version 951 (0.0005)
|
691 |
+
[2023-03-08 14:33:14,453][682729] Updated weights for policy 0, policy_version 961 (0.0005)
|
692 |
+
[2023-03-08 14:33:15,616][682729] Updated weights for policy 0, policy_version 971 (0.0006)
|
693 |
+
[2023-03-08 14:33:16,402][682716] Stopping Batcher_0...
|
694 |
+
[2023-03-08 14:33:16,402][682716] Loop batcher_evt_loop terminating...
|
695 |
+
[2023-03-08 14:33:16,402][682716] Saving /home/michal/programming/deep-rl-course/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
|
696 |
+
[2023-03-08 14:33:16,402][671990] Component Batcher_0 stopped!
|
697 |
+
[2023-03-08 14:33:16,411][682751] Stopping RolloutWorker_w6...
|
698 |
+
[2023-03-08 14:33:16,411][682747] Stopping RolloutWorker_w3...
|
699 |
+
[2023-03-08 14:33:16,412][682751] Loop rollout_proc6_evt_loop terminating...
|
700 |
+
[2023-03-08 14:33:16,412][682747] Loop rollout_proc3_evt_loop terminating...
|
701 |
+
[2023-03-08 14:33:16,412][682746] Stopping RolloutWorker_w1...
|
702 |
+
[2023-03-08 14:33:16,411][671990] Component RolloutWorker_w6 stopped!
|
703 |
+
[2023-03-08 14:33:16,412][682748] Stopping RolloutWorker_w2...
|
704 |
+
[2023-03-08 14:33:16,413][682746] Loop rollout_proc1_evt_loop terminating...
|
705 |
+
[2023-03-08 14:33:16,413][682748] Loop rollout_proc2_evt_loop terminating...
|
706 |
+
[2023-03-08 14:33:16,413][671990] Component RolloutWorker_w3 stopped!
|
707 |
+
[2023-03-08 14:33:16,414][682750] Stopping RolloutWorker_w5...
|
708 |
+
[2023-03-08 14:33:16,415][682750] Loop rollout_proc5_evt_loop terminating...
|
709 |
+
[2023-03-08 14:33:16,415][682752] Stopping RolloutWorker_w7...
|
710 |
+
[2023-03-08 14:33:16,415][671990] Component RolloutWorker_w1 stopped!
|
711 |
+
[2023-03-08 14:33:16,415][682752] Loop rollout_proc7_evt_loop terminating...
|
712 |
+
[2023-03-08 14:33:16,415][671990] Component RolloutWorker_w2 stopped!
|
713 |
+
[2023-03-08 14:33:16,416][671990] Component RolloutWorker_w5 stopped!
|
714 |
+
[2023-03-08 14:33:16,416][671990] Component RolloutWorker_w7 stopped!
|
715 |
+
[2023-03-08 14:33:16,418][682729] Weights refcount: 2 0
|
716 |
+
[2023-03-08 14:33:16,421][682729] Stopping InferenceWorker_p0-w0...
|
717 |
+
[2023-03-08 14:33:16,421][671990] Component InferenceWorker_p0-w0 stopped!
|
718 |
+
[2023-03-08 14:33:16,422][682729] Loop inference_proc0-0_evt_loop terminating...
|
719 |
+
[2023-03-08 14:33:16,440][682749] Stopping RolloutWorker_w4...
|
720 |
+
[2023-03-08 14:33:16,441][682749] Loop rollout_proc4_evt_loop terminating...
|
721 |
+
[2023-03-08 14:33:16,441][671990] Component RolloutWorker_w4 stopped!
|
722 |
+
[2023-03-08 14:33:16,477][682730] Stopping RolloutWorker_w0...
|
723 |
+
[2023-03-08 14:33:16,478][682730] Loop rollout_proc0_evt_loop terminating...
|
724 |
+
[2023-03-08 14:33:16,477][671990] Component RolloutWorker_w0 stopped!
|
725 |
+
[2023-03-08 14:33:16,493][682716] Saving /home/michal/programming/deep-rl-course/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
|
726 |
+
[2023-03-08 14:33:16,584][682716] Stopping LearnerWorker_p0...
|
727 |
+
[2023-03-08 14:33:16,584][682716] Loop learner_proc0_evt_loop terminating...
|
728 |
+
[2023-03-08 14:33:16,584][671990] Component LearnerWorker_p0 stopped!
|
729 |
+
[2023-03-08 14:33:16,586][671990] Waiting for process learner_proc0 to stop...
|
730 |
+
[2023-03-08 14:33:16,976][671990] Waiting for process inference_proc0-0 to join...
|
731 |
+
[2023-03-08 14:33:16,977][671990] Waiting for process rollout_proc0 to join...
