Upload . with huggingface_hub
Browse files- .gitattributes +1 -0
- .summary/0/events.out.tfevents.1677145364.9ce75a2e03cc +3 -0
- README.md +56 -0
- checkpoint_p0/best_000000843_3452928_reward_29.378.pth +3 -0
- checkpoint_p0/checkpoint_000000927_3796992.pth +3 -0
- checkpoint_p0/checkpoint_000000978_4005888.pth +3 -0
- config.json +142 -0
- replay.mp4 +3 -0
- sf_log.txt +1055 -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.1677145364.9ce75a2e03cc
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ebcf6ba05cfc4fe2a351b0cb1e6622ef921e5bef40fe09058b693421e8e290c7
|
3 |
+
size 454070
|
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: 12.12 +/- 5.77
|
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 moodlep/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_000000843_3452928_reward_29.378.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e0fc1e0c50af94670a66583f35f508316c7ca0518cbda1bd3c6d08b22cf220e5
|
3 |
+
size 34928614
|
checkpoint_p0/checkpoint_000000927_3796992.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0e9dc3f54b5d51ac4e6cd26c90aff17484a5c3990ecc13461ec8ad5c42ab5657
|
3 |
+
size 34929028
|
checkpoint_p0/checkpoint_000000978_4005888.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a7c921d644bc44ae1c8966feee82af16d57e5ba77ca7c3db956344e5cd0ab90a
|
3 |
+
size 34929028
|
config.json
ADDED
@@ -0,0 +1,142 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"help": false,
|
3 |
+
"algo": "APPO",
|
4 |
+
"env": "doom_health_gathering_supreme",
|
5 |
+
"experiment": "default_experiment",
|
6 |
+
"train_dir": "/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": 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:ce83fddaf50a57af88fe1351cd41c1666001ab45532f5b9e5fda5f47ff427f8d
|
3 |
+
size 23856418
|
sf_log.txt
ADDED
@@ -0,0 +1,1055 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
[2023-02-23 09:42:48,897][11985] Saving configuration to /content/train_dir/default_experiment/config.json...
|
2 |
+
[2023-02-23 09:42:48,905][11985] Rollout worker 0 uses device cpu
|
3 |
+
[2023-02-23 09:42:48,906][11985] Rollout worker 1 uses device cpu
|
4 |
+
[2023-02-23 09:42:48,908][11985] Rollout worker 2 uses device cpu
|
5 |
+
[2023-02-23 09:42:48,909][11985] Rollout worker 3 uses device cpu
|
6 |
+
[2023-02-23 09:42:48,912][11985] Rollout worker 4 uses device cpu
|
7 |
+
[2023-02-23 09:42:48,919][11985] Rollout worker 5 uses device cpu
|
8 |
+
[2023-02-23 09:42:48,923][11985] Rollout worker 6 uses device cpu
|
9 |
+
[2023-02-23 09:42:48,924][11985] Rollout worker 7 uses device cpu
|
10 |
+
[2023-02-23 09:42:49,107][11985] Using GPUs [0] for process 0 (actually maps to GPUs [0])
|
11 |
+
[2023-02-23 09:42:49,109][11985] InferenceWorker_p0-w0: min num requests: 2
|
12 |
+
[2023-02-23 09:42:49,154][11985] Starting all processes...
|
13 |
+
[2023-02-23 09:42:49,156][11985] Starting process learner_proc0
|
14 |
+
[2023-02-23 09:42:49,248][11985] Starting all processes...
|
15 |
+
[2023-02-23 09:42:49,259][11985] Starting process inference_proc0-0
|
16 |
+
[2023-02-23 09:42:49,260][11985] Starting process rollout_proc0
|
17 |
+
[2023-02-23 09:42:49,261][11985] Starting process rollout_proc1
|
18 |
+
[2023-02-23 09:42:49,261][11985] Starting process rollout_proc2
|
19 |
+
[2023-02-23 09:42:49,261][11985] Starting process rollout_proc3
|
20 |
+
[2023-02-23 09:42:49,261][11985] Starting process rollout_proc4
|
21 |
+
[2023-02-23 09:42:49,261][11985] Starting process rollout_proc5
|
22 |
+
[2023-02-23 09:42:49,261][11985] Starting process rollout_proc6
|
23 |
+
[2023-02-23 09:42:49,261][11985] Starting process rollout_proc7
|
24 |
+
[2023-02-23 09:42:54,027][12181] Using GPUs [0] for process 0 (actually maps to GPUs [0])
|
25 |
+
[2023-02-23 09:42:54,028][12181] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for learning process 0
|
26 |
+
[2023-02-23 09:42:54,488][12201] Worker 1 uses CPU cores [1]
|
27 |
+
[2023-02-23 09:42:54,627][12195] Using GPUs [0] for process 0 (actually maps to GPUs [0])
|
28 |
+
[2023-02-23 09:42:54,627][12195] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for inference process 0
|
29 |
+
[2023-02-23 09:42:54,638][12203] Worker 3 uses CPU cores [3]
|
30 |
+
[2023-02-23 09:42:54,878][12196] Worker 0 uses CPU cores [0]
|
31 |
+
[2023-02-23 09:42:54,935][12204] Worker 4 uses CPU cores [0]
|
32 |
+
[2023-02-23 09:42:54,984][12208] Worker 7 uses CPU cores [3]
|
33 |
+
[2023-02-23 09:42:55,013][12206] Worker 6 uses CPU cores [2]
|
34 |
+
[2023-02-23 09:42:55,026][12181] Num visible devices: 1
|
35 |
+
[2023-02-23 09:42:55,029][12195] Num visible devices: 1
|
36 |
+
[2023-02-23 09:42:55,048][12181] Starting seed is not provided
|
37 |
+
[2023-02-23 09:42:55,048][12181] Using GPUs [0] for process 0 (actually maps to GPUs [0])
|
38 |
+
[2023-02-23 09:42:55,048][12181] Initializing actor-critic model on device cuda:0
|
39 |
+
[2023-02-23 09:42:55,049][12181] RunningMeanStd input shape: (3, 72, 128)
|
40 |
+
[2023-02-23 09:42:55,050][12181] RunningMeanStd input shape: (1,)
|
41 |
+
[2023-02-23 09:42:55,062][12205] Worker 5 uses CPU cores [1]
|
42 |
+
[2023-02-23 09:42:55,063][12181] ConvEncoder: input_channels=3
|
43 |
+
[2023-02-23 09:42:55,066][12202] Worker 2 uses CPU cores [2]
|
44 |
+
[2023-02-23 09:42:55,348][12181] Conv encoder output size: 512
|
45 |
+
[2023-02-23 09:42:55,349][12181] Policy head output size: 512
|
46 |
+
[2023-02-23 09:42:55,394][12181] Created Actor Critic model with architecture:
|
47 |
+
[2023-02-23 09:42:55,394][12181] 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 |
+
[2023-02-23 09:43:02,976][12181] Using optimizer <class 'torch.optim.adam.Adam'>
|
89 |
+
[2023-02-23 09:43:02,976][12181] No checkpoints found
|
90 |
+
[2023-02-23 09:43:02,977][12181] Did not load from checkpoint, starting from scratch!
|
91 |
+
[2023-02-23 09:43:02,977][12181] Initialized policy 0 weights for model version 0
|
92 |
+
[2023-02-23 09:43:02,979][12181] Using GPUs [0] for process 0 (actually maps to GPUs [0])
|
93 |
+
[2023-02-23 09:43:02,981][12181] LearnerWorker_p0 finished initialization!
|
94 |
+
[2023-02-23 09:43:03,080][12195] RunningMeanStd input shape: (3, 72, 128)
|
95 |
+
[2023-02-23 09:43:03,082][12195] RunningMeanStd input shape: (1,)
|
96 |
+
[2023-02-23 09:43:03,098][12195] ConvEncoder: input_channels=3
|
97 |
+
[2023-02-23 09:43:03,199][12195] Conv encoder output size: 512
|
98 |
+
[2023-02-23 09:43:03,199][12195] Policy head output size: 512
|
99 |
+
[2023-02-23 09:43:04,449][11985] Fps is (10 sec: nan, 60 sec: nan, 300 sec: nan). Total num frames: 0. Throughput: 0: nan. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0)
|
100 |
+
[2023-02-23 09:43:05,356][11985] Inference worker 0-0 is ready!
|
101 |
+
[2023-02-23 09:43:05,358][11985] All inference workers are ready! Signal rollout workers to start!
|
102 |
+
[2023-02-23 09:43:05,406][12206] Doom resolution: 160x120, resize resolution: (128, 72)
|
103 |
+
[2023-02-23 09:43:05,409][12196] Doom resolution: 160x120, resize resolution: (128, 72)
|
104 |
+
[2023-02-23 09:43:05,409][12202] Doom resolution: 160x120, resize resolution: (128, 72)
|
105 |
+
[2023-02-23 09:43:05,409][12201] Doom resolution: 160x120, resize resolution: (128, 72)
|
106 |
+
[2023-02-23 09:43:05,410][12205] Doom resolution: 160x120, resize resolution: (128, 72)
|
107 |
+
[2023-02-23 09:43:05,411][12204] Doom resolution: 160x120, resize resolution: (128, 72)
|
108 |
+
[2023-02-23 09:43:05,408][12208] Doom resolution: 160x120, resize resolution: (128, 72)
|
109 |
+
[2023-02-23 09:43:05,417][12203] Doom resolution: 160x120, resize resolution: (128, 72)
|
110 |
+
[2023-02-23 09:43:05,842][12196] Decorrelating experience for 0 frames...
|
111 |
+
[2023-02-23 09:43:05,842][12206] Decorrelating experience for 0 frames...
|
112 |
+
[2023-02-23 09:43:05,890][12201] Decorrelating experience for 0 frames...
|
113 |
+
[2023-02-23 09:43:05,895][12205] Decorrelating experience for 0 frames...
|
114 |
+
[2023-02-23 09:43:06,179][12206] Decorrelating experience for 32 frames...
|
115 |
+
[2023-02-23 09:43:06,304][12203] Decorrelating experience for 0 frames...
|
116 |
+
[2023-02-23 09:43:06,465][12196] Decorrelating experience for 32 frames...
|
117 |
+
[2023-02-23 09:43:06,464][12208] Decorrelating experience for 0 frames...
|
118 |
+
[2023-02-23 09:43:06,568][12205] Decorrelating experience for 32 frames...
|
119 |
+
[2023-02-23 09:43:06,614][12204] Decorrelating experience for 0 frames...
|
120 |
+
[2023-02-23 09:43:06,709][12206] Decorrelating experience for 64 frames...
|
121 |
+
[2023-02-23 09:43:06,738][12203] Decorrelating experience for 32 frames...
|
122 |
+
[2023-02-23 09:43:07,174][12204] Decorrelating experience for 32 frames...
|
123 |
+
[2023-02-23 09:43:07,198][12202] Decorrelating experience for 0 frames...
|
124 |
+
[2023-02-23 09:43:07,332][12205] Decorrelating experience for 64 frames...
|
125 |
+
[2023-02-23 09:43:07,338][12206] Decorrelating experience for 96 frames...
|
126 |
+
[2023-02-23 09:43:07,386][12201] Decorrelating experience for 32 frames...
|
127 |
+
[2023-02-23 09:43:07,388][12196] Decorrelating experience for 64 frames...
|
128 |
+
[2023-02-23 09:43:07,461][12208] Decorrelating experience for 32 frames...
|
129 |
+
[2023-02-23 09:43:07,517][12203] Decorrelating experience for 64 frames...
|
130 |
+
[2023-02-23 09:43:07,771][12202] Decorrelating experience for 32 frames...
|
131 |
+
[2023-02-23 09:43:07,890][12204] Decorrelating experience for 64 frames...
|
132 |
+
[2023-02-23 09:43:08,094][12205] Decorrelating experience for 96 frames...
|
133 |
+
[2023-02-23 09:43:08,226][12201] Decorrelating experience for 64 frames...
|
134 |
+
[2023-02-23 09:43:08,279][12203] Decorrelating experience for 96 frames...
|
135 |
+
[2023-02-23 09:43:08,298][12202] Decorrelating experience for 64 frames...
|
136 |
+
[2023-02-23 09:43:08,300][12208] Decorrelating experience for 64 frames...
|
137 |
+
[2023-02-23 09:43:08,542][12201] Decorrelating experience for 96 frames...
|
138 |
+
[2023-02-23 09:43:08,597][12196] Decorrelating experience for 96 frames...
|
139 |
+
[2023-02-23 09:43:08,679][12204] Decorrelating experience for 96 frames...
|
140 |
+
[2023-02-23 09:43:08,775][12202] Decorrelating experience for 96 frames...
|
141 |
+
[2023-02-23 09:43:08,813][12208] Decorrelating experience for 96 frames...
|
142 |
+
[2023-02-23 09:43:09,087][11985] Heartbeat connected on Batcher_0
|
143 |
+
[2023-02-23 09:43:09,092][11985] Heartbeat connected on LearnerWorker_p0
|
144 |
+
[2023-02-23 09:43:09,116][11985] Heartbeat connected on RolloutWorker_w0
|
145 |
+
[2023-02-23 09:43:09,121][11985] Heartbeat connected on RolloutWorker_w1
|
146 |
+
[2023-02-23 09:43:09,127][11985] Heartbeat connected on RolloutWorker_w2
|
147 |
+
[2023-02-23 09:43:09,131][11985] Heartbeat connected on RolloutWorker_w3
|
148 |
+
[2023-02-23 09:43:09,136][11985] Heartbeat connected on RolloutWorker_w4
|
149 |
+
[2023-02-23 09:43:09,140][11985] Heartbeat connected on RolloutWorker_w5
|
150 |
+
[2023-02-23 09:43:09,145][11985] Heartbeat connected on RolloutWorker_w6
|
151 |
+
[2023-02-23 09:43:09,149][11985] Heartbeat connected on RolloutWorker_w7
|
152 |
+
[2023-02-23 09:43:09,449][11985] 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)
|
153 |
+
[2023-02-23 09:43:11,163][11985] Heartbeat connected on InferenceWorker_p0-w0
|
154 |
+
[2023-02-23 09:43:12,330][12181] Signal inference workers to stop experience collection...
|
155 |
+
[2023-02-23 09:43:12,338][12195] InferenceWorker_p0-w0: stopping experience collection
|
156 |
+
[2023-02-23 09:43:14,449][11985] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 236.0. Samples: 2360. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0)
|
157 |
+
[2023-02-23 09:43:14,451][11985] Avg episode reward: [(0, '2.158')]
|
158 |
+
[2023-02-23 09:43:15,043][12181] Signal inference workers to resume experience collection...
|
159 |
+
[2023-02-23 09:43:15,044][12195] InferenceWorker_p0-w0: resuming experience collection
|
160 |
+
[2023-02-23 09:43:19,449][11985] Fps is (10 sec: 3276.7, 60 sec: 2184.5, 300 sec: 2184.5). Total num frames: 32768. Throughput: 0: 355.5. Samples: 5332. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0)
|
161 |
+
[2023-02-23 09:43:19,455][11985] Avg episode reward: [(0, '3.785')]
|
162 |
+
[2023-02-23 09:43:20,203][12195] Updated weights for policy 0, policy_version 10 (0.0018)
|
163 |
+
[2023-02-23 09:43:24,449][11985] Fps is (10 sec: 7782.3, 60 sec: 3891.2, 300 sec: 3891.2). Total num frames: 77824. Throughput: 0: 897.3. Samples: 17946. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
|
164 |
+
[2023-02-23 09:43:24,452][11985] Avg episode reward: [(0, '4.565')]
|
165 |
+
[2023-02-23 09:43:24,722][12195] Updated weights for policy 0, policy_version 20 (0.0018)
|
166 |
+
[2023-02-23 09:43:28,925][12195] Updated weights for policy 0, policy_version 30 (0.0015)
|
167 |
+
[2023-02-23 09:43:29,449][11985] Fps is (10 sec: 9420.9, 60 sec: 5079.0, 300 sec: 5079.0). Total num frames: 126976. Throughput: 0: 1288.5. Samples: 32212. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
|
168 |
+
[2023-02-23 09:43:29,455][11985] Avg episode reward: [(0, '4.511')]
|
169 |
+
[2023-02-23 09:43:29,458][12181] Saving new best policy, reward=4.511!
|
170 |
+
[2023-02-23 09:43:34,348][12195] Updated weights for policy 0, policy_version 40 (0.0021)
|
171 |
+
[2023-02-23 09:43:34,449][11985] Fps is (10 sec: 8601.6, 60 sec: 5461.3, 300 sec: 5461.3). Total num frames: 163840. Throughput: 0: 1276.1. Samples: 38282. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
|
172 |
+
[2023-02-23 09:43:34,452][11985] Avg episode reward: [(0, '4.379')]
|
173 |
+
[2023-02-23 09:43:39,449][11985] Fps is (10 sec: 6963.2, 60 sec: 5617.4, 300 sec: 5617.4). Total num frames: 196608. Throughput: 0: 1386.5. Samples: 48528. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
|
174 |
+
[2023-02-23 09:43:39,453][11985] Avg episode reward: [(0, '4.551')]
|
175 |
+
[2023-02-23 09:43:39,528][12181] Saving new best policy, reward=4.551!
|
176 |
+
[2023-02-23 09:43:40,012][12195] Updated weights for policy 0, policy_version 50 (0.0012)
|
177 |
+
[2023-02-23 09:43:44,449][11985] Fps is (10 sec: 7782.4, 60 sec: 6041.6, 300 sec: 6041.6). Total num frames: 241664. Throughput: 0: 1543.3. Samples: 61734. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
|
178 |
+
[2023-02-23 09:43:44,451][11985] Avg episode reward: [(0, '4.583')]
|
179 |
+
[2023-02-23 09:43:44,459][12181] Saving new best policy, reward=4.583!
|
180 |
+
[2023-02-23 09:43:44,641][12195] Updated weights for policy 0, policy_version 60 (0.0016)
|
181 |
+
[2023-02-23 09:43:48,917][12195] Updated weights for policy 0, policy_version 70 (0.0015)
|
182 |
+
[2023-02-23 09:43:49,449][11985] Fps is (10 sec: 9420.6, 60 sec: 6462.5, 300 sec: 6462.5). Total num frames: 290816. Throughput: 0: 1525.8. Samples: 68662. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
|
183 |
+
[2023-02-23 09:43:49,452][11985] Avg episode reward: [(0, '4.312')]
|
184 |
+
[2023-02-23 09:43:54,449][11985] Fps is (10 sec: 8191.9, 60 sec: 6471.7, 300 sec: 6471.7). Total num frames: 323584. Throughput: 0: 1787.5. Samples: 80440. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
|
185 |
+
[2023-02-23 09:43:54,452][11985] Avg episode reward: [(0, '4.541')]
|
186 |
+
[2023-02-23 09:43:54,599][12195] Updated weights for policy 0, policy_version 80 (0.0012)
|
187 |
+
[2023-02-23 09:43:59,449][11985] Fps is (10 sec: 7372.8, 60 sec: 6628.1, 300 sec: 6628.1). Total num frames: 364544. Throughput: 0: 2003.7. Samples: 92528. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
|
188 |
+
[2023-02-23 09:43:59,451][11985] Avg episode reward: [(0, '4.515')]
|
189 |
+
[2023-02-23 09:43:59,496][12195] Updated weights for policy 0, policy_version 90 (0.0017)
|
190 |
+
[2023-02-23 09:44:03,900][12195] Updated weights for policy 0, policy_version 100 (0.0018)
|
191 |
+
[2023-02-23 09:44:04,449][11985] Fps is (10 sec: 9011.3, 60 sec: 6894.9, 300 sec: 6894.9). Total num frames: 413696. Throughput: 0: 2092.9. Samples: 99514. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
|
192 |
+
[2023-02-23 09:44:04,452][11985] Avg episode reward: [(0, '4.543')]
|
193 |
+
[2023-02-23 09:44:08,509][12195] Updated weights for policy 0, policy_version 110 (0.0023)
|
194 |
+
[2023-02-23 09:44:09,449][11985] Fps is (10 sec: 9011.3, 60 sec: 7577.6, 300 sec: 6994.7). Total num frames: 454656. Throughput: 0: 2114.2. Samples: 113084. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
|
195 |
+
[2023-02-23 09:44:09,452][11985] Avg episode reward: [(0, '4.431')]
|
196 |
+
[2023-02-23 09:44:14,269][12195] Updated weights for policy 0, policy_version 120 (0.0013)
|
197 |
+
[2023-02-23 09:44:14,449][11985] Fps is (10 sec: 7782.4, 60 sec: 8192.0, 300 sec: 7021.7). Total num frames: 491520. Throughput: 0: 2036.9. Samples: 123874. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
|
198 |
+
[2023-02-23 09:44:14,454][11985] Avg episode reward: [(0, '4.407')]
|
199 |
+
[2023-02-23 09:44:18,726][12195] Updated weights for policy 0, policy_version 130 (0.0017)
|
200 |
+
[2023-02-23 09:44:19,449][11985] Fps is (10 sec: 8192.1, 60 sec: 8396.8, 300 sec: 7154.3). Total num frames: 536576. Throughput: 0: 2050.7. Samples: 130564. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
|
201 |
+
[2023-02-23 09:44:19,452][11985] Avg episode reward: [(0, '4.499')]
|
202 |
+
[2023-02-23 09:44:23,056][12195] Updated weights for policy 0, policy_version 140 (0.0022)
|
203 |
+
[2023-02-23 09:44:24,449][11985] Fps is (10 sec: 9011.2, 60 sec: 8396.8, 300 sec: 7270.4). Total num frames: 581632. Throughput: 0: 2137.7. Samples: 144726. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
|
204 |
+
[2023-02-23 09:44:24,451][11985] Avg episode reward: [(0, '4.272')]
|
205 |
+
[2023-02-23 09:44:28,236][12195] Updated weights for policy 0, policy_version 150 (0.0018)
|
206 |
+
[2023-02-23 09:44:29,449][11985] Fps is (10 sec: 8192.0, 60 sec: 8192.0, 300 sec: 7276.4). Total num frames: 618496. Throughput: 0: 2098.8. Samples: 156180. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
|
207 |
+
[2023-02-23 09:44:29,454][11985] Avg episode reward: [(0, '4.315')]
|
208 |
+
[2023-02-23 09:44:33,827][12195] Updated weights for policy 0, policy_version 160 (0.0014)
|
209 |
+
[2023-02-23 09:44:34,449][11985] Fps is (10 sec: 7782.4, 60 sec: 8260.3, 300 sec: 7327.3). Total num frames: 659456. Throughput: 0: 2062.5. Samples: 161476. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
|
210 |
+
[2023-02-23 09:44:34,452][11985] Avg episode reward: [(0, '4.735')]
|
211 |
+
[2023-02-23 09:44:34,458][12181] Saving new best policy, reward=4.735!
|
212 |
+
[2023-02-23 09:44:38,376][12195] Updated weights for policy 0, policy_version 170 (0.0022)
|
213 |
+
[2023-02-23 09:44:39,449][11985] Fps is (10 sec: 8601.6, 60 sec: 8465.1, 300 sec: 7415.9). Total num frames: 704512. Throughput: 0: 2095.2. Samples: 174722. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
|
214 |
+
[2023-02-23 09:44:39,452][11985] Avg episode reward: [(0, '4.493')]
|
215 |
+
[2023-02-23 09:44:42,750][12195] Updated weights for policy 0, policy_version 180 (0.0014)
|
216 |
+
[2023-02-23 09:44:44,449][11985] Fps is (10 sec: 9011.2, 60 sec: 8465.1, 300 sec: 7495.7). Total num frames: 749568. Throughput: 0: 2125.3. Samples: 188168. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
|
217 |
+
[2023-02-23 09:44:44,451][11985] Avg episode reward: [(0, '4.674')]
|
218 |
+
[2023-02-23 09:44:44,465][12181] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000183_749568.pth...
|
219 |
+
[2023-02-23 09:44:48,389][12195] Updated weights for policy 0, policy_version 190 (0.0019)
|
220 |
+
[2023-02-23 09:44:49,449][11985] Fps is (10 sec: 7782.4, 60 sec: 8192.0, 300 sec: 7450.8). Total num frames: 782336. Throughput: 0: 2086.6. Samples: 193412. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
|
221 |
+
[2023-02-23 09:44:49,454][11985] Avg episode reward: [(0, '4.532')]
|
222 |
+
[2023-02-23 09:44:53,385][12195] Updated weights for policy 0, policy_version 200 (0.0019)
|
223 |
+
[2023-02-23 09:44:54,449][11985] Fps is (10 sec: 7782.4, 60 sec: 8396.8, 300 sec: 7521.7). Total num frames: 827392. Throughput: 0: 2052.5. Samples: 205446. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
|
224 |
+
[2023-02-23 09:44:54,458][11985] Avg episode reward: [(0, '4.616')]
|
225 |
+
[2023-02-23 09:44:57,684][12195] Updated weights for policy 0, policy_version 210 (0.0021)
|
226 |
+
[2023-02-23 09:44:59,449][11985] Fps is (10 sec: 9420.7, 60 sec: 8533.3, 300 sec: 7622.1). Total num frames: 876544. Throughput: 0: 2129.0. Samples: 219680. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
|
227 |
+
[2023-02-23 09:44:59,452][11985] Avg episode reward: [(0, '4.569')]
|
228 |
+
[2023-02-23 09:45:02,307][12195] Updated weights for policy 0, policy_version 220 (0.0019)
|
229 |
+
[2023-02-23 09:45:04,449][11985] Fps is (10 sec: 8601.3, 60 sec: 8328.5, 300 sec: 7611.7). Total num frames: 913408. Throughput: 0: 2120.4. Samples: 225982. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
|
230 |
+
[2023-02-23 09:45:04,451][11985] Avg episode reward: [(0, '4.635')]
|
231 |
+
[2023-02-23 09:45:08,111][12195] Updated weights for policy 0, policy_version 230 (0.0012)
|
232 |
+
[2023-02-23 09:45:09,449][11985] Fps is (10 sec: 7372.8, 60 sec: 8260.3, 300 sec: 7602.2). Total num frames: 950272. Throughput: 0: 2042.0. Samples: 236614. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
|
233 |
+
[2023-02-23 09:45:09,452][11985] Avg episode reward: [(0, '4.648')]
|
234 |
+
[2023-02-23 09:45:12,795][12195] Updated weights for policy 0, policy_version 240 (0.0016)
|
235 |
+
[2023-02-23 09:45:14,449][11985] Fps is (10 sec: 8192.3, 60 sec: 8396.8, 300 sec: 7656.4). Total num frames: 995328. Throughput: 0: 2088.3. Samples: 250152. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
|
236 |
+
[2023-02-23 09:45:14,451][11985] Avg episode reward: [(0, '4.570')]
|
237 |
+
[2023-02-23 09:45:17,063][12195] Updated weights for policy 0, policy_version 250 (0.0011)
|
238 |
+
[2023-02-23 09:45:19,449][11985] Fps is (10 sec: 9420.9, 60 sec: 8465.1, 300 sec: 7736.9). Total num frames: 1044480. Throughput: 0: 2127.3. Samples: 257206. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
|
239 |
+
[2023-02-23 09:45:19,452][11985] Avg episode reward: [(0, '4.853')]
|
240 |
+
[2023-02-23 09:45:19,461][12181] Saving new best policy, reward=4.853!
|
241 |
+
[2023-02-23 09:45:22,106][12195] Updated weights for policy 0, policy_version 260 (0.0015)
|
242 |
+
[2023-02-23 09:45:24,449][11985] Fps is (10 sec: 8601.6, 60 sec: 8328.5, 300 sec: 7723.9). Total num frames: 1081344. Throughput: 0: 2095.6. Samples: 269026. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
|
243 |
+
[2023-02-23 09:45:24,452][11985] Avg episode reward: [(0, '4.798')]
|
244 |
+
[2023-02-23 09:45:27,692][12195] Updated weights for policy 0, policy_version 270 (0.0017)
|
245 |
+
[2023-02-23 09:45:29,449][11985] Fps is (10 sec: 7782.4, 60 sec: 8396.8, 300 sec: 7740.0). Total num frames: 1122304. Throughput: 0: 2066.0. Samples: 281136. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
|
246 |
+
[2023-02-23 09:45:29,454][11985] Avg episode reward: [(0, '5.125')]
|
247 |
+
[2023-02-23 09:45:29,458][12181] Saving new best policy, reward=5.125!
|
248 |
+
[2023-02-23 09:45:32,104][12195] Updated weights for policy 0, policy_version 280 (0.0017)
|
249 |
+
[2023-02-23 09:45:34,449][11985] Fps is (10 sec: 8601.6, 60 sec: 8465.1, 300 sec: 7782.4). Total num frames: 1167360. Throughput: 0: 2105.3. Samples: 288152. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
|
250 |
+
[2023-02-23 09:45:34,452][11985] Avg episode reward: [(0, '5.136')]
|
251 |
+
[2023-02-23 09:45:34,459][12181] Saving new best policy, reward=5.136!
|
252 |
+
[2023-02-23 09:45:36,400][12195] Updated weights for policy 0, policy_version 290 (0.0014)
|
253 |
+
[2023-02-23 09:45:39,449][11985] Fps is (10 sec: 8601.6, 60 sec: 8396.8, 300 sec: 7795.6). Total num frames: 1208320. Throughput: 0: 2136.4. Samples: 301582. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
|
254 |
+
[2023-02-23 09:45:39,457][11985] Avg episode reward: [(0, '5.722')]
|
255 |
+
[2023-02-23 09:45:39,461][12181] Saving new best policy, reward=5.722!
|
256 |
+
[2023-02-23 09:45:41,934][12195] Updated weights for policy 0, policy_version 300 (0.0013)
|
257 |
+
[2023-02-23 09:45:44,449][11985] Fps is (10 sec: 7782.4, 60 sec: 8260.3, 300 sec: 7782.4). Total num frames: 1245184. Throughput: 0: 2055.5. Samples: 312178. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
|
258 |
+
[2023-02-23 09:45:44,451][11985] Avg episode reward: [(0, '5.316')]
|
259 |
+
[2023-02-23 09:45:47,191][12195] Updated weights for policy 0, policy_version 310 (0.0016)
|
260 |
+
[2023-02-23 09:45:49,449][11985] Fps is (10 sec: 8192.0, 60 sec: 8465.1, 300 sec: 7819.6). Total num frames: 1290240. Throughput: 0: 2060.9. Samples: 318724. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
|
261 |
+
[2023-02-23 09:45:49,452][11985] Avg episode reward: [(0, '5.515')]
|
262 |
+
[2023-02-23 09:45:51,437][12195] Updated weights for policy 0, policy_version 320 (0.0021)
|
263 |
+
[2023-02-23 09:45:54,449][11985] Fps is (10 sec: 9011.3, 60 sec: 8465.1, 300 sec: 7854.7). Total num frames: 1335296. Throughput: 0: 2139.2. Samples: 332878. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
|
264 |
+
[2023-02-23 09:45:54,451][11985] Avg episode reward: [(0, '5.299')]
|
265 |
+
[2023-02-23 09:45:55,929][12195] Updated weights for policy 0, policy_version 330 (0.0016)
|
266 |
+
[2023-02-23 09:45:59,449][11985] Fps is (10 sec: 8601.6, 60 sec: 8328.5, 300 sec: 7864.3). Total num frames: 1376256. Throughput: 0: 2103.2. Samples: 344796. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
|
267 |
+
[2023-02-23 09:45:59,452][11985] Avg episode reward: [(0, '5.580')]
|
268 |
+
[2023-02-23 09:46:01,522][12195] Updated weights for policy 0, policy_version 340 (0.0014)
|
269 |
+
[2023-02-23 09:46:04,449][11985] Fps is (10 sec: 7782.3, 60 sec: 8328.6, 300 sec: 7850.7). Total num frames: 1413120. Throughput: 0: 2068.1. Samples: 350270. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
|
270 |
+
[2023-02-23 09:46:04,452][11985] Avg episode reward: [(0, '5.824')]
|
271 |
+
[2023-02-23 09:46:04,461][12181] Saving new best policy, reward=5.824!
|
272 |
+
[2023-02-23 09:46:06,311][12195] Updated weights for policy 0, policy_version 350 (0.0015)
|
273 |
+
[2023-02-23 09:46:09,449][11985] Fps is (10 sec: 8601.5, 60 sec: 8533.3, 300 sec: 7904.2). Total num frames: 1462272. Throughput: 0: 2112.4. Samples: 364084. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
|
274 |
+
[2023-02-23 09:46:09,452][11985] Avg episode reward: [(0, '5.443')]
|
275 |
+
[2023-02-23 09:46:10,588][12195] Updated weights for policy 0, policy_version 360 (0.0012)
|
276 |
+
[2023-02-23 09:46:14,449][11985] Fps is (10 sec: 9420.9, 60 sec: 8533.3, 300 sec: 7933.3). Total num frames: 1507328. Throughput: 0: 2148.3. Samples: 377810. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
|
277 |
+
[2023-02-23 09:46:14,455][11985] Avg episode reward: [(0, '5.873')]
|
278 |
+
[2023-02-23 09:46:14,464][12181] Saving new best policy, reward=5.873!
|
279 |
+
[2023-02-23 09:46:15,362][12195] Updated weights for policy 0, policy_version 370 (0.0012)
|
280 |
+
[2023-02-23 09:46:19,450][11985] Fps is (10 sec: 8191.6, 60 sec: 8328.4, 300 sec: 7918.9). Total num frames: 1544192. Throughput: 0: 2109.6. Samples: 383086. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
|
281 |
+
[2023-02-23 09:46:19,453][11985] Avg episode reward: [(0, '5.740')]
|
282 |
+
[2023-02-23 09:46:20,916][12195] Updated weights for policy 0, policy_version 380 (0.0014)
|
283 |
+
[2023-02-23 09:46:24,449][11985] Fps is (10 sec: 8191.8, 60 sec: 8465.0, 300 sec: 7946.2). Total num frames: 1589248. Throughput: 0: 2087.3. Samples: 395510. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
|
284 |
+
[2023-02-23 09:46:24,451][11985] Avg episode reward: [(0, '6.755')]
|
285 |
+
[2023-02-23 09:46:24,466][12181] Saving new best policy, reward=6.755!
|
286 |
+
[2023-02-23 09:46:25,310][12195] Updated weights for policy 0, policy_version 390 (0.0013)
|
287 |
+
[2023-02-23 09:46:29,449][11985] Fps is (10 sec: 9011.8, 60 sec: 8533.3, 300 sec: 7972.2). Total num frames: 1634304. Throughput: 0: 2166.4. Samples: 409666. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
|
288 |
+
[2023-02-23 09:46:29,451][11985] Avg episode reward: [(0, '7.916')]
|
289 |
+
[2023-02-23 09:46:29,462][12181] Saving new best policy, reward=7.916!
|
290 |
+
[2023-02-23 09:46:29,693][12195] Updated weights for policy 0, policy_version 400 (0.0020)
|
291 |
+
[2023-02-23 09:46:34,449][11985] Fps is (10 sec: 8601.7, 60 sec: 8465.1, 300 sec: 7977.4). Total num frames: 1675264. Throughput: 0: 2166.8. Samples: 416232. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
|
292 |
+
[2023-02-23 09:46:34,452][11985] Avg episode reward: [(0, '7.913')]
|
293 |
+
[2023-02-23 09:46:34,768][12195] Updated weights for policy 0, policy_version 410 (0.0012)
|
294 |
+
[2023-02-23 09:46:39,449][11985] Fps is (10 sec: 7782.4, 60 sec: 8396.8, 300 sec: 7963.4). Total num frames: 1712128. Throughput: 0: 2091.8. Samples: 427008. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
|
295 |
+
[2023-02-23 09:46:39,452][11985] Avg episode reward: [(0, '7.571')]
|
296 |
+
[2023-02-23 09:46:40,104][12195] Updated weights for policy 0, policy_version 420 (0.0021)
|
297 |
+
[2023-02-23 09:46:44,449][11985] Fps is (10 sec: 8192.0, 60 sec: 8533.3, 300 sec: 7987.2). Total num frames: 1757184. Throughput: 0: 2131.4. Samples: 440708. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
|
298 |
+
[2023-02-23 09:46:44,452][11985] Avg episode reward: [(0, '9.034')]
|
299 |
+
[2023-02-23 09:46:44,503][12181] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000430_1761280.pth...
|
300 |
+
[2023-02-23 09:46:44,510][12195] Updated weights for policy 0, policy_version 430 (0.0012)
|
301 |
+
[2023-02-23 09:46:44,605][12181] Saving new best policy, reward=9.034!
|
302 |
+
[2023-02-23 09:46:48,871][12195] Updated weights for policy 0, policy_version 440 (0.0019)
|
303 |
+
[2023-02-23 09:46:49,449][11985] Fps is (10 sec: 9420.8, 60 sec: 8601.6, 300 sec: 8028.2). Total num frames: 1806336. Throughput: 0: 2165.1. Samples: 447698. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
|
304 |
+
[2023-02-23 09:46:49,452][11985] Avg episode reward: [(0, '9.109')]
|
305 |
+
[2023-02-23 09:46:49,455][12181] Saving new best policy, reward=9.109!
|
306 |
+
[2023-02-23 09:46:54,449][11985] Fps is (10 sec: 8192.1, 60 sec: 8396.8, 300 sec: 7996.1). Total num frames: 1839104. Throughput: 0: 2118.8. Samples: 459430. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
|
307 |
+
[2023-02-23 09:46:54,452][11985] Avg episode reward: [(0, '9.757')]
|
308 |
+
[2023-02-23 09:46:54,465][12181] Saving new best policy, reward=9.757!
|
309 |
+
[2023-02-23 09:46:54,465][12195] Updated weights for policy 0, policy_version 450 (0.0018)
|
310 |
+
[2023-02-23 09:46:59,411][12195] Updated weights for policy 0, policy_version 460 (0.0016)
|
311 |
+
[2023-02-23 09:46:59,449][11985] Fps is (10 sec: 7782.4, 60 sec: 8465.1, 300 sec: 8017.7). Total num frames: 1884160. Throughput: 0: 2085.8. Samples: 471672. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
|
312 |
+
[2023-02-23 09:46:59,451][11985] Avg episode reward: [(0, '11.222')]
|
313 |
+
[2023-02-23 09:46:59,455][12181] Saving new best policy, reward=11.222!
|
314 |
+
[2023-02-23 09:47:03,610][12195] Updated weights for policy 0, policy_version 470 (0.0015)
|
315 |
+
[2023-02-23 09:47:04,449][11985] Fps is (10 sec: 9011.2, 60 sec: 8601.6, 300 sec: 8038.4). Total num frames: 1929216. Throughput: 0: 2128.4. Samples: 478862. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0)
|
316 |
+
[2023-02-23 09:47:04,451][11985] Avg episode reward: [(0, '10.488')]
|
317 |
+
[2023-02-23 09:47:08,197][12195] Updated weights for policy 0, policy_version 480 (0.0020)
|
318 |
+
[2023-02-23 09:47:09,449][11985] Fps is (10 sec: 9011.0, 60 sec: 8533.3, 300 sec: 8058.2). Total num frames: 1974272. Throughput: 0: 2154.6. Samples: 492468. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
|
319 |
+
[2023-02-23 09:47:09,452][11985] Avg episode reward: [(0, '11.818')]
|
320 |
+
[2023-02-23 09:47:09,454][12181] Saving new best policy, reward=11.818!
|
321 |
+
[2023-02-23 09:47:14,031][12195] Updated weights for policy 0, policy_version 490 (0.0016)
|
322 |
+
[2023-02-23 09:47:14,450][11985] Fps is (10 sec: 7781.9, 60 sec: 8328.4, 300 sec: 8028.1). Total num frames: 2007040. Throughput: 0: 2077.1. Samples: 503138. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
|
323 |
+
[2023-02-23 09:47:14,455][11985] Avg episode reward: [(0, '12.534')]
|
324 |
+
[2023-02-23 09:47:14,467][12181] Saving new best policy, reward=12.534!
|
325 |
+
[2023-02-23 09:47:18,603][12195] Updated weights for policy 0, policy_version 500 (0.0012)
|
326 |
+
[2023-02-23 09:47:19,449][11985] Fps is (10 sec: 8192.2, 60 sec: 8533.4, 300 sec: 8063.5). Total num frames: 2056192. Throughput: 0: 2078.4. Samples: 509760. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
|
327 |
+
[2023-02-23 09:47:19,451][11985] Avg episode reward: [(0, '13.720')]
|
328 |
+
[2023-02-23 09:47:19,458][12181] Saving new best policy, reward=13.720!
|
329 |
+
[2023-02-23 09:47:22,759][12195] Updated weights for policy 0, policy_version 510 (0.0016)
|
330 |
+
[2023-02-23 09:47:24,449][11985] Fps is (10 sec: 9421.4, 60 sec: 8533.4, 300 sec: 8081.7). Total num frames: 2101248. Throughput: 0: 2161.0. Samples: 524252. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
|
331 |
+
[2023-02-23 09:47:24,451][11985] Avg episode reward: [(0, '16.638')]
|
332 |
+
[2023-02-23 09:47:24,505][12181] Saving new best policy, reward=16.638!
|
333 |
+
[2023-02-23 09:47:27,636][12195] Updated weights for policy 0, policy_version 520 (0.0014)
|
334 |
+
[2023-02-23 09:47:29,449][11985] Fps is (10 sec: 8601.3, 60 sec: 8465.0, 300 sec: 8083.8). Total num frames: 2142208. Throughput: 0: 2120.6. Samples: 536134. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
|
335 |
+
[2023-02-23 09:47:29,452][11985] Avg episode reward: [(0, '17.176')]
|
336 |
+
[2023-02-23 09:47:29,458][12181] Saving new best policy, reward=17.176!
|
337 |
+
[2023-02-23 09:47:33,238][12195] Updated weights for policy 0, policy_version 530 (0.0015)
|
338 |
+
[2023-02-23 09:47:34,449][11985] Fps is (10 sec: 7782.4, 60 sec: 8396.8, 300 sec: 8070.6). Total num frames: 2179072. Throughput: 0: 2087.7. Samples: 541644. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
|
339 |
+
[2023-02-23 09:47:34,451][11985] Avg episode reward: [(0, '16.530')]
|
340 |
+
[2023-02-23 09:47:37,540][12195] Updated weights for policy 0, policy_version 540 (0.0013)
|
341 |
+
[2023-02-23 09:47:39,449][11985] Fps is (10 sec: 8601.9, 60 sec: 8601.6, 300 sec: 8102.6). Total num frames: 2228224. Throughput: 0: 2133.3. Samples: 555430. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
|
342 |
+
[2023-02-23 09:47:39,452][11985] Avg episode reward: [(0, '17.124')]
|
343 |
+
[2023-02-23 09:47:41,919][12195] Updated weights for policy 0, policy_version 550 (0.0025)
|
344 |
+
[2023-02-23 09:47:44,449][11985] Fps is (10 sec: 9420.8, 60 sec: 8601.6, 300 sec: 8118.9). Total num frames: 2273280. Throughput: 0: 2160.5. Samples: 568896. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
|
345 |
+
[2023-02-23 09:47:44,455][11985] Avg episode reward: [(0, '20.636')]
|
346 |
+
[2023-02-23 09:47:44,463][12181] Saving new best policy, reward=20.636!
|
347 |
+
[2023-02-23 09:47:47,342][12195] Updated weights for policy 0, policy_version 560 (0.0019)
|
348 |
+
[2023-02-23 09:47:49,453][11985] Fps is (10 sec: 7779.4, 60 sec: 8328.0, 300 sec: 8091.3). Total num frames: 2306048. Throughput: 0: 2115.3. Samples: 574058. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
|
349 |
+
[2023-02-23 09:47:49,455][11985] Avg episode reward: [(0, '21.991')]
|
350 |
+
[2023-02-23 09:47:49,461][12181] Saving new best policy, reward=21.991!
|
351 |
+
[2023-02-23 09:47:52,645][12195] Updated weights for policy 0, policy_version 570 (0.0026)
|
352 |
+
[2023-02-23 09:47:54,449][11985] Fps is (10 sec: 7782.4, 60 sec: 8533.3, 300 sec: 8107.3). Total num frames: 2351104. Throughput: 0: 2082.1. Samples: 586162. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
|
353 |
+
[2023-02-23 09:47:54,454][11985] Avg episode reward: [(0, '21.684')]
|
354 |
+
[2023-02-23 09:47:56,960][12195] Updated weights for policy 0, policy_version 580 (0.0022)
|
355 |
+
[2023-02-23 09:47:59,449][11985] Fps is (10 sec: 9014.6, 60 sec: 8533.3, 300 sec: 8122.6). Total num frames: 2396160. Throughput: 0: 2161.1. Samples: 600384. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
|
356 |
+
[2023-02-23 09:47:59,451][11985] Avg episode reward: [(0, '20.133')]
|
357 |
+
[2023-02-23 09:48:01,287][12195] Updated weights for policy 0, policy_version 590 (0.0027)
|
358 |
+
[2023-02-23 09:48:04,457][11985] Fps is (10 sec: 8594.7, 60 sec: 8463.9, 300 sec: 8261.2). Total num frames: 2437120. Throughput: 0: 2155.1. Samples: 606756. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
|
359 |
+
[2023-02-23 09:48:04,460][11985] Avg episode reward: [(0, '19.120')]
|
360 |
+
[2023-02-23 09:48:07,052][12195] Updated weights for policy 0, policy_version 600 (0.0012)
|
361 |
+
[2023-02-23 09:48:09,449][11985] Fps is (10 sec: 7782.4, 60 sec: 8328.6, 300 sec: 8386.4). Total num frames: 2473984. Throughput: 0: 2070.9. Samples: 617442. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
|
362 |
+
[2023-02-23 09:48:09,452][11985] Avg episode reward: [(0, '19.500')]
|
363 |
+
[2023-02-23 09:48:11,830][12195] Updated weights for policy 0, policy_version 610 (0.0010)
|
364 |
+
[2023-02-23 09:48:14,449][11985] Fps is (10 sec: 8198.6, 60 sec: 8533.4, 300 sec: 8428.0). Total num frames: 2519040. Throughput: 0: 2114.1. Samples: 631268. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
|
365 |
+
[2023-02-23 09:48:14,453][11985] Avg episode reward: [(0, '19.848')]
|
366 |
+
[2023-02-23 09:48:16,219][12195] Updated weights for policy 0, policy_version 620 (0.0012)
|
367 |
+
[2023-02-23 09:48:19,449][11985] Fps is (10 sec: 9420.6, 60 sec: 8533.3, 300 sec: 8441.9). Total num frames: 2568192. Throughput: 0: 2149.9. Samples: 638392. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
|
368 |
+
[2023-02-23 09:48:19,454][11985] Avg episode reward: [(0, '20.705')]
|
369 |
+
[2023-02-23 09:48:20,894][12195] Updated weights for policy 0, policy_version 630 (0.0014)
|
370 |
+
[2023-02-23 09:48:24,449][11985] Fps is (10 sec: 8601.6, 60 sec: 8396.8, 300 sec: 8400.3). Total num frames: 2605056. Throughput: 0: 2103.4. Samples: 650084. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
|
371 |
+
[2023-02-23 09:48:24,452][11985] Avg episode reward: [(0, '19.771')]
|
372 |
+
[2023-02-23 09:48:26,658][12195] Updated weights for policy 0, policy_version 640 (0.0015)
|
373 |
+
[2023-02-23 09:48:29,449][11985] Fps is (10 sec: 7782.6, 60 sec: 8396.8, 300 sec: 8414.2). Total num frames: 2646016. Throughput: 0: 2072.8. Samples: 662174. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
|
374 |
+
[2023-02-23 09:48:29,454][11985] Avg episode reward: [(0, '20.309')]
|
375 |
+
[2023-02-23 09:48:31,096][12195] Updated weights for policy 0, policy_version 650 (0.0019)
|
376 |
+
[2023-02-23 09:48:34,449][11985] Fps is (10 sec: 8601.4, 60 sec: 8533.3, 300 sec: 8455.8). Total num frames: 2691072. Throughput: 0: 2115.9. Samples: 669266. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
|
377 |
+
[2023-02-23 09:48:34,452][11985] Avg episode reward: [(0, '20.493')]
|
378 |
+
[2023-02-23 09:48:35,536][12195] Updated weights for policy 0, policy_version 660 (0.0024)
|
379 |
+
[2023-02-23 09:48:39,449][11985] Fps is (10 sec: 8601.6, 60 sec: 8396.8, 300 sec: 8441.9). Total num frames: 2732032. Throughput: 0: 2142.2. Samples: 682562. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
|
380 |
+
[2023-02-23 09:48:39,452][11985] Avg episode reward: [(0, '20.372')]
|
381 |
+
[2023-02-23 09:48:40,741][12195] Updated weights for policy 0, policy_version 670 (0.0013)
|
382 |
+
[2023-02-23 09:48:44,449][11985] Fps is (10 sec: 7782.5, 60 sec: 8260.3, 300 sec: 8400.3). Total num frames: 2768896. Throughput: 0: 2059.5. Samples: 693062. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
|
383 |
+
[2023-02-23 09:48:44,452][11985] Avg episode reward: [(0, '20.828')]
|
384 |
+
[2023-02-23 09:48:44,460][12181] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000676_2768896.pth...
|
385 |
+
[2023-02-23 09:48:44,559][12181] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000183_749568.pth
|
386 |
+
[2023-02-23 09:48:46,209][12195] Updated weights for policy 0, policy_version 680 (0.0014)
|
387 |
+
[2023-02-23 09:48:49,449][11985] Fps is (10 sec: 8192.0, 60 sec: 8465.6, 300 sec: 8441.9). Total num frames: 2813952. Throughput: 0: 2065.5. Samples: 699688. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
|
388 |
+
[2023-02-23 09:48:49,453][11985] Avg episode reward: [(0, '21.928')]
|
389 |
+
[2023-02-23 09:48:50,514][12195] Updated weights for policy 0, policy_version 690 (0.0021)
|
390 |
+
[2023-02-23 09:48:54,449][11985] Fps is (10 sec: 9011.3, 60 sec: 8465.1, 300 sec: 8455.8). Total num frames: 2859008. Throughput: 0: 2143.3. Samples: 713892. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
|
391 |
+
[2023-02-23 09:48:54,452][11985] Avg episode reward: [(0, '23.629')]
|
392 |
+
[2023-02-23 09:48:54,501][12181] Saving new best policy, reward=23.629!
|
393 |
+
[2023-02-23 09:48:55,004][12195] Updated weights for policy 0, policy_version 700 (0.0017)
|
394 |
+
[2023-02-23 09:48:59,449][11985] Fps is (10 sec: 8601.6, 60 sec: 8396.8, 300 sec: 8428.0). Total num frames: 2899968. Throughput: 0: 2095.2. Samples: 725554. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
|
395 |
+
[2023-02-23 09:48:59,452][11985] Avg episode reward: [(0, '23.590')]
|
396 |
+
[2023-02-23 09:49:00,519][12195] Updated weights for policy 0, policy_version 710 (0.0021)
|
397 |
+
[2023-02-23 09:49:04,449][11985] Fps is (10 sec: 8192.0, 60 sec: 8397.9, 300 sec: 8428.0). Total num frames: 2940928. Throughput: 0: 2061.2. Samples: 731146. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
|
398 |
+
[2023-02-23 09:49:04,451][11985] Avg episode reward: [(0, '22.421')]
|
399 |
+
[2023-02-23 09:49:05,289][12195] Updated weights for policy 0, policy_version 720 (0.0013)
|
400 |
+
[2023-02-23 09:49:09,449][11985] Fps is (10 sec: 8601.6, 60 sec: 8533.3, 300 sec: 8455.8). Total num frames: 2985984. Throughput: 0: 2117.2. Samples: 745360. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
|
401 |
+
[2023-02-23 09:49:09,452][11985] Avg episode reward: [(0, '22.684')]
|
402 |
+
[2023-02-23 09:49:09,634][12195] Updated weights for policy 0, policy_version 730 (0.0012)
|
403 |
+
[2023-02-23 09:49:14,394][12195] Updated weights for policy 0, policy_version 740 (0.0015)
|
404 |
+
[2023-02-23 09:49:14,453][11985] Fps is (10 sec: 9007.6, 60 sec: 8532.8, 300 sec: 8455.7). Total num frames: 3031040. Throughput: 0: 2134.4. Samples: 758232. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
|
405 |
+
[2023-02-23 09:49:14,458][11985] Avg episode reward: [(0, '22.940')]
|
406 |
+
[2023-02-23 09:49:19,449][11985] Fps is (10 sec: 7782.3, 60 sec: 8260.3, 300 sec: 8414.2). Total num frames: 3063808. Throughput: 0: 2094.2. Samples: 763504. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
|
407 |
+
[2023-02-23 09:49:19,452][11985] Avg episode reward: [(0, '25.597')]
|
408 |
+
[2023-02-23 09:49:19,454][12181] Saving new best policy, reward=25.597!
|
409 |
+
[2023-02-23 09:49:20,260][12195] Updated weights for policy 0, policy_version 750 (0.0014)
|
410 |
+
[2023-02-23 09:49:24,449][11985] Fps is (10 sec: 7785.4, 60 sec: 8396.8, 300 sec: 8441.9). Total num frames: 3108864. Throughput: 0: 2071.9. Samples: 775796. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
|
411 |
+
[2023-02-23 09:49:24,455][11985] Avg episode reward: [(0, '25.070')]
|
412 |
+
[2023-02-23 09:49:24,654][12195] Updated weights for policy 0, policy_version 760 (0.0024)
|
413 |
+
[2023-02-23 09:49:29,028][12195] Updated weights for policy 0, policy_version 770 (0.0019)
|
414 |
+
[2023-02-23 09:49:29,449][11985] Fps is (10 sec: 9420.9, 60 sec: 8533.3, 300 sec: 8469.7). Total num frames: 3158016. Throughput: 0: 2154.8. Samples: 790028. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
|
415 |
+
[2023-02-23 09:49:29,455][11985] Avg episode reward: [(0, '22.735')]
|
416 |
+
[2023-02-23 09:49:34,129][12195] Updated weights for policy 0, policy_version 780 (0.0014)
|
417 |
+
[2023-02-23 09:49:34,449][11985] Fps is (10 sec: 8601.7, 60 sec: 8396.8, 300 sec: 8441.9). Total num frames: 3194880. Throughput: 0: 2147.2. Samples: 796314. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
|
418 |
+
[2023-02-23 09:49:34,451][11985] Avg episode reward: [(0, '23.693')]
|
419 |
+
[2023-02-23 09:49:39,449][11985] Fps is (10 sec: 7372.8, 60 sec: 8328.5, 300 sec: 8414.2). Total num frames: 3231744. Throughput: 0: 2070.2. Samples: 807052. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
|
420 |
+
[2023-02-23 09:49:39,451][11985] Avg episode reward: [(0, '25.573')]
|
421 |
+
[2023-02-23 09:49:39,571][12195] Updated weights for policy 0, policy_version 790 (0.0018)
|
422 |
+
[2023-02-23 09:49:43,817][12195] Updated weights for policy 0, policy_version 800 (0.0016)
|
423 |
+
[2023-02-23 09:49:44,449][11985] Fps is (10 sec: 8601.5, 60 sec: 8533.3, 300 sec: 8469.7). Total num frames: 3280896. Throughput: 0: 2123.3. Samples: 821104. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
|
424 |
+
[2023-02-23 09:49:44,458][11985] Avg episode reward: [(0, '25.345')]
|
425 |
+
[2023-02-23 09:49:48,188][12195] Updated weights for policy 0, policy_version 810 (0.0017)
|
426 |
+
[2023-02-23 09:49:49,449][11985] Fps is (10 sec: 9420.8, 60 sec: 8533.3, 300 sec: 8469.7). Total num frames: 3325952. Throughput: 0: 2156.2. Samples: 828176. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
|
427 |
+
[2023-02-23 09:49:49,453][11985] Avg episode reward: [(0, '26.339')]
|
428 |
+
[2023-02-23 09:49:49,463][12181] Saving new best policy, reward=26.339!
|
429 |
+
[2023-02-23 09:49:53,630][12195] Updated weights for policy 0, policy_version 820 (0.0018)
|
430 |
+
[2023-02-23 09:49:54,449][11985] Fps is (10 sec: 8192.1, 60 sec: 8396.8, 300 sec: 8428.0). Total num frames: 3362816. Throughput: 0: 2101.7. Samples: 839938. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
|
431 |
+
[2023-02-23 09:49:54,452][11985] Avg episode reward: [(0, '28.001')]
|
432 |
+
[2023-02-23 09:49:54,466][12181] Saving new best policy, reward=28.001!
|
433 |
+
[2023-02-23 09:49:58,602][12195] Updated weights for policy 0, policy_version 830 (0.0017)
|
434 |
+
[2023-02-23 09:49:59,449][11985] Fps is (10 sec: 8192.0, 60 sec: 8465.1, 300 sec: 8455.8). Total num frames: 3407872. Throughput: 0: 2094.3. Samples: 852468. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
|
435 |
+
[2023-02-23 09:49:59,452][11985] Avg episode reward: [(0, '28.260')]
|
436 |
+
[2023-02-23 09:49:59,454][12181] Saving new best policy, reward=28.260!
|
437 |
+
[2023-02-23 09:50:02,897][12195] Updated weights for policy 0, policy_version 840 (0.0012)
|
438 |
+
[2023-02-23 09:50:04,449][11985] Fps is (10 sec: 9011.1, 60 sec: 8533.3, 300 sec: 8483.6). Total num frames: 3452928. Throughput: 0: 2135.8. Samples: 859614. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
|
439 |
+
[2023-02-23 09:50:04,452][11985] Avg episode reward: [(0, '29.378')]
|
440 |
+
[2023-02-23 09:50:04,461][12181] Saving new best policy, reward=29.378!
|
441 |
+
[2023-02-23 09:50:07,221][12195] Updated weights for policy 0, policy_version 850 (0.0020)
|
442 |
+
[2023-02-23 09:50:09,449][11985] Fps is (10 sec: 8601.6, 60 sec: 8465.1, 300 sec: 8469.7). Total num frames: 3493888. Throughput: 0: 2160.4. Samples: 873012. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
|
443 |
+
[2023-02-23 09:50:09,452][11985] Avg episode reward: [(0, '28.820')]
|
444 |
+
[2023-02-23 09:50:12,931][12195] Updated weights for policy 0, policy_version 860 (0.0025)
|
445 |
+
[2023-02-23 09:50:14,449][11985] Fps is (10 sec: 7782.5, 60 sec: 8329.1, 300 sec: 8428.0). Total num frames: 3530752. Throughput: 0: 2090.0. Samples: 884080. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
|
446 |
+
[2023-02-23 09:50:14,454][11985] Avg episode reward: [(0, '25.738')]
|
447 |
+
[2023-02-23 09:50:17,653][12195] Updated weights for policy 0, policy_version 870 (0.0017)
|
448 |
+
[2023-02-23 09:50:19,449][11985] Fps is (10 sec: 8601.4, 60 sec: 8601.6, 300 sec: 8469.7). Total num frames: 3579904. Throughput: 0: 2100.9. Samples: 890856. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
|
449 |
+
[2023-02-23 09:50:19,452][11985] Avg episode reward: [(0, '24.015')]
|
450 |
+
[2023-02-23 09:50:21,905][12195] Updated weights for policy 0, policy_version 880 (0.0024)
|
451 |
+
[2023-02-23 09:50:24,449][11985] Fps is (10 sec: 9830.2, 60 sec: 8669.9, 300 sec: 8497.5). Total num frames: 3629056. Throughput: 0: 2189.2. Samples: 905566. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
|
452 |
+
[2023-02-23 09:50:24,452][11985] Avg episode reward: [(0, '25.122')]
|
453 |
+
[2023-02-23 09:50:26,457][12195] Updated weights for policy 0, policy_version 890 (0.0012)
|
454 |
+
[2023-02-23 09:50:29,455][11985] Fps is (10 sec: 8596.4, 60 sec: 8464.2, 300 sec: 8469.5). Total num frames: 3665920. Throughput: 0: 2133.0. Samples: 917104. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
|
455 |
+
[2023-02-23 09:50:29,461][11985] Avg episode reward: [(0, '24.957')]
|
456 |
+
[2023-02-23 09:50:32,106][12195] Updated weights for policy 0, policy_version 900 (0.0024)
|
457 |
+
[2023-02-23 09:50:34,449][11985] Fps is (10 sec: 7782.3, 60 sec: 8533.3, 300 sec: 8469.7). Total num frames: 3706880. Throughput: 0: 2102.6. Samples: 922792. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
|
458 |
+
[2023-02-23 09:50:34,452][11985] Avg episode reward: [(0, '25.811')]
|
459 |
+
[2023-02-23 09:50:36,509][12195] Updated weights for policy 0, policy_version 910 (0.0019)
|
460 |
+
[2023-02-23 09:50:39,449][11985] Fps is (10 sec: 8607.0, 60 sec: 8669.9, 300 sec: 8497.5). Total num frames: 3751936. Throughput: 0: 2155.0. Samples: 936912. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
|
461 |
+
[2023-02-23 09:50:39,452][11985] Avg episode reward: [(0, '25.578')]
|
462 |
+
[2023-02-23 09:50:40,826][12195] Updated weights for policy 0, policy_version 920 (0.0011)
|
463 |
+
[2023-02-23 09:50:44,449][11985] Fps is (10 sec: 9011.4, 60 sec: 8601.6, 300 sec: 8497.5). Total num frames: 3796992. Throughput: 0: 2170.7. Samples: 950150. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
|
464 |
+
[2023-02-23 09:50:44,452][11985] Avg episode reward: [(0, '24.904')]
|
465 |
+
[2023-02-23 09:50:44,462][12181] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000927_3796992.pth...
|
466 |
+
[2023-02-23 09:50:44,563][12181] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000430_1761280.pth
|
467 |
+
[2023-02-23 09:50:46,062][12195] Updated weights for policy 0, policy_version 930 (0.0011)
|
468 |
+
[2023-02-23 09:50:49,449][11985] Fps is (10 sec: 7782.4, 60 sec: 8396.8, 300 sec: 8455.8). Total num frames: 3829760. Throughput: 0: 2123.5. Samples: 955170. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
|
469 |
+
[2023-02-23 09:50:49,452][11985] Avg episode reward: [(0, '25.615')]
|
470 |
+
[2023-02-23 09:50:51,603][12195] Updated weights for policy 0, policy_version 940 (0.0015)
|
471 |
+
[2023-02-23 09:50:54,449][11985] Fps is (10 sec: 7782.3, 60 sec: 8533.3, 300 sec: 8469.7). Total num frames: 3874816. Throughput: 0: 2094.1. Samples: 967248. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
|
472 |
+
[2023-02-23 09:50:54,451][11985] Avg episode reward: [(0, '27.631')]
|
473 |
+
[2023-02-23 09:50:55,995][12195] Updated weights for policy 0, policy_version 950 (0.0022)
|
474 |
+
[2023-02-23 09:50:59,449][11985] Fps is (10 sec: 9011.2, 60 sec: 8533.3, 300 sec: 8497.5). Total num frames: 3919872. Throughput: 0: 2166.4. Samples: 981568. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
|
475 |
+
[2023-02-23 09:50:59,451][11985] Avg episode reward: [(0, '28.712')]
|
476 |
+
[2023-02-23 09:51:00,319][12195] Updated weights for policy 0, policy_version 960 (0.0012)
|
477 |
+
[2023-02-23 09:51:04,451][11985] Fps is (10 sec: 8599.8, 60 sec: 8464.8, 300 sec: 8469.6). Total num frames: 3960832. Throughput: 0: 2158.0. Samples: 987970. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
|
478 |
+
[2023-02-23 09:51:04,453][11985] Avg episode reward: [(0, '28.934')]
|
479 |
+
[2023-02-23 09:51:05,559][12195] Updated weights for policy 0, policy_version 970 (0.0016)
|
480 |
+
[2023-02-23 09:51:09,449][11985] Fps is (10 sec: 8191.9, 60 sec: 8465.1, 300 sec: 8455.8). Total num frames: 4001792. Throughput: 0: 2082.8. Samples: 999292. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
|
481 |
+
[2023-02-23 09:51:09,452][11985] Avg episode reward: [(0, '27.953')]
|
482 |
+
[2023-02-23 09:51:09,666][12181] Stopping Batcher_0...
|
483 |
+
[2023-02-23 09:51:09,667][12181] Loop batcher_evt_loop terminating...
|
484 |
+
[2023-02-23 09:51:09,673][11985] Component Batcher_0 stopped!
|
485 |
+
[2023-02-23 09:51:09,678][12181] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
|
486 |
+
[2023-02-23 09:51:09,686][11985] Component RolloutWorker_w1 stopped!
|
487 |
+
[2023-02-23 09:51:09,688][11985] Component RolloutWorker_w3 stopped!
|
488 |
+
[2023-02-23 09:51:09,686][12203] Stopping RolloutWorker_w3...
|
489 |
+
[2023-02-23 09:51:09,690][11985] Component RolloutWorker_w7 stopped!
|
490 |
+
[2023-02-23 09:51:09,692][12203] Loop rollout_proc3_evt_loop terminating...
|
491 |
+
[2023-02-23 09:51:09,693][12201] Stopping RolloutWorker_w1...
|
492 |
+
[2023-02-23 09:51:09,697][12201] Loop rollout_proc1_evt_loop terminating...
|
493 |
+
[2023-02-23 09:51:09,687][12208] Stopping RolloutWorker_w7...
|
494 |
+
[2023-02-23 09:51:09,699][12208] Loop rollout_proc7_evt_loop terminating...
|
495 |
+
[2023-02-23 09:51:09,702][11985] Component RolloutWorker_w5 stopped!
|
496 |
+
[2023-02-23 09:51:09,708][12204] Stopping RolloutWorker_w4...
|
497 |
+
[2023-02-23 09:51:09,710][12204] Loop rollout_proc4_evt_loop terminating...
|
498 |
+
[2023-02-23 09:51:09,711][12195] Weights refcount: 2 0
|
499 |
+
[2023-02-23 09:51:09,708][11985] Component RolloutWorker_w4 stopped!
|
500 |
+
[2023-02-23 09:51:09,705][12205] Stopping RolloutWorker_w5...
|
501 |
+
[2023-02-23 09:51:09,714][12205] Loop rollout_proc5_evt_loop terminating...
|
502 |
+
[2023-02-23 09:51:09,715][12196] Stopping RolloutWorker_w0...
|
503 |
+
[2023-02-23 09:51:09,716][12196] Loop rollout_proc0_evt_loop terminating...
|
504 |
+
[2023-02-23 09:51:09,715][12195] Stopping InferenceWorker_p0-w0...
|
505 |
+
[2023-02-23 09:51:09,715][11985] Component RolloutWorker_w0 stopped!
|
506 |
+
[2023-02-23 09:51:09,717][12195] Loop inference_proc0-0_evt_loop terminating...
|
507 |
+
[2023-02-23 09:51:09,717][11985] Component InferenceWorker_p0-w0 stopped!
|
508 |
+
[2023-02-23 09:51:09,728][12206] Stopping RolloutWorker_w6...
|
509 |
+
[2023-02-23 09:51:09,729][12206] Loop rollout_proc6_evt_loop terminating...
|
510 |
+
[2023-02-23 09:51:09,728][11985] Component RolloutWorker_w6 stopped!
|
511 |
+
[2023-02-23 09:51:09,741][12202] Stopping RolloutWorker_w2...
|
512 |
+
[2023-02-23 09:51:09,741][12202] Loop rollout_proc2_evt_loop terminating...
|
513 |
+
[2023-02-23 09:51:09,741][11985] Component RolloutWorker_w2 stopped!
|
514 |
+
[2023-02-23 09:51:09,781][12181] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000676_2768896.pth
|
515 |
+
[2023-02-23 09:51:09,788][12181] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
|
516 |
+
[2023-02-23 09:51:09,905][12181] Stopping LearnerWorker_p0...
|
517 |
+
[2023-02-23 09:51:09,905][11985] Component LearnerWorker_p0 stopped!
|
518 |
+
[2023-02-23 09:51:09,907][12181] Loop learner_proc0_evt_loop terminating...
|
519 |
+
[2023-02-23 09:51:09,911][11985] Waiting for process learner_proc0 to stop...
|
520 |
+
[2023-02-23 09:51:11,333][11985] Waiting for process inference_proc0-0 to join...
|
521 |
+
[2023-02-23 09:51:11,336][11985] Waiting for process rollout_proc0 to join...
|
522 |
+
[2023-02-23 09:51:11,338][11985] Waiting for process rollout_proc1 to join...
|
523 |
+
[2023-02-23 09:51:11,340][11985] Waiting for process rollout_proc2 to join...
|
524 |
+
[2023-02-23 09:51:11,342][11985] Waiting for process rollout_proc3 to join...
|
525 |
+
[2023-02-23 09:51:11,345][11985] Waiting for process rollout_proc4 to join...
|
526 |
+
[2023-02-23 09:51:11,346][11985] Waiting for process rollout_proc5 to join...
|
527 |
+
[2023-02-23 09:51:11,348][11985] Waiting for process rollout_proc6 to join...
|
528 |
+
[2023-02-23 09:51:11,351][11985] Waiting for process rollout_proc7 to join...
|
529 |
+
[2023-02-23 09:51:11,353][11985] Batcher 0 profile tree view:
|
530 |
+
batching: 19.3320, releasing_batches: 0.0301
|
531 |
+
[2023-02-23 09:51:11,354][11985] InferenceWorker_p0-w0 profile tree view:
|
532 |
+
wait_policy: 0.0001
|
533 |
+
wait_policy_total: 72.7663
|
534 |
+
update_model: 6.4008
|
535 |
+
weight_update: 0.0012
|
536 |
+
one_step: 0.0028
|
537 |
+
handle_policy_step: 376.2500
|
538 |
+
deserialize: 14.5737, stack: 2.6149, obs_to_device_normalize: 101.7087, forward: 165.2253, send_messages: 18.9011
|
539 |
+
prepare_outputs: 54.3567
|
540 |
+
to_cpu: 36.7975
|
541 |
+
[2023-02-23 09:51:11,356][11985] Learner 0 profile tree view:
|
542 |
+
misc: 0.0058, prepare_batch: 13.4537
|
543 |
+
train: 60.3458
|
544 |
+
epoch_init: 0.0055, minibatch_init: 0.0060, losses_postprocess: 0.5459, kl_divergence: 0.4910, after_optimizer: 27.1247
|
545 |
+
calculate_losses: 20.4763
|
546 |
+
losses_init: 0.0036, forward_head: 1.0775, bptt_initial: 14.3494, tail: 0.8022, advantages_returns: 0.2661, losses: 1.9835
|
547 |
+
bptt: 1.7620
|
548 |
+
bptt_forward_core: 1.6849
|
549 |
+
update: 11.2384
|
550 |
+
clip: 1.2855
|
551 |
+
[2023-02-23 09:51:11,357][11985] RolloutWorker_w0 profile tree view:
|
552 |
+
wait_for_trajectories: 0.2543, enqueue_policy_requests: 11.5761, env_step: 310.7096, overhead: 12.3420, complete_rollouts: 2.2334
|
553 |
+
save_policy_outputs: 11.3773
|
554 |
+
split_output_tensors: 5.6039
|
555 |
+
[2023-02-23 09:51:11,359][11985] RolloutWorker_w7 profile tree view:
|
556 |
+
wait_for_trajectories: 0.2208, enqueue_policy_requests: 11.6518, env_step: 310.6223, overhead: 12.3694, complete_rollouts: 2.3541
|
557 |
+
save_policy_outputs: 11.4765
|
558 |
+
split_output_tensors: 5.6588
|
559 |
+
[2023-02-23 09:51:11,362][11985] Loop Runner_EvtLoop terminating...
|
560 |
+
[2023-02-23 09:51:11,364][11985] Runner profile tree view:
|
561 |
+
main_loop: 502.2108
|
562 |
+
[2023-02-23 09:51:11,366][11985] Collected {0: 4005888}, FPS: 7976.5
|
563 |
+
[2023-02-23 09:56:07,776][11985] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json
|
564 |
+
[2023-02-23 09:56:07,778][11985] Overriding arg 'num_workers' with value 1 passed from command line
|
565 |
+
[2023-02-23 09:56:07,780][11985] Adding new argument 'no_render'=True that is not in the saved config file!
|
566 |
+
[2023-02-23 09:56:07,782][11985] Adding new argument 'save_video'=True that is not in the saved config file!
|
567 |
+
[2023-02-23 09:56:07,783][11985] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file!
|
568 |
+
[2023-02-23 09:56:07,785][11985] Adding new argument 'video_name'=None that is not in the saved config file!
|
569 |
+
[2023-02-23 09:56:07,787][11985] Adding new argument 'max_num_frames'=1000000000.0 that is not in the saved config file!
|
570 |
+
[2023-02-23 09:56:07,789][11985] Adding new argument 'max_num_episodes'=10 that is not in the saved config file!
|
571 |
+
[2023-02-23 09:56:07,791][11985] Adding new argument 'push_to_hub'=False that is not in the saved config file!
|
572 |
+
[2023-02-23 09:56:07,793][11985] Adding new argument 'hf_repository'=None that is not in the saved config file!
|
573 |
+
[2023-02-23 09:56:07,794][11985] Adding new argument 'policy_index'=0 that is not in the saved config file!
|
574 |
+
[2023-02-23 09:56:07,796][11985] Adding new argument 'eval_deterministic'=False that is not in the saved config file!
|
575 |
+
[2023-02-23 09:56:07,797][11985] Adding new argument 'train_script'=None that is not in the saved config file!
|
576 |
+
[2023-02-23 09:56:07,800][11985] Adding new argument 'enjoy_script'=None that is not in the saved config file!
|
577 |
+
[2023-02-23 09:56:07,802][11985] Using frameskip 1 and render_action_repeat=4 for evaluation
|
578 |
+
[2023-02-23 09:56:07,818][11985] Doom resolution: 160x120, resize resolution: (128, 72)
|
579 |
+
[2023-02-23 09:56:07,821][11985] RunningMeanStd input shape: (3, 72, 128)
|
580 |
+
[2023-02-23 09:56:07,824][11985] RunningMeanStd input shape: (1,)
|
581 |
+
[2023-02-23 09:56:07,839][11985] ConvEncoder: input_channels=3
|
582 |
+
[2023-02-23 09:56:08,547][11985] Conv encoder output size: 512
|
583 |
+
[2023-02-23 09:56:08,549][11985] Policy head output size: 512
|
584 |
+
[2023-02-23 09:56:10,819][11985] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
|
585 |
+
[2023-02-23 09:56:12,057][11985] Num frames 100...
|
586 |
+
[2023-02-23 09:56:12,162][11985] Num frames 200...
|
587 |
+
[2023-02-23 09:56:12,268][11985] Num frames 300...
|
588 |
+
[2023-02-23 09:56:12,369][11985] Num frames 400...
|
589 |
+
[2023-02-23 09:56:12,471][11985] Num frames 500...
|
590 |
+
[2023-02-23 09:56:12,571][11985] Num frames 600...
|
591 |
+
[2023-02-23 09:56:12,647][11985] Avg episode rewards: #0: 14.180, true rewards: #0: 6.180
|
592 |
+
[2023-02-23 09:56:12,649][11985] Avg episode reward: 14.180, avg true_objective: 6.180
|
593 |
+
[2023-02-23 09:56:12,745][11985] Num frames 700...
|
594 |
+
[2023-02-23 09:56:12,844][11985] Num frames 800...
|
595 |
+
[2023-02-23 09:56:12,949][11985] Num frames 900...
|
596 |
+
[2023-02-23 09:56:13,070][11985] Num frames 1000...
|
597 |
+
[2023-02-23 09:56:13,195][11985] Num frames 1100...
|
598 |
+
[2023-02-23 09:56:13,307][11985] Num frames 1200...
|
599 |
+
[2023-02-23 09:56:13,418][11985] Num frames 1300...
|
600 |
+
[2023-02-23 09:56:13,532][11985] Num frames 1400...
|
601 |
+
[2023-02-23 09:56:13,660][11985] Num frames 1500...
|
602 |
+
[2023-02-23 09:56:13,784][11985] Num frames 1600...
|
603 |
+
[2023-02-23 09:56:13,897][11985] Num frames 1700...
|
604 |
+
[2023-02-23 09:56:14,009][11985] Num frames 1800...
|
605 |
+
[2023-02-23 09:56:14,108][11985] Avg episode rewards: #0: 22.670, true rewards: #0: 9.170
|
606 |
+
[2023-02-23 09:56:14,111][11985] Avg episode reward: 22.670, avg true_objective: 9.170
|
607 |
+
[2023-02-23 09:56:14,200][11985] Num frames 1900...
|
608 |
+
[2023-02-23 09:56:14,338][11985] Num frames 2000...
|
609 |
+
[2023-02-23 09:56:14,456][11985] Num frames 2100...
|
610 |
+
[2023-02-23 09:56:14,573][11985] Num frames 2200...
|
611 |
+
[2023-02-23 09:56:14,695][11985] Num frames 2300...
|
612 |
+
[2023-02-23 09:56:14,807][11985] Num frames 2400...
|
613 |
+
[2023-02-23 09:56:14,922][11985] Num frames 2500...
|
614 |
+
[2023-02-23 09:56:15,037][11985] Num frames 2600...
|
615 |
+
[2023-02-23 09:56:15,148][11985] Num frames 2700...
|
616 |
+
[2023-02-23 09:56:15,263][11985] Num frames 2800...
|
617 |
+
[2023-02-23 09:56:15,376][11985] Num frames 2900...
|
618 |
+
[2023-02-23 09:56:15,491][11985] Num frames 3000...
|
619 |
+
[2023-02-23 09:56:15,630][11985] Avg episode rewards: #0: 23.607, true rewards: #0: 10.273
|
620 |
+
[2023-02-23 09:56:15,632][11985] Avg episode reward: 23.607, avg true_objective: 10.273
|
621 |
+
[2023-02-23 09:56:15,656][11985] Num frames 3100...
|
622 |
+
[2023-02-23 09:56:15,765][11985] Num frames 3200...
|
623 |
+
[2023-02-23 09:56:15,868][11985] Num frames 3300...
|
624 |
+
[2023-02-23 09:56:15,971][11985] Num frames 3400...
|
625 |
+
[2023-02-23 09:56:16,079][11985] Num frames 3500...
|
626 |
+
[2023-02-23 09:56:16,183][11985] Num frames 3600...
|
627 |
+
[2023-02-23 09:56:16,284][11985] Num frames 3700...
|
628 |
+
[2023-02-23 09:56:16,392][11985] Num frames 3800...
|
629 |
+
[2023-02-23 09:56:16,499][11985] Num frames 3900...
|
630 |
+
[2023-02-23 09:56:16,606][11985] Num frames 4000...
|
631 |
+
[2023-02-23 09:56:16,700][11985] Avg episode rewards: #0: 22.838, true rewards: #0: 10.087
|
632 |
+
[2023-02-23 09:56:16,703][11985] Avg episode reward: 22.838, avg true_objective: 10.087
|
633 |
+
[2023-02-23 09:56:16,775][11985] Num frames 4100...
|
634 |
+
[2023-02-23 09:56:16,889][11985] Num frames 4200...
|
635 |
+
[2023-02-23 09:56:16,995][11985] Num frames 4300...
|
636 |
+
[2023-02-23 09:56:17,105][11985] Num frames 4400...
|
637 |
+
[2023-02-23 09:56:17,213][11985] Num frames 4500...
|
638 |
+
[2023-02-23 09:56:17,318][11985] Num frames 4600...
|
639 |
+
[2023-02-23 09:56:17,420][11985] Num frames 4700...
|
640 |
+
[2023-02-23 09:56:17,527][11985] Num frames 4800...
|
641 |
+
[2023-02-23 09:56:17,602][11985] Avg episode rewards: #0: 21.636, true rewards: #0: 9.636
|
642 |
+
[2023-02-23 09:56:17,604][11985] Avg episode reward: 21.636, avg true_objective: 9.636
|
643 |
+
[2023-02-23 09:56:17,694][11985] Num frames 4900...
|
644 |
+
[2023-02-23 09:56:17,807][11985] Num frames 5000...
|
645 |
+
[2023-02-23 09:56:17,915][11985] Num frames 5100...
|
646 |
+
[2023-02-23 09:56:18,017][11985] Num frames 5200...
|
647 |
+
[2023-02-23 09:56:18,126][11985] Num frames 5300...
|
648 |
+
[2023-02-23 09:56:18,237][11985] Num frames 5400...
|
649 |
+
[2023-02-23 09:56:18,351][11985] Num frames 5500...
|
650 |
+
[2023-02-23 09:56:18,457][11985] Num frames 5600...
|
651 |
+
[2023-02-23 09:56:18,559][11985] Num frames 5700...
|
652 |
+
[2023-02-23 09:56:18,664][11985] Num frames 5800...
|
653 |
+
[2023-02-23 09:56:18,775][11985] Num frames 5900...
|
654 |
+
[2023-02-23 09:56:18,877][11985] Num frames 6000...
|
655 |
+
[2023-02-23 09:56:19,001][11985] Num frames 6100...
|
656 |
+
[2023-02-23 09:56:19,110][11985] Num frames 6200...
|
657 |
+
[2023-02-23 09:56:19,220][11985] Num frames 6300...
|
658 |
+
[2023-02-23 09:56:19,334][11985] Num frames 6400...
|
659 |
+
[2023-02-23 09:56:19,448][11985] Num frames 6500...
|
660 |
+
[2023-02-23 09:56:19,553][11985] Num frames 6600...
|
661 |
+
[2023-02-23 09:56:19,667][11985] Num frames 6700...
|
662 |
+
[2023-02-23 09:56:19,795][11985] Num frames 6800...
|
663 |
+
[2023-02-23 09:56:19,916][11985] Num frames 6900...
|
664 |
+
[2023-02-23 09:56:19,993][11985] Avg episode rewards: #0: 27.697, true rewards: #0: 11.530
|
665 |
+
[2023-02-23 09:56:19,996][11985] Avg episode reward: 27.697, avg true_objective: 11.530
|
666 |
+
[2023-02-23 09:56:20,096][11985] Num frames 7000...
|
667 |
+
[2023-02-23 09:56:20,206][11985] Num frames 7100...
|
668 |
+
[2023-02-23 09:56:20,312][11985] Num frames 7200...
|
669 |
+
[2023-02-23 09:56:20,421][11985] Num frames 7300...
|
670 |
+
[2023-02-23 09:56:20,530][11985] Num frames 7400...
|
671 |
+
[2023-02-23 09:56:20,637][11985] Num frames 7500...
|
672 |
+
[2023-02-23 09:56:20,745][11985] Num frames 7600...
|
673 |
+
[2023-02-23 09:56:20,846][11985] Num frames 7700...
|
674 |
+
[2023-02-23 09:56:20,945][11985] Num frames 7800...
|
675 |
+
[2023-02-23 09:56:21,047][11985] Num frames 7900...
|
676 |
+
[2023-02-23 09:56:21,151][11985] Num frames 8000...
|
677 |
+
[2023-02-23 09:56:21,258][11985] Num frames 8100...
|
678 |
+
[2023-02-23 09:56:21,367][11985] Num frames 8200...
|
679 |
+
[2023-02-23 09:56:21,480][11985] Num frames 8300...
|
680 |
+
[2023-02-23 09:56:21,597][11985] Num frames 8400...
|
681 |
+
[2023-02-23 09:56:21,707][11985] Num frames 8500...
|
682 |
+
[2023-02-23 09:56:21,816][11985] Num frames 8600...
|
683 |
+
[2023-02-23 09:56:21,921][11985] Num frames 8700...
|
684 |
+
[2023-02-23 09:56:22,027][11985] Num frames 8800...
|
685 |
+
[2023-02-23 09:56:22,129][11985] Avg episode rewards: #0: 31.203, true rewards: #0: 12.631
|
686 |
+
[2023-02-23 09:56:22,130][11985] Avg episode reward: 31.203, avg true_objective: 12.631
|
687 |
+
[2023-02-23 09:56:22,196][11985] Num frames 8900...
|
688 |
+
[2023-02-23 09:56:22,302][11985] Num frames 9000...
|
689 |
+
[2023-02-23 09:56:22,410][11985] Num frames 9100...
|
690 |
+
[2023-02-23 09:56:22,516][11985] Num frames 9200...
|
691 |
+
[2023-02-23 09:56:22,619][11985] Num frames 9300...
|
692 |
+
[2023-02-23 09:56:22,729][11985] Num frames 9400...
|
693 |
+
[2023-02-23 09:56:22,833][11985] Num frames 9500...
|
694 |
+
[2023-02-23 09:56:22,938][11985] Num frames 9600...
|
695 |
+
[2023-02-23 09:56:23,043][11985] Num frames 9700...
|
696 |
+
[2023-02-23 09:56:23,152][11985] Num frames 9800...
|
697 |
+
[2023-02-23 09:56:23,253][11985] Num frames 9900...
|
698 |
+
[2023-02-23 09:56:23,342][11985] Avg episode rewards: #0: 30.162, true rewards: #0: 12.412
|
699 |
+
[2023-02-23 09:56:23,345][11985] Avg episode reward: 30.162, avg true_objective: 12.412
|
700 |
+
[2023-02-23 09:56:23,423][11985] Num frames 10000...
|
701 |
+
[2023-02-23 09:56:23,529][11985] Num frames 10100...
|
702 |
+
[2023-02-23 09:56:23,641][11985] Num frames 10200...
|
703 |
+
[2023-02-23 09:56:23,750][11985] Num frames 10300...
|
704 |
+
[2023-02-23 09:56:23,853][11985] Num frames 10400...
|
705 |
+
[2023-02-23 09:56:23,981][11985] Avg episode rewards: #0: 27.971, true rewards: #0: 11.638
|
706 |
+
[2023-02-23 09:56:23,983][11985] Avg episode reward: 27.971, avg true_objective: 11.638
|
707 |
+
[2023-02-23 09:56:24,014][11985] Num frames 10500...
|
708 |
+
[2023-02-23 09:56:24,119][11985] Num frames 10600...
|
709 |
+
[2023-02-23 09:56:24,225][11985] Num frames 10700...
|
710 |
+
[2023-02-23 09:56:24,329][11985] Num frames 10800...
|
711 |
+
[2023-02-23 09:56:24,435][11985] Num frames 10900...
|
712 |
+
[2023-02-23 09:56:24,541][11985] Num frames 11000...
|
713 |
+
[2023-02-23 09:56:24,642][11985] Num frames 11100...
|
714 |
+
[2023-02-23 09:56:24,746][11985] Num frames 11200...
|
715 |
+
[2023-02-23 09:56:24,855][11985] Num frames 11300...
|
716 |
+
[2023-02-23 09:56:24,966][11985] Num frames 11400...
|
717 |
+
[2023-02-23 09:56:25,057][11985] Avg episode rewards: #0: 27.234, true rewards: #0: 11.434
|
718 |
+
[2023-02-23 09:56:25,060][11985] Avg episode reward: 27.234, avg true_objective: 11.434
|
719 |
+
[2023-02-23 09:57:03,493][11985] Replay video saved to /content/train_dir/default_experiment/replay.mp4!
|
720 |
+
[2023-02-23 10:05:26,470][11985] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json
|
721 |
+
[2023-02-23 10:05:26,471][11985] Overriding arg 'num_workers' with value 1 passed from command line
|
722 |
+
[2023-02-23 10:05:26,473][11985] Adding new argument 'no_render'=True that is not in the saved config file!
|
723 |
+
[2023-02-23 10:05:26,474][11985] Adding new argument 'save_video'=True that is not in the saved config file!
|
724 |
+
[2023-02-23 10:05:26,477][11985] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file!
|
725 |
+
[2023-02-23 10:05:26,478][11985] Adding new argument 'video_name'=None that is not in the saved config file!
|
726 |
+
[2023-02-23 10:05:26,479][11985] Adding new argument 'max_num_frames'=100000 that is not in the saved config file!
|
727 |
+
[2023-02-23 10:05:26,481][11985] Adding new argument 'max_num_episodes'=10 that is not in the saved config file!
|
728 |
+
[2023-02-23 10:05:26,483][11985] Adding new argument 'push_to_hub'=True that is not in the saved config file!
|
729 |
+
[2023-02-23 10:05:26,485][11985] Adding new argument 'hf_repository'='moodlep/rl_course_vizdoom_health_gathering_supreme' that is not in the saved config file!
|
730 |
+
[2023-02-23 10:05:26,486][11985] Adding new argument 'policy_index'=0 that is not in the saved config file!
|
731 |
+
[2023-02-23 10:05:26,487][11985] Adding new argument 'eval_deterministic'=False that is not in the saved config file!
|
732 |
+
[2023-02-23 10:05:26,488][11985] Adding new argument 'train_script'=None that is not in the saved config file!
|
733 |
+
[2023-02-23 10:05:26,492][11985] Adding new argument 'enjoy_script'=None that is not in the saved config file!
|
734 |
+
[2023-02-23 10:05:26,494][11985] Using frameskip 1 and render_action_repeat=4 for evaluation
|
735 |
+
[2023-02-23 10:05:26,506][11985] RunningMeanStd input shape: (3, 72, 128)
|
736 |
+
[2023-02-23 10:05:26,508][11985] RunningMeanStd input shape: (1,)
|
737 |
+
[2023-02-23 10:05:26,523][11985] ConvEncoder: input_channels=3
|
738 |
+
[2023-02-23 10:05:26,558][11985] Conv encoder output size: 512
|
739 |
+
[2023-02-23 10:05:26,560][11985] Policy head output size: 512
|
740 |
+
[2023-02-23 10:05:26,577][11985] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
|
741 |
+
[2023-02-23 10:05:26,977][11985] Num frames 100...
|
742 |
+
[2023-02-23 10:05:27,082][11985] Num frames 200...
|
743 |
+
[2023-02-23 10:05:27,197][11985] Avg episode rewards: #0: 2.560, true rewards: #0: 2.560
|
744 |
+
[2023-02-23 10:05:27,199][11985] Avg episode reward: 2.560, avg true_objective: 2.560
|
745 |
+
[2023-02-23 10:05:27,249][11985] Num frames 300...
|
746 |
+
[2023-02-23 10:05:27,355][11985] Num frames 400...
|
747 |
+
[2023-02-23 10:05:27,463][11985] Num frames 500...
|
748 |
+
[2023-02-23 10:05:27,561][11985] Num frames 600...
|
749 |
+
[2023-02-23 10:05:27,658][11985] Num frames 700...
|
750 |
+
[2023-02-23 10:05:27,764][11985] Num frames 800...
|
751 |
+
[2023-02-23 10:05:27,882][11985] Avg episode rewards: #0: 6.805, true rewards: #0: 4.305
|
752 |
+
[2023-02-23 10:05:27,884][11985] Avg episode reward: 6.805, avg true_objective: 4.305
|
753 |
+
[2023-02-23 10:05:27,929][11985] Num frames 900...
|
754 |
+
[2023-02-23 10:05:28,037][11985] Num frames 1000...
|
755 |
+
[2023-02-23 10:05:28,145][11985] Num frames 1100...
|
756 |
+
[2023-02-23 10:05:28,255][11985] Num frames 1200...
|
757 |
+
[2023-02-23 10:05:28,358][11985] Num frames 1300...
|
758 |
+
[2023-02-23 10:05:28,462][11985] Num frames 1400...
|
759 |
+
[2023-02-23 10:05:28,565][11985] Num frames 1500...
|
760 |
+
[2023-02-23 10:05:28,676][11985] Num frames 1600...
|
761 |
+
[2023-02-23 10:05:28,778][11985] Num frames 1700...
|
762 |
+
[2023-02-23 10:05:28,883][11985] Num frames 1800...
|
763 |
+
[2023-02-23 10:05:28,990][11985] Num frames 1900...
|
764 |
+
[2023-02-23 10:05:29,097][11985] Num frames 2000...
|
765 |
+
[2023-02-23 10:05:29,205][11985] Num frames 2100...
|
766 |
+
[2023-02-23 10:05:29,304][11985] Num frames 2200...
|
767 |
+
[2023-02-23 10:05:29,414][11985] Num frames 2300...
|
768 |
+
[2023-02-23 10:05:29,522][11985] Num frames 2400...
|
769 |
+
[2023-02-23 10:05:29,635][11985] Num frames 2500...
|
770 |
+
[2023-02-23 10:05:29,758][11985] Num frames 2600...
|
771 |
+
[2023-02-23 10:05:29,885][11985] Num frames 2700...
|
772 |
+
[2023-02-23 10:05:29,994][11985] Num frames 2800...
|
773 |
+
[2023-02-23 10:05:30,104][11985] Num frames 2900...
|
774 |
+
[2023-02-23 10:05:30,227][11985] Avg episode rewards: #0: 25.203, true rewards: #0: 9.870
|
775 |
+
[2023-02-23 10:05:30,229][11985] Avg episode reward: 25.203, avg true_objective: 9.870
|
776 |
+
[2023-02-23 10:05:30,273][11985] Num frames 3000...
|
777 |
+
[2023-02-23 10:05:30,379][11985] Num frames 3100...
|
778 |
+
[2023-02-23 10:05:30,482][11985] Num frames 3200...
|
779 |
+
[2023-02-23 10:05:30,584][11985] Num frames 3300...
|
780 |
+
[2023-02-23 10:05:30,685][11985] Num frames 3400...
|
781 |
+
[2023-02-23 10:05:30,790][11985] Num frames 3500...
|
782 |
+
[2023-02-23 10:05:30,893][11985] Num frames 3600...
|
783 |
+
[2023-02-23 10:05:31,005][11985] Num frames 3700...
|
784 |
+
[2023-02-23 10:05:31,107][11985] Num frames 3800...
|
785 |
+
[2023-02-23 10:05:31,209][11985] Num frames 3900...
|
786 |
+
[2023-02-23 10:05:31,319][11985] Num frames 4000...
|
787 |
+
[2023-02-23 10:05:31,420][11985] Num frames 4100...
|
788 |
+
[2023-02-23 10:05:31,532][11985] Avg episode rewards: #0: 25.630, true rewards: #0: 10.380
|
789 |
+
[2023-02-23 10:05:31,533][11985] Avg episode reward: 25.630, avg true_objective: 10.380
|
790 |
+
[2023-02-23 10:05:31,590][11985] Num frames 4200...
|
791 |
+
[2023-02-23 10:05:31,703][11985] Num frames 4300...
|
792 |
+
[2023-02-23 10:05:31,813][11985] Num frames 4400...
|
793 |
+
[2023-02-23 10:05:31,914][11985] Num frames 4500...
|
794 |
+
[2023-02-23 10:05:32,025][11985] Num frames 4600...
|
795 |
+
[2023-02-23 10:05:32,130][11985] Num frames 4700...
|
796 |
+
[2023-02-23 10:05:32,239][11985] Num frames 4800...
|
797 |
+
[2023-02-23 10:05:32,342][11985] Num frames 4900...
|
798 |
+
[2023-02-23 10:05:32,450][11985] Num frames 5000...
|
799 |
+
[2023-02-23 10:05:32,549][11985] Num frames 5100...
|
800 |
+
[2023-02-23 10:05:32,656][11985] Num frames 5200...
|
801 |
+
[2023-02-23 10:05:32,770][11985] Num frames 5300...
|
802 |
+
[2023-02-23 10:05:32,881][11985] Num frames 5400...
|
803 |
+
[2023-02-23 10:05:32,994][11985] Num frames 5500...
|
804 |
+
[2023-02-23 10:05:33,109][11985] Num frames 5600...
|
805 |
+
[2023-02-23 10:05:33,215][11985] Num frames 5700...
|
806 |
+
[2023-02-23 10:05:33,323][11985] Num frames 5800...
|
807 |
+
[2023-02-23 10:05:33,432][11985] Num frames 5900...
|
808 |
+
[2023-02-23 10:05:33,539][11985] Num frames 6000...
|
809 |
+
[2023-02-23 10:05:33,648][11985] Num frames 6100...
|
810 |
+
[2023-02-23 10:05:33,800][11985] Avg episode rewards: #0: 32.900, true rewards: #0: 12.300
|
811 |
+
[2023-02-23 10:05:33,802][11985] Avg episode reward: 32.900, avg true_objective: 12.300
|
812 |
+
[2023-02-23 10:05:33,860][11985] Num frames 6200...
|
813 |
+
[2023-02-23 10:05:33,969][11985] Num frames 6300...
|
814 |
+
[2023-02-23 10:05:34,079][11985] Num frames 6400...
|
815 |
+
[2023-02-23 10:05:34,186][11985] Num frames 6500...
|
816 |
+
[2023-02-23 10:05:34,291][11985] Num frames 6600...
|
817 |
+
[2023-02-23 10:05:34,441][11985] Num frames 6700...
|
818 |
+
[2023-02-23 10:05:34,550][11985] Num frames 6800...
|
819 |
+
[2023-02-23 10:05:34,659][11985] Num frames 6900...
|
820 |
+
[2023-02-23 10:05:34,761][11985] Num frames 7000...
|
821 |
+
[2023-02-23 10:05:34,869][11985] Num frames 7100...
|
822 |
+
[2023-02-23 10:05:34,997][11985] Num frames 7200...
|
823 |
+
[2023-02-23 10:05:35,127][11985] Num frames 7300...
|
824 |
+
[2023-02-23 10:05:35,237][11985] Avg episode rewards: #0: 32.903, true rewards: #0: 12.237
|
825 |
+
[2023-02-23 10:05:35,238][11985] Avg episode reward: 32.903, avg true_objective: 12.237
|
826 |
+
[2023-02-23 10:05:35,304][11985] Num frames 7400...
|
827 |
+
[2023-02-23 10:05:35,422][11985] Num frames 7500...
|
828 |
+
[2023-02-23 10:05:35,535][11985] Num frames 7600...
|
829 |
+
[2023-02-23 10:05:35,655][11985] Num frames 7700...
|
830 |
+
[2023-02-23 10:05:35,764][11985] Num frames 7800...
|
831 |
+
[2023-02-23 10:05:35,881][11985] Num frames 7900...
|
832 |
+
[2023-02-23 10:05:35,992][11985] Num frames 8000...
|
833 |
+
[2023-02-23 10:05:36,120][11985] Num frames 8100...
|
834 |
+
[2023-02-23 10:05:36,240][11985] Num frames 8200...
|
835 |
+
[2023-02-23 10:05:36,358][11985] Num frames 8300...
|
836 |
+
[2023-02-23 10:05:36,476][11985] Num frames 8400...
|
837 |
+
[2023-02-23 10:05:36,587][11985] Num frames 8500...
|
838 |
+
[2023-02-23 10:05:36,698][11985] Num frames 8600...
|
839 |
+
[2023-02-23 10:05:36,809][11985] Num frames 8700...
|
840 |
+
[2023-02-23 10:05:36,926][11985] Num frames 8800...
|
841 |
+
[2023-02-23 10:05:37,046][11985] Num frames 8900...
|
842 |
+
[2023-02-23 10:05:37,161][11985] Num frames 9000...
|
843 |
+
[2023-02-23 10:05:37,277][11985] Num frames 9100...
|
844 |
+
[2023-02-23 10:05:37,387][11985] Num frames 9200...
|
845 |
+
[2023-02-23 10:05:37,462][11985] Avg episode rewards: #0: 34.742, true rewards: #0: 13.171
|
846 |
+
[2023-02-23 10:05:37,463][11985] Avg episode reward: 34.742, avg true_objective: 13.171
|
847 |
+
[2023-02-23 10:05:37,550][11985] Num frames 9300...
|
848 |
+
[2023-02-23 10:05:37,657][11985] Num frames 9400...
|
849 |
+
[2023-02-23 10:05:37,760][11985] Num frames 9500...
|
850 |
+
[2023-02-23 10:05:37,863][11985] Num frames 9600...
|
851 |
+
[2023-02-23 10:05:37,968][11985] Num frames 9700...
|
852 |
+
[2023-02-23 10:05:38,077][11985] Num frames 9800...
|
853 |
+
[2023-02-23 10:05:38,182][11985] Num frames 9900...
|
854 |
+
[2023-02-23 10:05:38,283][11985] Num frames 10000...
|
855 |
+
[2023-02-23 10:05:38,432][11985] Avg episode rewards: #0: 32.605, true rewards: #0: 12.605
|
856 |
+
[2023-02-23 10:05:38,434][11985] Avg episode reward: 32.605, avg true_objective: 12.605
|
857 |
+
[2023-02-23 10:05:38,455][11985] Num frames 10100...
|
858 |
+
[2023-02-23 10:05:38,561][11985] Num frames 10200...
|
859 |
+
[2023-02-23 10:05:38,666][11985] Num frames 10300...
|
860 |
+
[2023-02-23 10:05:38,776][11985] Num frames 10400...
|
861 |
+
[2023-02-23 10:05:38,877][11985] Num frames 10500...
|
862 |
+
[2023-02-23 10:05:38,979][11985] Num frames 10600...
|
863 |
+
[2023-02-23 10:05:39,097][11985] Num frames 10700...
|
864 |
+
[2023-02-23 10:05:39,209][11985] Num frames 10800...
|
865 |
+
[2023-02-23 10:05:39,311][11985] Num frames 10900...
|
866 |
+
[2023-02-23 10:05:39,420][11985] Num frames 11000...
|
867 |
+
[2023-02-23 10:05:39,529][11985] Num frames 11100...
|
868 |
+
[2023-02-23 10:05:39,637][11985] Num frames 11200...
|
869 |
+
[2023-02-23 10:05:39,740][11985] Num frames 11300...
|
870 |
+
[2023-02-23 10:05:39,842][11985] Num frames 11400...
|
871 |
+
[2023-02-23 10:05:39,950][11985] Num frames 11500...
|
872 |
+
[2023-02-23 10:05:40,040][11985] Avg episode rewards: #0: 33.483, true rewards: #0: 12.817
|
873 |
+
[2023-02-23 10:05:40,042][11985] Avg episode reward: 33.483, avg true_objective: 12.817
|
874 |
+
[2023-02-23 10:05:40,116][11985] Num frames 11600...
|
875 |
+
[2023-02-23 10:05:40,224][11985] Num frames 11700...
|
876 |
+
[2023-02-23 10:05:40,325][11985] Num frames 11800...
|
877 |
+
[2023-02-23 10:05:40,434][11985] Num frames 11900...
|
878 |
+
[2023-02-23 10:05:40,533][11985] Num frames 12000...
|
879 |
+
[2023-02-23 10:05:40,635][11985] Num frames 12100...
|
880 |
+
[2023-02-23 10:05:40,736][11985] Num frames 12200...
|
881 |
+
[2023-02-23 10:05:40,836][11985] Num frames 12300...
|
882 |
+
[2023-02-23 10:05:40,941][11985] Num frames 12400...
|
883 |
+
[2023-02-23 10:05:41,045][11985] Num frames 12500...
|
884 |
+
[2023-02-23 10:05:41,156][11985] Num frames 12600...
|
885 |
+
[2023-02-23 10:05:41,266][11985] Num frames 12700...
|
886 |
+
[2023-02-23 10:05:41,372][11985] Num frames 12800...
|
887 |
+
[2023-02-23 10:05:41,475][11985] Num frames 12900...
|
888 |
+
[2023-02-23 10:05:41,577][11985] Num frames 13000...
|
889 |
+
[2023-02-23 10:05:41,682][11985] Num frames 13100...
|
890 |
+
[2023-02-23 10:05:41,818][11985] Avg episode rewards: #0: 33.978, true rewards: #0: 13.178
|
891 |
+
[2023-02-23 10:05:41,820][11985] Avg episode reward: 33.978, avg true_objective: 13.178
|
892 |
+
[2023-02-23 10:06:25,487][11985] Replay video saved to /content/train_dir/default_experiment/replay.mp4!
|
893 |
+
[2023-02-23 10:07:58,227][11985] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json
|
894 |
+
[2023-02-23 10:07:58,228][11985] Overriding arg 'num_workers' with value 1 passed from command line
|
895 |
+
[2023-02-23 10:07:58,230][11985] Adding new argument 'no_render'=True that is not in the saved config file!
|
896 |
+
[2023-02-23 10:07:58,232][11985] Adding new argument 'save_video'=True that is not in the saved config file!
|
897 |
+
[2023-02-23 10:07:58,234][11985] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file!
|
898 |
+
[2023-02-23 10:07:58,236][11985] Adding new argument 'video_name'=None that is not in the saved config file!
|
899 |
+
[2023-02-23 10:07:58,237][11985] Adding new argument 'max_num_frames'=100000 that is not in the saved config file!
|
900 |
+
[2023-02-23 10:07:58,240][11985] Adding new argument 'max_num_episodes'=10 that is not in the saved config file!
|
901 |
+
[2023-02-23 10:07:58,241][11985] Adding new argument 'push_to_hub'=True that is not in the saved config file!
|
902 |
+
[2023-02-23 10:07:58,242][11985] Adding new argument 'hf_repository'='moodlep/rl_course_vizdoom_health_gathering_supreme' that is not in the saved config file!
|
903 |
+
[2023-02-23 10:07:58,245][11985] Adding new argument 'policy_index'=0 that is not in the saved config file!
|
904 |
+
[2023-02-23 10:07:58,246][11985] Adding new argument 'eval_deterministic'=False that is not in the saved config file!
|
905 |
+
[2023-02-23 10:07:58,248][11985] Adding new argument 'train_script'=None that is not in the saved config file!
|
906 |
+
[2023-02-23 10:07:58,250][11985] Adding new argument 'enjoy_script'=None that is not in the saved config file!
|
907 |
+
[2023-02-23 10:07:58,251][11985] