Upload folder using huggingface_hub
Browse files- .gitattributes +1 -0
- .summary/0/events.out.tfevents.1700031294.4391a95ca488 +0 -0
- .summary/0/events.out.tfevents.1700031391.4391a95ca488 +0 -0
- .summary/0/events.out.tfevents.1700031580.4391a95ca488 +0 -0
- .summary/0/events.out.tfevents.1700031701.4391a95ca488 +3 -0
- README.md +56 -0
- checkpoint_p0/checkpoint_000000002_8192.pth +3 -0
- config.json +142 -0
- replay.mp4 +3 -0
- sf_log.txt +484 -0
.gitattributes
CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
+
replay.mp4 filter=lfs diff=lfs merge=lfs -text
|
.summary/0/events.out.tfevents.1700031294.4391a95ca488
ADDED
File without changes
|
.summary/0/events.out.tfevents.1700031391.4391a95ca488
ADDED
File without changes
|
.summary/0/events.out.tfevents.1700031580.4391a95ca488
ADDED
File without changes
|
.summary/0/events.out.tfevents.1700031701.4391a95ca488
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fe35b8b0d096d1765b515cb8736640d2c619211ad36fbfa0cb42cbbd34260d3f
|
3 |
+
size 2256
|
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: 3.95 +/- 0.22
|
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 nikxtaco/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/checkpoint_000000002_8192.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ebb8b7db46f5efe55b31c40b49344e81c1c7c6bb6b1b7a3b3fbfb8eeb13f528f
|
3 |
+
size 34929349
|
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": "/content/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": 4000,
|
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=4000",
|
134 |
+
"cli_args": {
|
135 |
+
"env": "doom_health_gathering_supreme",
|
136 |
+
"num_workers": 8,
|
137 |
+
"num_envs_per_worker": 4,
|
138 |
+
"train_for_env_steps": 4000
|
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 sha256:01b87e99871d2f8d4d81a63e3acee4121ec1176e9c5d6e8d3e3bf3ea93a90f50
|
3 |
+
size 6189816
|
sf_log.txt
ADDED
@@ -0,0 +1,484 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
[2023-11-15 07:01:43,246][00663] Saving configuration to /content/train_dir/default_experiment/config.json...
|
2 |
+
[2023-11-15 07:01:43,251][00663] Rollout worker 0 uses device cpu
|
3 |
+
[2023-11-15 07:01:43,255][00663] Rollout worker 1 uses device cpu
|
4 |
+
[2023-11-15 07:01:43,256][00663] Rollout worker 2 uses device cpu
|
5 |
+
[2023-11-15 07:01:43,258][00663] Rollout worker 3 uses device cpu
|
6 |
+
[2023-11-15 07:01:43,262][00663] Rollout worker 4 uses device cpu
|
7 |
+
[2023-11-15 07:01:43,264][00663] Rollout worker 5 uses device cpu
|
8 |
+
[2023-11-15 07:01:43,265][00663] Rollout worker 6 uses device cpu
|
9 |
+
[2023-11-15 07:01:43,267][00663] Rollout worker 7 uses device cpu
|
10 |
+
[2023-11-15 07:01:43,416][00663] Using GPUs [0] for process 0 (actually maps to GPUs [0])
|
11 |
+
[2023-11-15 07:01:43,417][00663] InferenceWorker_p0-w0: min num requests: 2
|
12 |
+
[2023-11-15 07:01:43,448][00663] Starting all processes...
|
13 |
+
[2023-11-15 07:01:43,450][00663] Starting process learner_proc0
|
14 |
+
[2023-11-15 07:01:43,501][00663] Starting all processes...
|
15 |
+
[2023-11-15 07:01:43,510][00663] Starting process inference_proc0-0
|
16 |
+
[2023-11-15 07:01:43,510][00663] Starting process rollout_proc0
|
17 |
+
[2023-11-15 07:01:43,512][00663] Starting process rollout_proc1
|
18 |
+
[2023-11-15 07:01:43,513][00663] Starting process rollout_proc2
|
19 |
+
[2023-11-15 07:01:43,514][00663] Starting process rollout_proc3
|
20 |
+
[2023-11-15 07:01:43,514][00663] Starting process rollout_proc4
|
21 |
+
[2023-11-15 07:01:43,514][00663] Starting process rollout_proc5
|
22 |
+
[2023-11-15 07:01:43,514][00663] Starting process rollout_proc6
|
23 |
+
[2023-11-15 07:01:43,514][00663] Starting process rollout_proc7
|
24 |
+
[2023-11-15 07:02:00,834][10761] Using GPUs [0] for process 0 (actually maps to GPUs [0])
|
25 |
+
[2023-11-15 07:02:00,838][10761] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for learning process 0
|
26 |
+
[2023-11-15 07:02:00,910][10761] Num visible devices: 1
|
27 |
+
[2023-11-15 07:02:00,941][10761] Starting seed is not provided
|
28 |
+
[2023-11-15 07:02:00,941][10761] Using GPUs [0] for process 0 (actually maps to GPUs [0])
|
29 |
+
[2023-11-15 07:02:00,941][10761] Initializing actor-critic model on device cuda:0
|
30 |
+
[2023-11-15 07:02:00,943][10761] RunningMeanStd input shape: (3, 72, 128)
|
31 |
+
[2023-11-15 07:02:00,948][10761] RunningMeanStd input shape: (1,)
|
32 |
+
[2023-11-15 07:02:00,987][10780] Worker 1 uses CPU cores [1]
|
33 |
+
[2023-11-15 07:02:01,005][10761] ConvEncoder: input_channels=3
|
34 |
+
[2023-11-15 07:02:01,011][10779] Worker 0 uses CPU cores [0]
|
35 |
+
[2023-11-15 07:02:01,024][10778] Using GPUs [0] for process 0 (actually maps to GPUs [0])
|
36 |
+
[2023-11-15 07:02:01,027][10778] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for inference process 0
|
37 |
+
[2023-11-15 07:02:01,056][10778] Num visible devices: 1
|
38 |
+
[2023-11-15 07:02:01,127][10785] Worker 6 uses CPU cores [0]
|
39 |
+
[2023-11-15 07:02:01,251][10786] Worker 7 uses CPU cores [1]
|
40 |
+
[2023-11-15 07:02:01,290][10781] Worker 3 uses CPU cores [1]
|
41 |
+
[2023-11-15 07:02:01,334][10783] Worker 4 uses CPU cores [0]
|
42 |
+
[2023-11-15 07:02:01,373][10782] Worker 2 uses CPU cores [0]
|
43 |
+
[2023-11-15 07:02:01,383][10784] Worker 5 uses CPU cores [1]
|
44 |
+
[2023-11-15 07:02:01,422][10761] Conv encoder output size: 512
|
45 |
+
[2023-11-15 07:02:01,422][10761] Policy head output size: 512
|
46 |
+
[2023-11-15 07:02:01,475][10761] Created Actor Critic model with architecture:
|
47 |
+
[2023-11-15 07:02:01,475][10761] ActorCriticSharedWeights(
|
48 |
+
(obs_normalizer): ObservationNormalizer(
|
49 |
+
(running_mean_std): RunningMeanStdDictInPlace(
|
50 |
+
(running_mean_std): ModuleDict(
|
51 |
+
(obs): RunningMeanStdInPlace()
|
52 |
+
)
|
53 |
+
)
|
54 |
+
)
|
55 |
+
(returns_normalizer): RecursiveScriptModule(original_name=RunningMeanStdInPlace)
|
56 |
+
(encoder): VizdoomEncoder(
|
57 |
+
(basic_encoder): ConvEncoder(
|
58 |
+
(enc): RecursiveScriptModule(
|
59 |
+
original_name=ConvEncoderImpl
|
60 |
+
(conv_head): RecursiveScriptModule(
|
61 |
+
original_name=Sequential
|
62 |
+
(0): RecursiveScriptModule(original_name=Conv2d)
|
63 |
+
(1): RecursiveScriptModule(original_name=ELU)
|
64 |
+
(2): RecursiveScriptModule(original_name=Conv2d)
|
65 |
+
(3): RecursiveScriptModule(original_name=ELU)
|
66 |
+
(4): RecursiveScriptModule(original_name=Conv2d)
|
67 |
+
(5): RecursiveScriptModule(original_name=ELU)
|
68 |
+
)
|
69 |
+
(mlp_layers): RecursiveScriptModule(
|
70 |
+
original_name=Sequential
|
71 |
+
(0): RecursiveScriptModule(original_name=Linear)
|
72 |
+
(1): RecursiveScriptModule(original_name=ELU)
|
73 |
+
)
|
74 |
+
)
|
75 |
+
)
|
76 |
+
)
|
77 |
+
(core): ModelCoreRNN(
|
78 |
+
(core): GRU(512, 512)
|
79 |
+
)
|
80 |
+
(decoder): MlpDecoder(
|
81 |
+
(mlp): Identity()
|
82 |
+
)
|
83 |
+
(critic_linear): Linear(in_features=512, out_features=1, bias=True)
|
84 |
+
(action_parameterization): ActionParameterizationDefault(
|
85 |
+
(distribution_linear): Linear(in_features=512, out_features=5, bias=True)
|
86 |
+
)
|
87 |
+
)
|
88 |
+
[2023-11-15 07:02:01,853][10761] Using optimizer <class 'torch.optim.adam.Adam'>
|
89 |
+
[2023-11-15 07:02:02,202][10761] No checkpoints found
|
90 |
+
[2023-11-15 07:02:02,203][10761] Did not load from checkpoint, starting from scratch!
|
91 |
+
[2023-11-15 07:02:02,203][10761] Initialized policy 0 weights for model version 0
|
92 |
+
[2023-11-15 07:02:02,207][10761] LearnerWorker_p0 finished initialization!
|
93 |
+
[2023-11-15 07:02:02,208][10761] Using GPUs [0] for process 0 (actually maps to GPUs [0])
|
94 |
+
[2023-11-15 07:02:02,385][10778] RunningMeanStd input shape: (3, 72, 128)
|
95 |
+
[2023-11-15 07:02:02,386][10778] RunningMeanStd input shape: (1,)
|
96 |
+
[2023-11-15 07:02:02,398][10778] ConvEncoder: input_channels=3
|
97 |
+
[2023-11-15 07:02:02,495][10778] Conv encoder output size: 512
|
98 |
+
[2023-11-15 07:02:02,495][10778] Policy head output size: 512
|
99 |
+
[2023-11-15 07:02:02,555][00663] Inference worker 0-0 is ready!
|
100 |
+
[2023-11-15 07:02:02,556][00663] All inference workers are ready! Signal rollout workers to start!
|
101 |
+
[2023-11-15 07:02:02,758][10783] Doom resolution: 160x120, resize resolution: (128, 72)
|
102 |
+
[2023-11-15 07:02:02,759][10782] Doom resolution: 160x120, resize resolution: (128, 72)
|
103 |
+
[2023-11-15 07:02:02,760][10779] Doom resolution: 160x120, resize resolution: (128, 72)
|
104 |
+
[2023-11-15 07:02:02,761][10785] Doom resolution: 160x120, resize resolution: (128, 72)
|
105 |
+
[2023-11-15 07:02:02,770][10784] Doom resolution: 160x120, resize resolution: (128, 72)
|
106 |
+
[2023-11-15 07:02:02,763][10781] Doom resolution: 160x120, resize resolution: (128, 72)
|
107 |
+
[2023-11-15 07:02:02,772][10780] Doom resolution: 160x120, resize resolution: (128, 72)
|
108 |
+
[2023-11-15 07:02:02,773][10786] Doom resolution: 160x120, resize resolution: (128, 72)
|
109 |
+
[2023-11-15 07:02:03,403][00663] Heartbeat connected on Batcher_0
|
110 |
+
[2023-11-15 07:02:03,409][00663] Heartbeat connected on LearnerWorker_p0
|
111 |
+
[2023-11-15 07:02:03,460][00663] Heartbeat connected on InferenceWorker_p0-w0
|
112 |
+
[2023-11-15 07:02:03,770][10780] Decorrelating experience for 0 frames...
|
113 |
+
[2023-11-15 07:02:03,769][10784] Decorrelating experience for 0 frames...
|
114 |
+
[2023-11-15 07:02:04,070][10782] Decorrelating experience for 0 frames...
|
115 |
+
[2023-11-15 07:02:04,076][10783] Decorrelating experience for 0 frames...
|
116 |
+
[2023-11-15 07:02:04,079][10785] Decorrelating experience for 0 frames...
|
117 |
+
[2023-11-15 07:02:04,923][10780] Decorrelating experience for 32 frames...
|
118 |
+
[2023-11-15 07:02:04,927][10784] Decorrelating experience for 32 frames...
|
119 |
+
[2023-11-15 07:02:04,992][10781] Decorrelating experience for 0 frames...
|
120 |
+
[2023-11-15 07:02:05,650][10782] Decorrelating experience for 32 frames...
|
121 |
+
[2023-11-15 07:02:05,654][10783] Decorrelating experience for 32 frames...
|
122 |
+
[2023-11-15 07:02:05,705][10779] Decorrelating experience for 0 frames...
|
123 |
+
[2023-11-15 07:02:06,206][00663] 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)
|
124 |
+
[2023-11-15 07:02:06,845][10786] Decorrelating experience for 0 frames...
|
125 |
+
[2023-11-15 07:02:07,400][10784] Decorrelating experience for 64 frames...
|
126 |
+
[2023-11-15 07:02:07,555][10780] Decorrelating experience for 64 frames...
|
127 |
+
[2023-11-15 07:02:07,628][10785] Decorrelating experience for 32 frames...
|
128 |
+
[2023-11-15 07:02:07,692][10779] Decorrelating experience for 32 frames...
|
129 |
+
[2023-11-15 07:02:08,073][10783] Decorrelating experience for 64 frames...
|
130 |
+
[2023-11-15 07:02:08,089][10782] Decorrelating experience for 64 frames...
|
131 |
+
[2023-11-15 07:02:09,560][10785] Decorrelating experience for 64 frames...
|
132 |
+
[2023-11-15 07:02:09,642][10779] Decorrelating experience for 64 frames...
|
133 |
+
[2023-11-15 07:02:09,771][10781] Decorrelating experience for 32 frames...
|
134 |
+
[2023-11-15 07:02:09,855][10784] Decorrelating experience for 96 frames...
|
135 |
+
[2023-11-15 07:02:09,900][10782] Decorrelating experience for 96 frames...
|
136 |
+
[2023-11-15 07:02:10,156][10786] Decorrelating experience for 32 frames...
|
137 |
+
[2023-11-15 07:02:10,296][00663] Heartbeat connected on RolloutWorker_w2
|
138 |
+
[2023-11-15 07:02:10,303][00663] Heartbeat connected on RolloutWorker_w5
|
139 |
+
[2023-11-15 07:02:11,207][00663] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 0.0. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0)
|
140 |
+
[2023-11-15 07:02:11,442][10783] Decorrelating experience for 96 frames...
|
141 |
+
[2023-11-15 07:02:11,533][10785] Decorrelating experience for 96 frames...
|
142 |
+
[2023-11-15 07:02:11,565][10780] Decorrelating experience for 96 frames...
|
143 |
+
[2023-11-15 07:02:11,747][00663] Heartbeat connected on RolloutWorker_w4
|
144 |
+
[2023-11-15 07:02:11,837][00663] Heartbeat connected on RolloutWorker_w6
|
145 |
+
[2023-11-15 07:02:11,969][00663] Heartbeat connected on RolloutWorker_w1
|
146 |
+
[2023-11-15 07:02:12,639][10786] Decorrelating experience for 64 frames...
|
147 |
+
[2023-11-15 07:02:14,290][10779] Decorrelating experience for 96 frames...
|
148 |
+
[2023-11-15 07:02:14,776][10781] Decorrelating experience for 64 frames...
|
149 |
+
[2023-11-15 07:02:15,186][00663] Heartbeat connected on RolloutWorker_w0
|
150 |
+
[2023-11-15 07:02:16,203][00663] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 120.8. Samples: 1208. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0)
|
151 |
+
[2023-11-15 07:02:16,206][00663] Avg episode reward: [(0, '2.474')]
|
152 |
+
[2023-11-15 07:02:16,576][10786] Decorrelating experience for 96 frames...
|
153 |
+
[2023-11-15 07:02:17,569][00663] Heartbeat connected on RolloutWorker_w7
|
154 |
+
[2023-11-15 07:02:17,852][10761] Signal inference workers to stop experience collection...
|
155 |
+
[2023-11-15 07:02:17,922][10778] InferenceWorker_p0-w0: stopping experience collection
|
156 |
+
[2023-11-15 07:02:18,028][10781] Decorrelating experience for 96 frames...
|
157 |
+
[2023-11-15 07:02:18,105][00663] Heartbeat connected on RolloutWorker_w3
|
158 |
+
[2023-11-15 07:02:18,723][10761] Signal inference workers to resume experience collection...
|
159 |
+
[2023-11-15 07:02:18,724][10778] InferenceWorker_p0-w0: resuming experience collection
|
160 |
+
[2023-11-15 07:02:20,186][10761] Stopping Batcher_0...
|
161 |
+
[2023-11-15 07:02:20,187][10761] Loop batcher_evt_loop terminating...
|
162 |
+
[2023-11-15 07:02:20,187][00663] Component Batcher_0 stopped!
|
163 |
+
[2023-11-15 07:02:20,196][10761] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000002_8192.pth...
|
164 |
+
[2023-11-15 07:02:20,229][00663] Component RolloutWorker_w1 stopped!
|
165 |
+
[2023-11-15 07:02:20,228][10780] Stopping RolloutWorker_w1...
|
166 |
+
[2023-11-15 07:02:20,234][00663] Component RolloutWorker_w5 stopped!
|
167 |
+
[2023-11-15 07:02:20,240][10781] Stopping RolloutWorker_w3...
|
168 |
+
[2023-11-15 07:02:20,242][10781] Loop rollout_proc3_evt_loop terminating...
|
169 |
+
[2023-11-15 07:02:20,241][00663] Component RolloutWorker_w3 stopped!
|
170 |
+
[2023-11-15 07:02:20,234][10784] Stopping RolloutWorker_w5...
|
171 |
+
[2023-11-15 07:02:20,235][10780] Loop rollout_proc1_evt_loop terminating...
|
172 |
+
[2023-11-15 07:02:20,251][00663] Component RolloutWorker_w7 stopped!
|
173 |
+
[2023-11-15 07:02:20,250][10786] Stopping RolloutWorker_w7...
|
174 |
+
[2023-11-15 07:02:20,251][10784] Loop rollout_proc5_evt_loop terminating...
|
175 |
+
[2023-11-15 07:02:20,254][10786] Loop rollout_proc7_evt_loop terminating...
|
176 |
+
[2023-11-15 07:02:20,269][10778] Weights refcount: 2 0
|
177 |
+
[2023-11-15 07:02:20,270][10782] Stopping RolloutWorker_w2...
|
178 |
+
[2023-11-15 07:02:20,270][00663] Component RolloutWorker_w2 stopped!
|
179 |
+
[2023-11-15 07:02:20,272][10778] Stopping InferenceWorker_p0-w0...
|
180 |
+
[2023-11-15 07:02:20,273][10778] Loop inference_proc0-0_evt_loop terminating...
|
181 |
+
[2023-11-15 07:02:20,273][00663] Component InferenceWorker_p0-w0 stopped!
|
182 |
+
[2023-11-15 07:02:20,286][10782] Loop rollout_proc2_evt_loop terminating...
|
183 |
+
[2023-11-15 07:02:20,295][00663] Component RolloutWorker_w6 stopped!
|
184 |
+
[2023-11-15 07:02:20,303][00663] Component RolloutWorker_w0 stopped!
|
185 |
+
[2023-11-15 07:02:20,295][10785] Stopping RolloutWorker_w6...
|
186 |
+
[2023-11-15 07:02:20,303][10779] Stopping RolloutWorker_w0...
|
187 |
+
[2023-11-15 07:02:20,309][10785] Loop rollout_proc6_evt_loop terminating...
|
188 |
+
[2023-11-15 07:02:20,310][10779] Loop rollout_proc0_evt_loop terminating...
|
189 |
+
[2023-11-15 07:02:20,321][00663] Component RolloutWorker_w4 stopped!
|
190 |
+
[2023-11-15 07:02:20,321][10783] Stopping RolloutWorker_w4...
|
191 |
+
[2023-11-15 07:02:20,327][10783] Loop rollout_proc4_evt_loop terminating...
|
192 |
+
[2023-11-15 07:02:20,370][10761] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000002_8192.pth...
|
193 |
+
[2023-11-15 07:02:20,586][00663] Component LearnerWorker_p0 stopped!
|
194 |
+
[2023-11-15 07:02:20,588][00663] Waiting for process learner_proc0 to stop...
|
195 |
+
[2023-11-15 07:02:20,586][10761] Stopping LearnerWorker_p0...
|
196 |
+
[2023-11-15 07:02:20,591][10761] Loop learner_proc0_evt_loop terminating...
|
197 |
+
[2023-11-15 07:02:22,053][00663] Waiting for process inference_proc0-0 to join...
|
198 |
+
[2023-11-15 07:02:22,102][00663] Waiting for process rollout_proc0 to join...
|
199 |
+
[2023-11-15 07:02:24,502][00663] Waiting for process rollout_proc1 to join...
|
200 |
+
[2023-11-15 07:02:24,604][00663] Waiting for process rollout_proc2 to join...
|
201 |
+
[2023-11-15 07:02:24,606][00663] Waiting for process rollout_proc3 to join...
|
202 |
+
[2023-11-15 07:02:24,609][00663] Waiting for process rollout_proc4 to join...
|
203 |
+
[2023-11-15 07:02:24,612][00663] Waiting for process rollout_proc5 to join...
|
204 |
+
[2023-11-15 07:02:24,615][00663] Waiting for process rollout_proc6 to join...
|
205 |
+
[2023-11-15 07:02:24,620][00663] Waiting for process rollout_proc7 to join...
|
206 |
+
[2023-11-15 07:02:24,623][00663] Batcher 0 profile tree view:
|
207 |
+
batching: 0.0629, releasing_batches: 0.0004
|
208 |
+
[2023-11-15 07:02:24,625][00663] InferenceWorker_p0-w0 profile tree view:
|
209 |
+
wait_policy: 0.0000
|
210 |
+
wait_policy_total: 11.1031
|
211 |
+
update_model: 0.0531
|
212 |
+
weight_update: 0.0035
|
213 |
+
one_step: 0.0117
|
214 |
+
handle_policy_step: 5.3752
|
215 |
+
deserialize: 0.0825, stack: 0.0142, obs_to_device_normalize: 0.7806, forward: 3.7947, send_messages: 0.1665
|
216 |
+
prepare_outputs: 0.4019
|
217 |
+
to_cpu: 0.1972
|
218 |
+
[2023-11-15 07:02:24,627][00663] Learner 0 profile tree view:
|
219 |
+
misc: 0.0000, prepare_batch: 3.1931
|
220 |
+
train: 1.9676
|
221 |
+
epoch_init: 0.0000, minibatch_init: 0.0000, losses_postprocess: 0.0005, kl_divergence: 0.0067, after_optimizer: 0.0663
|
222 |
+
calculate_losses: 0.6155
|
223 |
+
losses_init: 0.0000, forward_head: 0.3481, bptt_initial: 0.1651, tail: 0.0300, advantages_returns: 0.0021, losses: 0.0578
|
224 |
+
bptt: 0.0118
|
225 |
+
bptt_forward_core: 0.0117
|
226 |
+
update: 1.2776
|
227 |
+
clip: 0.0777
|
228 |
+
[2023-11-15 07:02:24,629][00663] RolloutWorker_w0 profile tree view:
|
229 |
+
wait_for_trajectories: 0.0032, enqueue_policy_requests: 0.6631, env_step: 2.7787, overhead: 0.0796, complete_rollouts: 0.0091
|
230 |
+
save_policy_outputs: 0.0847
|
231 |
+
split_output_tensors: 0.0449
|
232 |
+
[2023-11-15 07:02:24,632][00663] RolloutWorker_w7 profile tree view:
|
233 |
+
wait_for_trajectories: 0.0005, enqueue_policy_requests: 0.1984, env_step: 1.3664, overhead: 0.0326, complete_rollouts: 0.0003
|
234 |
+
save_policy_outputs: 0.0129
|
235 |
+
split_output_tensors: 0.0069
|
236 |
+
[2023-11-15 07:02:24,636][00663] Loop Runner_EvtLoop terminating...
|
237 |
+
[2023-11-15 07:02:24,638][00663] Runner profile tree view:
|
238 |
+
main_loop: 41.1905
|
239 |
+
[2023-11-15 07:02:24,640][00663] Collected {0: 8192}, FPS: 198.9
|
240 |
+
[2023-11-15 07:02:45,729][00663] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json
|
241 |
+
[2023-11-15 07:02:45,730][00663] Overriding arg 'num_workers' with value 1 passed from command line
|
242 |
+
[2023-11-15 07:02:45,734][00663] Adding new argument 'no_render'=True that is not in the saved config file!
|
243 |
+
[2023-11-15 07:02:45,739][00663] Adding new argument 'save_video'=True that is not in the saved config file!
|
244 |
+
[2023-11-15 07:02:45,742][00663] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file!
|
245 |
+
[2023-11-15 07:02:45,743][00663] Adding new argument 'video_name'=None that is not in the saved config file!
|
246 |
+
[2023-11-15 07:02:45,749][00663] Adding new argument 'max_num_frames'=1000000000.0 that is not in the saved config file!
|
247 |
+
[2023-11-15 07:02:45,750][00663] Adding new argument 'max_num_episodes'=10 that is not in the saved config file!
|
248 |
+
[2023-11-15 07:02:45,751][00663] Adding new argument 'push_to_hub'=False that is not in the saved config file!
|
249 |
+
[2023-11-15 07:02:45,753][00663] Adding new argument 'hf_repository'=None that is not in the saved config file!
|
250 |
+
[2023-11-15 07:02:45,755][00663] Adding new argument 'policy_index'=0 that is not in the saved config file!
|
251 |
+
[2023-11-15 07:02:45,756][00663] Adding new argument 'eval_deterministic'=False that is not in the saved config file!
|
252 |
+
[2023-11-15 07:02:45,757][00663] Adding new argument 'train_script'=None that is not in the saved config file!
|
253 |
+
[2023-11-15 07:02:45,758][00663] Adding new argument 'enjoy_script'=None that is not in the saved config file!
|
254 |
+
[2023-11-15 07:02:45,760][00663] Using frameskip 1 and render_action_repeat=4 for evaluation
|
255 |
+
[2023-11-15 07:02:45,797][00663] Doom resolution: 160x120, resize resolution: (128, 72)
|
256 |
+
[2023-11-15 07:02:45,801][00663] RunningMeanStd input shape: (3, 72, 128)
|
257 |
+
[2023-11-15 07:02:45,806][00663] RunningMeanStd input shape: (1,)
|
258 |
+
[2023-11-15 07:02:45,821][00663] ConvEncoder: input_channels=3
|
259 |
+
[2023-11-15 07:02:45,925][00663] Conv encoder output size: 512
|
260 |
+
[2023-11-15 07:02:45,926][00663] Policy head output size: 512
|
261 |
+
[2023-11-15 07:02:53,558][00663] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000002_8192.pth...
|
262 |
+
[2023-11-15 07:02:57,671][00663] Num frames 100...
|
263 |
+
[2023-11-15 07:02:57,861][00663] Num frames 200...
|
264 |
+
[2023-11-15 07:02:58,054][00663] Num frames 300...
|
265 |
+
[2023-11-15 07:02:58,250][00663] Num frames 400...
|
266 |
+
[2023-11-15 07:02:58,398][00663] Avg episode rewards: #0: 5.480, true rewards: #0: 4.480
|
267 |
+
[2023-11-15 07:02:58,401][00663] Avg episode reward: 5.480, avg true_objective: 4.480
|
268 |
+
[2023-11-15 07:02:58,505][00663] Num frames 500...
|
269 |
+
[2023-11-15 07:02:58,692][00663] Num frames 600...
|
270 |
+
[2023-11-15 07:02:58,874][00663] Num frames 700...
|
271 |
+
[2023-11-15 07:02:59,057][00663] Num frames 800...
|
272 |
+
[2023-11-15 07:02:59,155][00663] Avg episode rewards: #0: 4.660, true rewards: #0: 4.160
|
273 |
+
[2023-11-15 07:02:59,156][00663] Avg episode reward: 4.660, avg true_objective: 4.160
|
274 |
+
[2023-11-15 07:02:59,251][00663] Num frames 900...
|
275 |
+
[2023-11-15 07:02:59,388][00663] Num frames 1000...
|
276 |
+
[2023-11-15 07:02:59,534][00663] Num frames 1100...
|
277 |
+
[2023-11-15 07:02:59,667][00663] Num frames 1200...
|
278 |
+
[2023-11-15 07:02:59,826][00663] Avg episode rewards: #0: 4.933, true rewards: #0: 4.267
|
279 |
+
[2023-11-15 07:02:59,828][00663] Avg episode reward: 4.933, avg true_objective: 4.267
|
280 |
+
[2023-11-15 07:02:59,858][00663] Num frames 1300...
|
281 |
+
[2023-11-15 07:02:59,983][00663] Num frames 1400...
|
282 |
+
[2023-11-15 07:03:00,112][00663] Num frames 1500...
|
283 |
+
[2023-11-15 07:03:00,241][00663] Num frames 1600...
|
284 |
+
[2023-11-15 07:03:00,367][00663] Num frames 1700...
|
285 |
+
[2023-11-15 07:03:00,462][00663] Avg episode rewards: #0: 5.070, true rewards: #0: 4.320
|
286 |
+
[2023-11-15 07:03:00,463][00663] Avg episode reward: 5.070, avg true_objective: 4.320
|
287 |
+
[2023-11-15 07:03:00,561][00663] Num frames 1800...
|
288 |
+
[2023-11-15 07:03:00,688][00663] Num frames 1900...
|
289 |
+
[2023-11-15 07:03:00,815][00663] Num frames 2000...
|
290 |
+
[2023-11-15 07:03:00,939][00663] Num frames 2100...
|
291 |
+
[2023-11-15 07:03:01,047][00663] Avg episode rewards: #0: 4.888, true rewards: #0: 4.288
|
292 |
+
[2023-11-15 07:03:01,050][00663] Avg episode reward: 4.888, avg true_objective: 4.288
|
293 |
+
[2023-11-15 07:03:01,123][00663] Num frames 2200...
|
294 |
+
[2023-11-15 07:03:01,253][00663] Num frames 2300...
|
295 |
+
[2023-11-15 07:03:01,386][00663] Num frames 2400...
|
296 |
+
[2023-11-15 07:03:01,514][00663] Num frames 2500...
|
297 |
+
[2023-11-15 07:03:01,698][00663] Avg episode rewards: #0: 4.987, true rewards: #0: 4.320
|
298 |
+
[2023-11-15 07:03:01,700][00663] Avg episode reward: 4.987, avg true_objective: 4.320
|
299 |
+
[2023-11-15 07:03:01,718][00663] Num frames 2600...
|
300 |
+
[2023-11-15 07:03:01,862][00663] Num frames 2700...
|
301 |
+
[2023-11-15 07:03:01,996][00663] Num frames 2800...
|
302 |
+
[2023-11-15 07:03:02,124][00663] Num frames 2900...
|
303 |
+
[2023-11-15 07:03:02,278][00663] Avg episode rewards: #0: 4.823, true rewards: #0: 4.251
|
304 |
+
[2023-11-15 07:03:02,279][00663] Avg episode reward: 4.823, avg true_objective: 4.251
|
305 |
+
[2023-11-15 07:03:02,313][00663] Num frames 3000...
|
306 |
+
[2023-11-15 07:03:02,439][00663] Num frames 3100...
|
307 |
+
[2023-11-15 07:03:02,585][00663] Num frames 3200...
|
308 |
+
[2023-11-15 07:03:02,713][00663] Num frames 3300...
|
309 |
+
[2023-11-15 07:03:02,845][00663] Avg episode rewards: #0: 4.700, true rewards: #0: 4.200
|
310 |
+
[2023-11-15 07:03:02,846][00663] Avg episode reward: 4.700, avg true_objective: 4.200
|
311 |
+
[2023-11-15 07:03:02,903][00663] Num frames 3400...
|
312 |
+
[2023-11-15 07:03:03,028][00663] Num frames 3500...
|
313 |
+
[2023-11-15 07:03:03,164][00663] Num frames 3600...
|
314 |
+
[2023-11-15 07:03:03,291][00663] Num frames 3700...
|
315 |
+
[2023-11-15 07:03:03,401][00663] Avg episode rewards: #0: 4.604, true rewards: #0: 4.160
|
316 |
+
[2023-11-15 07:03:03,402][00663] Avg episode reward: 4.604, avg true_objective: 4.160
|
317 |
+
[2023-11-15 07:03:03,475][00663] Num frames 3800...
|
318 |
+
[2023-11-15 07:03:03,606][00663] Num frames 3900...
|
319 |
+
[2023-11-15 07:03:03,733][00663] Num frames 4000...
|
320 |
+
[2023-11-15 07:03:03,860][00663] Num frames 4100...
|
321 |
+
[2023-11-15 07:03:03,954][00663] Avg episode rewards: #0: 4.528, true rewards: #0: 4.128
|
322 |
+
[2023-11-15 07:03:03,955][00663] Avg episode reward: 4.528, avg true_objective: 4.128
|
323 |
+
[2023-11-15 07:03:30,284][00663] Replay video saved to /content/train_dir/default_experiment/replay.mp4!
|
324 |
+
[2023-11-15 07:03:44,458][00663] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json
|
325 |
+
[2023-11-15 07:03:44,463][00663] Overriding arg 'num_workers' with value 1 passed from command line
|
326 |
+
[2023-11-15 07:03:44,465][00663] Adding new argument 'no_render'=True that is not in the saved config file!
|
327 |
+
[2023-11-15 07:03:44,467][00663] Adding new argument 'save_video'=True that is not in the saved config file!
|
328 |
+
[2023-11-15 07:03:44,473][00663] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file!
|
329 |
+
[2023-11-15 07:03:44,474][00663] Adding new argument 'video_name'=None that is not in the saved config file!
|
330 |
+
[2023-11-15 07:03:44,476][00663] Adding new argument 'max_num_frames'=100000 that is not in the saved config file!
|
331 |
+
[2023-11-15 07:03:44,477][00663] Adding new argument 'max_num_episodes'=10 that is not in the saved config file!
|
332 |
+
[2023-11-15 07:03:44,478][00663] Adding new argument 'push_to_hub'=True that is not in the saved config file!
|
333 |
+
[2023-11-15 07:03:44,484][00663] Adding new argument 'hf_repository'='nikxtaco/rl_course_vizdoom_health_gathering_supreme' that is not in the saved config file!
|
334 |
+
[2023-11-15 07:03:44,485][00663] Adding new argument 'policy_index'=0 that is not in the saved config file!
|
335 |
+
[2023-11-15 07:03:44,486][00663] Adding new argument 'eval_deterministic'=False that is not in the saved config file!
|
336 |
+
[2023-11-15 07:03:44,487][00663] Adding new argument 'train_script'=None that is not in the saved config file!
|
337 |
+
[2023-11-15 07:03:44,488][00663] Adding new argument 'enjoy_script'=None that is not in the saved config file!
|
338 |
+
[2023-11-15 07:03:44,489][00663] Using frameskip 1 and render_action_repeat=4 for evaluation
|
339 |
+
[2023-11-15 07:03:44,548][00663] RunningMeanStd input shape: (3, 72, 128)
|
340 |
+
[2023-11-15 07:03:44,553][00663] RunningMeanStd input shape: (1,)
|
341 |
+
[2023-11-15 07:03:44,575][00663] ConvEncoder: input_channels=3
|
342 |
+
[2023-11-15 07:03:44,652][00663] Conv encoder output size: 512
|
343 |
+
[2023-11-15 07:03:44,655][00663] Policy head output size: 512
|
344 |
+
[2023-11-15 07:03:44,682][00663] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000002_8192.pth...
|
345 |
+
[2023-11-15 07:03:45,285][00663] Num frames 100...
|
346 |
+
[2023-11-15 07:03:45,421][00663] Num frames 200...
|
347 |
+
[2023-11-15 07:03:45,563][00663] Num frames 300...
|
348 |
+
[2023-11-15 07:03:45,734][00663] Avg episode rewards: #0: 3.840, true rewards: #0: 3.840
|
349 |
+
[2023-11-15 07:03:45,737][00663] Avg episode reward: 3.840, avg true_objective: 3.840
|
350 |
+
[2023-11-15 07:03:45,763][00663] Num frames 400...
|
351 |
+
[2023-11-15 07:03:45,894][00663] Num frames 500...
|
352 |
+
[2023-11-15 07:03:46,058][00663] Num frames 600...
|
353 |
+
[2023-11-15 07:03:46,234][00663] Num frames 700...
|
354 |
+
[2023-11-15 07:03:46,379][00663] Avg episode rewards: #0: 3.840, true rewards: #0: 3.840
|
355 |
+
[2023-11-15 07:03:46,380][00663] Avg episode reward: 3.840, avg true_objective: 3.840
|
356 |
+
[2023-11-15 07:03:46,428][00663] Num frames 800...
|
357 |
+
[2023-11-15 07:03:46,552][00663] Num frames 900...
|
358 |
+
[2023-11-15 07:03:46,685][00663] Num frames 1000...
|
359 |
+
[2023-11-15 07:03:46,815][00663] Num frames 1100...
|
360 |
+
[2023-11-15 07:03:46,939][00663] Avg episode rewards: #0: 3.840, true rewards: #0: 3.840
|
361 |
+
[2023-11-15 07:03:46,942][00663] Avg episode reward: 3.840, avg true_objective: 3.840
|
362 |
+
[2023-11-15 07:03:47,005][00663] Num frames 1200...
|
363 |
+
[2023-11-15 07:03:47,138][00663] Num frames 1300...
|
364 |
+
[2023-11-15 07:03:47,265][00663] Num frames 1400...
|
365 |
+
[2023-11-15 07:03:47,393][00663] Num frames 1500...
|
366 |
+
[2023-11-15 07:03:47,498][00663] Avg episode rewards: #0: 3.840, true rewards: #0: 3.840
|
367 |
+
[2023-11-15 07:03:47,500][00663] Avg episode reward: 3.840, avg true_objective: 3.840
|
368 |
+
[2023-11-15 07:03:47,584][00663] Num frames 1600...
|
369 |
+
[2023-11-15 07:03:47,719][00663] Num frames 1700...
|
370 |
+
[2023-11-15 07:03:47,849][00663] Num frames 1800...
|
371 |
+
[2023-11-15 07:03:47,973][00663] Num frames 1900...
|
372 |
+
[2023-11-15 07:03:48,055][00663] Avg episode rewards: #0: 3.840, true rewards: #0: 3.840
|
373 |
+
[2023-11-15 07:03:48,057][00663] Avg episode reward: 3.840, avg true_objective: 3.840
|
374 |
+
[2023-11-15 07:03:48,163][00663] Num frames 2000...
|
375 |
+
[2023-11-15 07:03:48,289][00663] Num frames 2100...
|
376 |
+
[2023-11-15 07:03:48,419][00663] Num frames 2200...
|
377 |
+
[2023-11-15 07:03:48,545][00663] Num frames 2300...
|
378 |
+
[2023-11-15 07:03:48,606][00663] Avg episode rewards: #0: 3.840, true rewards: #0: 3.840
|
379 |
+
[2023-11-15 07:03:48,607][00663] Avg episode reward: 3.840, avg true_objective: 3.840
|
380 |
+
[2023-11-15 07:03:48,741][00663] Num frames 2400...
|
381 |
+
[2023-11-15 07:03:48,869][00663] Num frames 2500...
|
382 |
+
[2023-11-15 07:03:48,992][00663] Num frames 2600...
|
383 |
+
[2023-11-15 07:03:49,160][00663] Avg episode rewards: #0: 3.840, true rewards: #0: 3.840
|
384 |
+
[2023-11-15 07:03:49,161][00663] Avg episode reward: 3.840, avg true_objective: 3.840
|
385 |
+
[2023-11-15 07:03:49,181][00663] Num frames 2700...
|
386 |
+
[2023-11-15 07:03:49,313][00663] Num frames 2800...
|
387 |
+
[2023-11-15 07:03:49,439][00663] Num frames 2900...
|
388 |
+
[2023-11-15 07:03:49,564][00663] Num frames 3000...
|
389 |
+
[2023-11-15 07:03:49,711][00663] Avg episode rewards: #0: 3.840, true rewards: #0: 3.840
|
390 |
+
[2023-11-15 07:03:49,713][00663] Avg episode reward: 3.840, avg true_objective: 3.840
|
391 |
+
[2023-11-15 07:03:49,757][00663] Num frames 3100...
|
392 |
+
[2023-11-15 07:03:49,883][00663] Num frames 3200...
|
393 |
+
[2023-11-15 07:03:50,006][00663] Num frames 3300...
|
394 |
+
[2023-11-15 07:03:50,148][00663] Num frames 3400...
|
395 |
+
[2023-11-15 07:03:50,274][00663] Avg episode rewards: #0: 3.840, true rewards: #0: 3.840
|
396 |
+
[2023-11-15 07:03:50,276][00663] Avg episode reward: 3.840, avg true_objective: 3.840
|
397 |
+
[2023-11-15 07:03:50,335][00663] Num frames 3500...
|
398 |
+
[2023-11-15 07:03:50,460][00663] Num frames 3600...
|
399 |
+
[2023-11-15 07:03:50,584][00663] Num frames 3700...
|
400 |
+
[2023-11-15 07:03:50,718][00663] Num frames 3800...
|
401 |
+
[2023-11-15 07:03:50,834][00663] Avg episode rewards: #0: 3.840, true rewards: #0: 3.840
|
402 |
+
[2023-11-15 07:03:50,836][00663] Avg episode reward: 3.840, avg true_objective: 3.840
|
403 |
+
[2023-11-15 07:04:09,945][00663] Replay video saved to /content/train_dir/default_experiment/replay.mp4!
|
404 |
+
[2023-11-15 07:04:24,386][00663] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json
|
405 |
+
[2023-11-15 07:04:24,389][00663] Overriding arg 'num_workers' with value 1 passed from command line
|
406 |
+
[2023-11-15 07:04:24,391][00663] Adding new argument 'no_render'=True that is not in the saved config file!
|
407 |
+
[2023-11-15 07:04:24,393][00663] Adding new argument 'save_video'=True that is not in the saved config file!
|
408 |
+
[2023-11-15 07:04:24,396][00663] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file!
|
409 |
+
[2023-11-15 07:04:24,398][00663] Adding new argument 'video_name'=None that is not in the saved config file!
|
410 |
+
[2023-11-15 07:04:24,400][00663] Adding new argument 'max_num_frames'=100000 that is not in the saved config file!
|
411 |
+
[2023-11-15 07:04:24,402][00663] Adding new argument 'max_num_episodes'=10 that is not in the saved config file!
|
412 |
+
[2023-11-15 07:04:24,403][00663] Adding new argument 'push_to_hub'=True that is not in the saved config file!
|
413 |
+
[2023-11-15 07:04:24,404][00663] Adding new argument 'hf_repository'='nikxtaco/rl_course_vizdoom_health_gathering_supreme' that is not in the saved config file!
|
414 |
+
[2023-11-15 07:04:24,405][00663] Adding new argument 'policy_index'=0 that is not in the saved config file!
|
415 |
+
[2023-11-15 07:04:24,406][00663] Adding new argument 'eval_deterministic'=False that is not in the saved config file!
|
416 |
+
[2023-11-15 07:04:24,407][00663] Adding new argument 'train_script'=None that is not in the saved config file!
|
417 |
+
[2023-11-15 07:04:24,409][00663] Adding new argument 'enjoy_script'=None that is not in the saved config file!
|
418 |
+
[2023-11-15 07:04:24,410][00663] Using frameskip 1 and render_action_repeat=4 for evaluation
|
419 |
+
[2023-11-15 07:04:24,447][00663] RunningMeanStd input shape: (3, 72, 128)
|
420 |
+
[2023-11-15 07:04:24,449][00663] RunningMeanStd input shape: (1,)
|
421 |
+
[2023-11-15 07:04:24,462][00663] ConvEncoder: input_channels=3
|
422 |
+
[2023-11-15 07:04:24,498][00663] Conv encoder output size: 512
|
423 |
+
[2023-11-15 07:04:24,499][00663] Policy head output size: 512
|
424 |
+
[2023-11-15 07:04:24,518][00663] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000002_8192.pth...
|
425 |
+
[2023-11-15 07:04:24,954][00663] Num frames 100...
|
426 |
+
[2023-11-15 07:04:25,083][00663] Num frames 200...
|
427 |
+
[2023-11-15 07:04:25,208][00663] Num frames 300...
|
428 |
+
[2023-11-15 07:04:25,402][00663] Avg episode rewards: #0: 3.840, true rewards: #0: 3.840
|
429 |
+
[2023-11-15 07:04:25,405][00663] Avg episode reward: 3.840, avg true_objective: 3.840
|
430 |
+
[2023-11-15 07:04:25,438][00663] Num frames 400...
|
431 |
+
[2023-11-15 07:04:25,627][00663] Num frames 500...
|
432 |
+
[2023-11-15 07:04:25,826][00663] Num frames 600...
|
433 |
+
[2023-11-15 07:04:26,017][00663] Num frames 700...
|
434 |
+
[2023-11-15 07:04:26,206][00663] Avg episode rewards: #0: 3.840, true rewards: #0: 3.840
|
435 |
+
[2023-11-15 07:04:26,208][00663] Avg episode reward: 3.840, avg true_objective: 3.840
|
436 |
+
[2023-11-15 07:04:26,273][00663] Num frames 800...
|
437 |
+
[2023-11-15 07:04:26,472][00663] Num frames 900...
|
438 |
+
[2023-11-15 07:04:26,666][00663] Num frames 1000...
|
439 |
+
[2023-11-15 07:04:26,875][00663] Num frames 1100...
|
440 |
+
[2023-11-15 07:04:27,057][00663] Num frames 1200...
|
441 |
+
[2023-11-15 07:04:27,142][00663] Avg episode rewards: #0: 4.387, true rewards: #0: 4.053
|
442 |
+
[2023-11-15 07:04:27,145][00663] Avg episode reward: 4.387, avg true_objective: 4.053
|
443 |
+
[2023-11-15 07:04:27,312][00663] Num frames 1300...
|
444 |
+
[2023-11-15 07:04:27,525][00663] Num frames 1400...
|
445 |
+
[2023-11-15 07:04:27,728][00663] Num frames 1500...
|
446 |
+
[2023-11-15 07:04:27,956][00663] Num frames 1600...
|
447 |
+
[2023-11-15 07:04:28,012][00663] Avg episode rewards: #0: 4.250, true rewards: #0: 4.000
|
448 |
+
[2023-11-15 07:04:28,014][00663] Avg episode reward: 4.250, avg true_objective: 4.000
|
449 |
+
[2023-11-15 07:04:28,206][00663] Num frames 1700...
|
450 |
+
[2023-11-15 07:04:28,392][00663] Num frames 1800...
|
451 |
+
[2023-11-15 07:04:28,570][00663] Num frames 1900...
|
452 |
+
[2023-11-15 07:04:28,780][00663] Avg episode rewards: #0: 4.168, true rewards: #0: 3.968
|
453 |
+
[2023-11-15 07:04:28,782][00663] Avg episode reward: 4.168, avg true_objective: 3.968
|
454 |
+
[2023-11-15 07:04:28,815][00663] Num frames 2000...
|
455 |
+
[2023-11-15 07:04:28,992][00663] Num frames 2100...
|
456 |
+
[2023-11-15 07:04:29,175][00663] Num frames 2200...
|
457 |
+
[2023-11-15 07:04:29,362][00663] Num frames 2300...
|
458 |
+
[2023-11-15 07:04:29,549][00663] Avg episode rewards: #0: 4.113, true rewards: #0: 3.947
|
459 |
+
[2023-11-15 07:04:29,551][00663] Avg episode reward: 4.113, avg true_objective: 3.947
|
460 |
+
[2023-11-15 07:04:29,615][00663] Num frames 2400...
|
461 |
+
[2023-11-15 07:04:29,807][00663] Num frames 2500...
|
462 |
+
[2023-11-15 07:04:29,995][00663] Num frames 2600...
|
463 |
+
[2023-11-15 07:04:30,176][00663] Num frames 2700...
|
464 |
+
[2023-11-15 07:04:30,332][00663] Avg episode rewards: #0: 4.074, true rewards: #0: 3.931
|
465 |
+
[2023-11-15 07:04:30,335][00663] Avg episode reward: 4.074, avg true_objective: 3.931
|
466 |
+
[2023-11-15 07:04:30,431][00663] Num frames 2800...
|
467 |
+
[2023-11-15 07:04:30,613][00663] Num frames 2900...
|
468 |
+
[2023-11-15 07:04:30,802][00663] Num frames 3000...
|
469 |
+
[2023-11-15 07:04:30,988][00663] Num frames 3100...
|
470 |
+
[2023-11-15 07:04:31,163][00663] Avg episode rewards: #0: 4.353, true rewards: #0: 3.977
|
471 |
+
[2023-11-15 07:04:31,164][00663] Avg episode reward: 4.353, avg true_objective: 3.977
|
472 |
+
[2023-11-15 07:04:31,190][00663] Num frames 3200...
|
473 |
+
[2023-11-15 07:04:31,325][00663] Num frames 3300...
|
474 |
+
[2023-11-15 07:04:31,455][00663] Num frames 3400...
|
475 |
+
[2023-11-15 07:04:31,583][00663] Num frames 3500...
|
476 |
+
[2023-11-15 07:04:31,725][00663] Avg episode rewards: #0: 4.296, true rewards: #0: 3.962
|
477 |
+
[2023-11-15 07:04:31,726][00663] Avg episode reward: 4.296, avg true_objective: 3.962
|
478 |
+
[2023-11-15 07:04:31,772][00663] Num frames 3600...
|
479 |
+
[2023-11-15 07:04:31,903][00663] Num frames 3700...
|
480 |
+
[2023-11-15 07:04:32,033][00663] Num frames 3800...
|
481 |
+
[2023-11-15 07:04:32,159][00663] Num frames 3900...
|
482 |
+
[2023-11-15 07:04:32,287][00663] Avg episode rewards: #0: 4.250, true rewards: #0: 3.950
|
483 |
+
[2023-11-15 07:04:32,288][00663] Avg episode reward: 4.250, avg true_objective: 3.950
|
484 |
+
[2023-11-15 07:04:53,857][00663] Replay video saved to /content/train_dir/default_experiment/replay.mp4!
|