|
732 |
+
[2023-03-08 14:33:16,978][671990] Waiting for process rollout_proc1 to join...
|
733 |
+
[2023-03-08 14:33:16,978][671990] Waiting for process rollout_proc2 to join...
|
734 |
+
[2023-03-08 14:33:16,979][671990] Waiting for process rollout_proc3 to join...
|
735 |
+
[2023-03-08 14:33:16,979][671990] Waiting for process rollout_proc4 to join...
|
736 |
+
[2023-03-08 14:33:16,980][671990] Waiting for process rollout_proc5 to join...
|
737 |
+
[2023-03-08 14:33:16,980][671990] Waiting for process rollout_proc6 to join...
|
738 |
+
[2023-03-08 14:33:16,981][671990] Waiting for process rollout_proc7 to join...
|
739 |
+
[2023-03-08 14:33:16,981][671990] Batcher 0 profile tree view:
|
740 |
+
batching: 10.8707, releasing_batches: 0.0115
|
741 |
+
[2023-03-08 14:33:16,982][671990] InferenceWorker_p0-w0 profile tree view:
|
742 |
+
wait_policy: 0.0000
|
743 |
+
wait_policy_total: 2.2257
|
744 |
+
update_model: 1.3996
|
745 |
+
weight_update: 0.0006
|
746 |
+
one_step: 0.0009
|
747 |
+
handle_policy_step: 96.0541
|
748 |
+
deserialize: 5.3775, stack: 0.4795, obs_to_device_normalize: 29.8978, forward: 30.9313, send_messages: 5.9810
|
749 |
+
prepare_outputs: 19.0649
|
750 |
+
to_cpu: 14.4507
|
751 |
+
[2023-03-08 14:33:16,982][671990] Learner 0 profile tree view:
|
752 |
+
misc: 0.0051, prepare_batch: 6.8415
|
753 |
+
train: 21.3246
|
754 |
+
epoch_init: 0.0031, minibatch_init: 0.0037, losses_postprocess: 0.3033, kl_divergence: 0.1304, after_optimizer: 10.3912
|
755 |
+
calculate_losses: 6.6995
|
756 |
+
losses_init: 0.0019, forward_head: 0.3111, bptt_initial: 4.7548, tail: 0.2907, advantages_returns: 0.0916, losses: 0.6107
|
757 |
+
bptt: 0.5510
|
758 |
+
bptt_forward_core: 0.5280
|
759 |
+
update: 3.5779
|
760 |
+
clip: 0.5862
|
761 |
+
[2023-03-08 14:33:16,983][671990] RolloutWorker_w0 profile tree view:
|
762 |
+
wait_for_trajectories: 0.0811, enqueue_policy_requests: 3.7469, env_step: 59.1615, overhead: 4.0872, complete_rollouts: 0.1260
|
763 |
+
save_policy_outputs: 4.2104
|
764 |
+
split_output_tensors: 2.0489
|
765 |
+
[2023-03-08 14:33:16,983][671990] RolloutWorker_w7 profile tree view:
|
766 |
+
wait_for_trajectories: 0.0810, enqueue_policy_requests: 3.7304, env_step: 59.5087, overhead: 4.1451, complete_rollouts: 0.1230
|
767 |
+
save_policy_outputs: 4.2532
|
768 |
+
split_output_tensors: 2.0561
|
769 |
+
[2023-03-08 14:33:16,984][671990] Loop Runner_EvtLoop terminating...
|
770 |
+
[2023-03-08 14:33:16,984][671990] Runner profile tree view:
|
771 |
+
main_loop: 109.1432
|
772 |
+
[2023-03-08 14:33:16,985][671990] Collected {0: 4005888}, FPS: 33663.2
|
773 |
+
[2023-03-08 14:40:07,216][671990] Loading existing experiment configuration from /home/michal/programming/deep-rl-course/train_dir/default_experiment/config.json
|
774 |
+
[2023-03-08 14:40:07,217][671990] Overriding arg 'num_workers' with value 1 passed from command line
|
775 |
+
[2023-03-08 14:40:07,217][671990] Adding new argument 'no_render'=True that is not in the saved config file!
|
776 |
+
[2023-03-08 14:40:07,217][671990] Adding new argument 'save_video'=True that is not in the saved config file!
|
777 |
+
[2023-03-08 14:40:07,218][671990] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file!
|
778 |
+
[2023-03-08 14:40:07,218][671990] Adding new argument 'video_name'=None that is not in the saved config file!
|
779 |
+
[2023-03-08 14:40:07,218][671990] Adding new argument 'max_num_frames'=1000000000.0 that is not in the saved config file!
|
780 |
+
[2023-03-08 14:40:07,219][671990] Adding new argument 'max_num_episodes'=10 that is not in the saved config file!
|
781 |
+
[2023-03-08 14:40:07,219][671990] Adding new argument 'push_to_hub'=False that is not in the saved config file!
|
782 |
+
[2023-03-08 14:40:07,219][671990] Adding new argument 'hf_repository'=None that is not in the saved config file!
|
783 |
+
[2023-03-08 14:40:07,219][671990] Adding new argument 'policy_index'=0 that is not in the saved config file!
|
784 |
+
[2023-03-08 14:40:07,220][671990] Adding new argument 'eval_deterministic'=False that is not in the saved config file!
|
785 |
+
[2023-03-08 14:40:07,220][671990] Adding new argument 'train_script'=None that is not in the saved config file!
|
786 |
+
[2023-03-08 14:40:07,220][671990] Adding new argument 'enjoy_script'=None that is not in the saved config file!
|
787 |
+
[2023-03-08 14:40:07,221][671990] Using frameskip 1 and render_action_repeat=4 for evaluation
|
788 |
+
[2023-03-08 14:40:07,228][671990] Doom resolution: 160x120, resize resolution: (128, 72)
|
789 |
+
[2023-03-08 14:40:07,229][671990] RunningMeanStd input shape: (3, 72, 128)
|
790 |
+
[2023-03-08 14:40:07,229][671990] RunningMeanStd input shape: (1,)
|
791 |
+
[2023-03-08 14:40:07,237][671990] ConvEncoder: input_channels=3
|
792 |
+
[2023-03-08 14:40:07,303][671990] Conv encoder output size: 512
|
793 |
+
[2023-03-08 14:40:07,304][671990] Policy head output size: 512
|
794 |
+
[2023-03-08 14:40:08,412][671990] Loading state from checkpoint /home/michal/programming/deep-rl-course/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
|
795 |
+
[2023-03-08 14:40:08,706][671990] Num frames 100...
|
796 |
+
[2023-03-08 14:40:08,766][671990] Num frames 200...
|
797 |
+
[2023-03-08 14:40:08,828][671990] Num frames 300...
|
798 |
+
[2023-03-08 14:40:08,891][671990] Num frames 400...
|
799 |
+
[2023-03-08 14:40:08,951][671990] Num frames 500...
|
800 |
+
[2023-03-08 14:40:09,012][671990] Num frames 600...
|
801 |
+
[2023-03-08 14:40:09,071][671990] Num frames 700...
|
802 |
+
[2023-03-08 14:40:09,134][671990] Num frames 800...
|
803 |
+
[2023-03-08 14:40:09,206][671990] Avg episode rewards: #0: 19.320, true rewards: #0: 8.320
|
804 |
+
[2023-03-08 14:40:09,207][671990] Avg episode reward: 19.320, avg true_objective: 8.320
|
805 |
+
[2023-03-08 14:40:09,252][671990] Num frames 900...
|
806 |
+
[2023-03-08 14:40:09,312][671990] Num frames 1000...
|
807 |
+
[2023-03-08 14:40:09,370][671990] Num frames 1100...
|
808 |
+
[2023-03-08 14:40:09,428][671990] Num frames 1200...
|
809 |
+
[2023-03-08 14:40:09,487][671990] Num frames 1300...
|
810 |
+
[2023-03-08 14:40:09,548][671990] Num frames 1400...
|
811 |
+
[2023-03-08 14:40:09,609][671990] Num frames 1500...
|
812 |
+
[2023-03-08 14:40:09,674][671990] Num frames 1600...
|
813 |
+
[2023-03-08 14:40:09,784][671990] Avg episode rewards: #0: 17.480, true rewards: #0: 8.480
|
814 |
+
[2023-03-08 14:40:09,785][671990] Avg episode reward: 17.480, avg true_objective: 8.480
|
815 |
+
[2023-03-08 14:40:09,791][671990] Num frames 1700...
|
816 |
+
[2023-03-08 14:40:09,851][671990] Num frames 1800...
|
817 |
+
[2023-03-08 14:40:09,910][671990] Num frames 1900...
|
818 |
+
[2023-03-08 14:40:09,969][671990] Num frames 2000...
|
819 |
+
[2023-03-08 14:40:10,027][671990] Num frames 2100...
|
820 |
+
[2023-03-08 14:40:10,086][671990] Num frames 2200...
|
821 |
+
[2023-03-08 14:40:10,145][671990] Num frames 2300...
|
822 |
+
[2023-03-08 14:40:10,238][671990] Avg episode rewards: #0: 16.897, true rewards: #0: 7.897
|
823 |
+
[2023-03-08 14:40:10,239][671990] Avg episode reward: 16.897, avg true_objective: 7.897
|
824 |
+
[2023-03-08 14:40:10,263][671990] Num frames 2400...
|
825 |
+
[2023-03-08 14:40:10,322][671990] Num frames 2500...
|
826 |
+
[2023-03-08 14:40:10,381][671990] Num frames 2600...
|
827 |
+
[2023-03-08 14:40:10,444][671990] Num frames 2700...
|
828 |
+
[2023-03-08 14:40:10,505][671990] Num frames 2800...
|
829 |
+
[2023-03-08 14:40:10,565][671990] Num frames 2900...
|
830 |
+
[2023-03-08 14:40:10,627][671990] Num frames 3000...
|
831 |
+
[2023-03-08 14:40:10,722][671990] Avg episode rewards: #0: 15.433, true rewards: #0: 7.682
|
832 |
+
[2023-03-08 14:40:10,723][671990] Avg episode reward: 15.433, avg true_objective: 7.682
|
833 |
+
[2023-03-08 14:40:10,743][671990] Num frames 3100...
|
834 |
+
[2023-03-08 14:40:10,802][671990] Num frames 3200...
|
835 |
+
[2023-03-08 14:40:10,862][671990] Num frames 3300...
|
836 |
+
[2023-03-08 14:40:10,920][671990] Num frames 3400...
|
837 |
+
[2023-03-08 14:40:10,979][671990] Num frames 3500...
|
838 |
+
[2023-03-08 14:40:11,041][671990] Num frames 3600...
|
839 |
+
[2023-03-08 14:40:11,103][671990] Num frames 3700...
|
840 |
+
[2023-03-08 14:40:11,161][671990] Num frames 3800...
|
841 |
+
[2023-03-08 14:40:11,227][671990] Num frames 3900...
|
842 |
+
[2023-03-08 14:40:11,287][671990] Num frames 4000...
|
843 |
+
[2023-03-08 14:40:11,350][671990] Num frames 4100...
|
844 |
+
[2023-03-08 14:40:11,411][671990] Num frames 4200...
|
845 |
+
[2023-03-08 14:40:11,469][671990] Num frames 4300...
|
846 |
+
[2023-03-08 14:40:11,531][671990] Num frames 4400...
|
847 |
+
[2023-03-08 14:40:11,596][671990] Num frames 4500...
|
848 |
+
[2023-03-08 14:40:11,655][671990] Num frames 4600...
|
849 |
+
[2023-03-08 14:40:11,715][671990] Num frames 4700...
|
850 |
+
[2023-03-08 14:40:11,775][671990] Num frames 4800...
|
851 |
+
[2023-03-08 14:40:11,835][671990] Num frames 4900...
|
852 |
+
[2023-03-08 14:40:11,896][671990] Num frames 5000...
|
853 |
+
[2023-03-08 14:40:11,957][671990] Num frames 5100...
|
854 |
+
[2023-03-08 14:40:12,056][671990] Avg episode rewards: #0: 23.346, true rewards: #0: 10.346
|
855 |
+
[2023-03-08 14:40:12,056][671990] Avg episode reward: 23.346, avg true_objective: 10.346
|
856 |
+
[2023-03-08 14:40:12,079][671990] Num frames 5200...
|
857 |
+
[2023-03-08 14:40:12,143][671990] Num frames 5300...
|
858 |
+
[2023-03-08 14:40:12,204][671990] Num frames 5400...
|
859 |
+
[2023-03-08 14:40:12,265][671990] Num frames 5500...
|
860 |
+
[2023-03-08 14:40:12,324][671990] Num frames 5600...
|
861 |
+
[2023-03-08 14:40:12,383][671990] Num frames 5700...
|
862 |
+
[2023-03-08 14:40:12,442][671990] Num frames 5800...
|
863 |
+
[2023-03-08 14:40:12,502][671990] Num frames 5900...
|
864 |
+
[2023-03-08 14:40:12,563][671990] Num frames 6000...
|
865 |
+
[2023-03-08 14:40:12,624][671990] Num frames 6100...
|
866 |
+
[2023-03-08 14:40:12,685][671990] Num frames 6200...
|
867 |
+
[2023-03-08 14:40:12,747][671990] Num frames 6300...
|
868 |
+
[2023-03-08 14:40:12,845][671990] Avg episode rewards: #0: 24.122, true rewards: #0: 10.622
|
869 |
+
[2023-03-08 14:40:12,846][671990] Avg episode reward: 24.122, avg true_objective: 10.622
|
870 |
+
[2023-03-08 14:40:12,867][671990] Num frames 6400...
|
871 |
+
[2023-03-08 14:40:12,933][671990] Num frames 6500...
|
872 |
+
[2023-03-08 14:40:13,000][671990] Num frames 6600...
|
873 |
+
[2023-03-08 14:40:13,059][671990] Num frames 6700...
|
874 |
+
[2023-03-08 14:40:13,122][671990] Num frames 6800...
|
875 |
+
[2023-03-08 14:40:13,182][671990] Num frames 6900...
|
876 |
+
[2023-03-08 14:40:13,241][671990] Num frames 7000...
|
877 |
+
[2023-03-08 14:40:13,302][671990] Num frames 7100...
|
878 |
+
[2023-03-08 14:40:13,361][671990] Num frames 7200...
|
879 |
+
[2023-03-08 14:40:13,422][671990] Num frames 7300...
|
880 |
+
[2023-03-08 14:40:13,484][671990] Num frames 7400...
|
881 |
+
[2023-03-08 14:40:13,556][671990] Avg episode rewards: #0: 23.613, true rewards: #0: 10.613
|
882 |
+
[2023-03-08 14:40:13,557][671990] Avg episode reward: 23.613, avg true_objective: 10.613
|
883 |
+
[2023-03-08 14:40:13,604][671990] Num frames 7500...
|
884 |
+
[2023-03-08 14:40:13,664][671990] Num frames 7600...
|
885 |
+
[2023-03-08 14:40:13,723][671990] Num frames 7700...
|
886 |
+
[2023-03-08 14:40:13,782][671990] Num frames 7800...
|
887 |
+
[2023-03-08 14:40:13,841][671990] Num frames 7900...
|
888 |
+
[2023-03-08 14:40:13,901][671990] Num frames 8000...
|
889 |
+
[2023-03-08 14:40:13,960][671990] Num frames 8100...
|
890 |
+
[2023-03-08 14:40:14,019][671990] Num frames 8200...
|
891 |
+
[2023-03-08 14:40:14,079][671990] Num frames 8300...
|
892 |
+
[2023-03-08 14:40:14,139][671990] Num frames 8400...
|
893 |
+
[2023-03-08 14:40:14,201][671990] Num frames 8500...
|
894 |
+
[2023-03-08 14:40:14,261][671990] Num frames 8600...
|
895 |
+
[2023-03-08 14:40:14,322][671990] Num frames 8700...
|
896 |
+
[2023-03-08 14:40:14,410][671990] Avg episode rewards: #0: 24.446, true rewards: #0: 10.946
|
897 |
+
[2023-03-08 14:40:14,411][671990] Avg episode reward: 24.446, avg true_objective: 10.946
|
898 |
+
[2023-03-08 14:40:14,439][671990] Num frames 8800...
|
899 |
+
[2023-03-08 14:40:14,499][671990] Num frames 8900...
|
900 |
+
[2023-03-08 14:40:14,559][671990] Num frames 9000...
|
901 |
+
[2023-03-08 14:40:14,618][671990] Num frames 9100...
|
902 |
+
[2023-03-08 14:40:14,678][671990] Num frames 9200...
|
903 |
+
[2023-03-08 14:40:14,737][671990] Num frames 9300...
|
904 |
+
[2023-03-08 14:40:14,796][671990] Num frames 9400...
|
905 |
+
[2023-03-08 14:40:14,856][671990] Num frames 9500...
|
906 |
+
[2023-03-08 14:40:14,916][671990] Num frames 9600...
|
907 |
+
[2023-03-08 14:40:14,976][671990] Num frames 9700...
|
908 |
+
[2023-03-08 14:40:15,039][671990] Num frames 9800...
|
909 |
+
[2023-03-08 14:40:15,099][671990] Num frames 9900...
|
910 |
+
[2023-03-08 14:40:15,161][671990] Num frames 10000...
|
911 |
+
[2023-03-08 14:40:15,237][671990] Avg episode rewards: #0: 24.819, true rewards: #0: 11.152
|
912 |
+
[2023-03-08 14:40:15,238][671990] Avg episode reward: 24.819, avg true_objective: 11.152
|
913 |
+
[2023-03-08 14:40:15,277][671990] Num frames 10100...
|
914 |
+
[2023-03-08 14:40:15,336][671990] Num frames 10200...
|
915 |
+
[2023-03-08 14:40:15,397][671990] Num frames 10300...
|
916 |
+
[2023-03-08 14:40:15,460][671990] Num frames 10400...
|
917 |
+
[2023-03-08 14:40:15,520][671990] Num frames 10500...
|
918 |
+
[2023-03-08 14:40:15,581][671990] Num frames 10600...
|
919 |
+
[2023-03-08 14:40:15,641][671990] Num frames 10700...
|
920 |
+
[2023-03-08 14:40:15,738][671990] Avg episode rewards: #0: 23.873, true rewards: #0: 10.773
|
921 |
+
[2023-03-08 14:40:15,739][671990] Avg episode reward: 23.873, avg true_objective: 10.773
|
922 |
+
[2023-03-08 14:40:26,813][671990] Replay video saved to /home/michal/programming/deep-rl-course/train_dir/default_experiment/replay.mp4!
|
923 |
+
[2023-03-08 14:41:24,935][671990] Loading existing experiment configuration from /home/michal/programming/deep-rl-course/train_dir/default_experiment/config.json
|
924 |
+
[2023-03-08 14:41:24,936][671990] Overriding arg 'num_workers' with value 1 passed from command line
|
925 |
+
[2023-03-08 14:41:24,936][671990] Adding new argument 'no_render'=True that is not in the saved config file!
|
926 |
+
[2023-03-08 14:41:24,936][671990] Adding new argument 'save_video'=True that is not in the saved config file!
|
927 |
+
[2023-03-08 14:41:24,937][671990] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file!
|
928 |
+
[2023-03-08 14:41:24,937][671990] Adding new argument 'video_name'=None that is not in the saved config file!
|
929 |
+
[2023-03-08 14:41:24,937][671990] Adding new argument 'max_num_frames'=100000 that is not in the saved config file!
|
930 |
+
[2023-03-08 14:41:24,938][671990] Adding new argument 'max_num_episodes'=10 that is not in the saved config file!
|
931 |
+
[2023-03-08 14:41:24,938][671990] Adding new argument 'push_to_hub'=True that is not in the saved config file!
|
932 |
+
[2023-03-08 14:41:24,938][671990] Adding new argument 'hf_repository'='michal512/rl_course_vizdoom_health_gathering_supreme' that is not in the saved config file!
|
933 |
+
[2023-03-08 14:41:24,939][671990] Adding new argument 'policy_index'=0 that is not in the saved config file!
|
934 |
+
[2023-03-08 14:41:24,939][671990] Adding new argument 'eval_deterministic'=False that is not in the saved config file!
|
935 |
+
[2023-03-08 14:41:24,940][671990] Adding new argument 'train_script'=None that is not in the saved config file!
|
936 |
+
[2023-03-08 14:41:24,941][671990] Adding new argument 'enjoy_script'=None that is not in the saved config file!
|
937 |
+
[2023-03-08 14:41:24,941][671990] Using frameskip 1 and render_action_repeat=4 for evaluation
|
938 |
+
[2023-03-08 14:41:24,948][671990] RunningMeanStd input shape: (3, 72, 128)
|
939 |
+
[2023-03-08 14:41:24,949][671990] RunningMeanStd input shape: (1,)
|
940 |
+
[2023-03-08 14:41:24,955][671990] ConvEncoder: input_channels=3
|
941 |
+
[2023-03-08 14:41:24,972][671990] Conv encoder output size: 512
|
942 |
+
[2023-03-08 14:41:24,972][671990] Policy head output size: 512
|
943 |
+
[2023-03-08 14:41:24,997][671990] Loading state from checkpoint /home/michal/programming/deep-rl-course/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
|
944 |
+
[2023-03-08 14:41:25,284][671990] Num frames 100...
|
945 |
+
[2023-03-08 14:41:25,343][671990] Num frames 200...
|
946 |
+
[2023-03-08 14:41:25,400][671990] Num frames 300...
|
947 |
+
[2023-03-08 14:41:25,463][671990] Num frames 400...
|
948 |
+
[2023-03-08 14:41:25,522][671990] Num frames 500...
|
949 |
+
[2023-03-08 14:41:25,580][671990] Num frames 600...
|
950 |
+
[2023-03-08 14:41:25,639][671990] Num frames 700...
|
951 |
+
[2023-03-08 14:41:25,698][671990] Num frames 800...
|
952 |
+
[2023-03-08 14:41:25,757][671990] Num frames 900...
|
953 |
+
[2023-03-08 14:41:25,827][671990] Avg episode rewards: #0: 18.280, true rewards: #0: 9.280
|
954 |
+
[2023-03-08 14:41:25,828][671990] Avg episode reward: 18.280, avg true_objective: 9.280
|
955 |
+
[2023-03-08 14:41:25,875][671990] Num frames 1000...
|
956 |
+
[2023-03-08 14:41:25,934][671990] Num frames 1100...
|
957 |
+
[2023-03-08 14:41:26,007][671990] Num frames 1200...
|
958 |
+
[2023-03-08 14:41:26,076][671990] Num frames 1300...
|
959 |
+
[2023-03-08 14:41:26,139][671990] Num frames 1400...
|
960 |
+
[2023-03-08 14:41:26,205][671990] Num frames 1500...
|
961 |
+
[2023-03-08 14:41:26,271][671990] Num frames 1600...
|
962 |
+
[2023-03-08 14:41:26,330][671990] Num frames 1700...
|
963 |
+
[2023-03-08 14:41:26,421][671990] Avg episode rewards: #0: 18.305, true rewards: #0: 8.805
|
964 |
+
[2023-03-08 14:41:26,422][671990] Avg episode reward: 18.305, avg true_objective: 8.805
|
965 |
+
[2023-03-08 14:41:26,449][671990] Num frames 1800...
|
966 |
+
[2023-03-08 14:41:26,507][671990] Num frames 1900...
|
967 |
+
[2023-03-08 14:41:26,569][671990] Num frames 2000...
|
968 |
+
[2023-03-08 14:41:26,628][671990] Num frames 2100...
|
969 |
+
[2023-03-08 14:41:26,687][671990] Num frames 2200...
|
970 |
+
[2023-03-08 14:41:26,745][671990] Num frames 2300...
|
971 |
+
[2023-03-08 14:41:26,808][671990] Num frames 2400...
|
972 |
+
[2023-03-08 14:41:26,869][671990] Num frames 2500...
|
973 |
+
[2023-03-08 14:41:26,928][671990] Num frames 2600...
|
974 |
+
[2023-03-08 14:41:26,987][671990] Num frames 2700...
|
975 |
+
[2023-03-08 14:41:27,046][671990] Num frames 2800...
|
976 |
+
[2023-03-08 14:41:27,105][671990] Num frames 2900...
|
977 |
+
[2023-03-08 14:41:27,163][671990] Num frames 3000...
|
978 |
+
[2023-03-08 14:41:27,259][671990] Avg episode rewards: #0: 20.577, true rewards: #0: 10.243
|
979 |
+
[2023-03-08 14:41:27,260][671990] Avg episode reward: 20.577, avg true_objective: 10.243
|
980 |
+
[2023-03-08 14:41:27,279][671990] Num frames 3100...
|
981 |
+
[2023-03-08 14:41:27,338][671990] Num frames 3200...
|
982 |
+
[2023-03-08 14:41:27,398][671990] Num frames 3300...
|
983 |
+
[2023-03-08 14:41:27,458][671990] Num frames 3400...
|
984 |
+
[2023-03-08 14:41:27,518][671990] Num frames 3500...
|
985 |
+
[2023-03-08 14:41:27,578][671990] Num frames 3600...
|
986 |
+
[2023-03-08 14:41:27,641][671990] Num frames 3700...
|
987 |
+
[2023-03-08 14:41:27,700][671990] Num frames 3800...
|
988 |
+
[2023-03-08 14:41:27,759][671990] Num frames 3900...
|
989 |
+
[2023-03-08 14:41:27,817][671990] Num frames 4000...
|
990 |
+
[2023-03-08 14:41:27,890][671990] Avg episode rewards: #0: 20.333, true rewards: #0: 10.082
|
991 |
+
[2023-03-08 14:41:27,891][671990] Avg episode reward: 20.333, avg true_objective: 10.082
|
992 |
+
[2023-03-08 14:41:27,935][671990] Num frames 4100...
|
993 |
+
[2023-03-08 14:41:27,996][671990] Num frames 4200...
|
994 |
+
[2023-03-08 14:41:28,056][671990] Num frames 4300...
|
995 |
+
[2023-03-08 14:41:28,116][671990] Num frames 4400...
|
996 |
+
[2023-03-08 14:41:28,218][671990] Avg episode rewards: #0: 17.362, true rewards: #0: 8.962
|
997 |
+
[2023-03-08 14:41:28,219][671990] Avg episode reward: 17.362, avg true_objective: 8.962
|
998 |
+
[2023-03-08 14:41:28,234][671990] Num frames 4500...
|
999 |
+
[2023-03-08 14:41:28,297][671990] Num frames 4600...
|
1000 |
+
[2023-03-08 14:41:28,359][671990] Num frames 4700...
|
1001 |
+
[2023-03-08 14:41:28,420][671990] Num frames 4800...
|
1002 |
+
[2023-03-08 14:41:28,480][671990] Num frames 4900...
|
1003 |
+
[2023-03-08 14:41:28,540][671990] Num frames 5000...
|
1004 |
+
[2023-03-08 14:41:28,601][671990] Num frames 5100...
|
1005 |
+
[2023-03-08 14:41:28,663][671990] Num frames 5200...
|
1006 |
+
[2023-03-08 14:41:28,723][671990] Num frames 5300...
|
1007 |
+
[2023-03-08 14:41:28,784][671990] Num frames 5400...
|
1008 |
+
[2023-03-08 14:41:28,846][671990] Num frames 5500...
|
1009 |
+
[2023-03-08 14:41:28,922][671990] Avg episode rewards: #0: 17.895, true rewards: #0: 9.228
|
1010 |
+
[2023-03-08 14:41:28,923][671990] Avg episode reward: 17.895, avg true_objective: 9.228
|
1011 |
+
[2023-03-08 14:41:28,965][671990] Num frames 5600...
|
1012 |
+
[2023-03-08 14:41:29,033][671990] Num frames 5700...
|
1013 |
+
[2023-03-08 14:41:29,092][671990] Num frames 5800...
|
1014 |
+
[2023-03-08 14:41:29,151][671990] Num frames 5900...
|
1015 |
+
[2023-03-08 14:41:29,211][671990] Num frames 6000...
|
1016 |
+
[2023-03-08 14:41:29,271][671990] Num frames 6100...
|
1017 |
+
[2023-03-08 14:41:29,329][671990] Num frames 6200...
|
1018 |
+
[2023-03-08 14:41:29,387][671990] Num frames 6300...
|
1019 |
+
[2023-03-08 14:41:29,445][671990] Num frames 6400...
|
1020 |
+
[2023-03-08 14:41:29,502][671990] Num frames 6500...
|
1021 |
+
[2023-03-08 14:41:29,561][671990] Num frames 6600...
|
1022 |
+
[2023-03-08 14:41:29,624][671990] Num frames 6700...
|
1023 |
+
[2023-03-08 14:41:29,684][671990] Num frames 6800...
|
1024 |
+
[2023-03-08 14:41:29,740][671990] Avg episode rewards: #0: 19.579, true rewards: #0: 9.721
|
1025 |
+
[2023-03-08 14:41:29,741][671990] Avg episode reward: 19.579, avg true_objective: 9.721
|
1026 |
+
[2023-03-08 14:41:29,801][671990] Num frames 6900...
|
1027 |
+
[2023-03-08 14:41:29,864][671990] Num frames 7000...
|
1028 |
+
[2023-03-08 14:41:29,922][671990] Num frames 7100...
|
1029 |
+
[2023-03-08 14:41:29,980][671990] Num frames 7200...
|
1030 |
+
[2023-03-08 14:41:30,039][671990] Num frames 7300...
|
1031 |
+
[2023-03-08 14:41:30,097][671990] Num frames 7400...
|
1032 |
+
[2023-03-08 14:41:30,156][671990] Num frames 7500...
|
1033 |
+
[2023-03-08 14:41:30,214][671990] Num frames 7600...
|
1034 |
+
[2023-03-08 14:41:30,273][671990] Num frames 7700...
|
1035 |
+
[2023-03-08 14:41:30,332][671990] Num frames 7800...
|
1036 |
+
[2023-03-08 14:41:30,389][671990] Avg episode rewards: #0: 19.508, true rewards: #0: 9.757
|
1037 |
+
[2023-03-08 14:41:30,390][671990] Avg episode reward: 19.508, avg true_objective: 9.757
|
1038 |
+
[2023-03-08 14:41:30,448][671990] Num frames 7900...
|
1039 |
+
[2023-03-08 14:41:30,506][671990] Num frames 8000...
|
1040 |
+
[2023-03-08 14:41:30,567][671990] Num frames 8100...
|
1041 |
+
[2023-03-08 14:41:30,627][671990] Num frames 8200...
|
1042 |
+
[2023-03-08 14:41:30,718][671990] Avg episode rewards: #0: 17.949, true rewards: #0: 9.171
|
1043 |
+
[2023-03-08 14:41:30,718][671990] Avg episode reward: 17.949, avg true_objective: 9.171
|
1044 |
+
[2023-03-08 14:41:30,749][671990] Num frames 8300...
|
1045 |
+
[2023-03-08 14:41:30,808][671990] Num frames 8400...
|
1046 |
+
[2023-03-08 14:41:30,869][671990] Num frames 8500...
|
1047 |
+
[2023-03-08 14:41:30,931][671990] Num frames 8600...
|
1048 |
+
[2023-03-08 14:41:30,993][671990] Num frames 8700...
|
1049 |
+
[2023-03-08 14:41:31,053][671990] Num frames 8800...
|
1050 |
+
[2023-03-08 14:41:31,136][671990] Avg episode rewards: #0: 17.552, true rewards: #0: 8.852
|
1051 |
+
[2023-03-08 14:41:31,137][671990] Avg episode reward: 17.552, avg true_objective: 8.852
|
1052 |
+
[2023-03-08 14:41:40,764][671990] Replay video saved to /home/michal/programming/deep-rl-course/train_dir/default_experiment/replay.mp4!
|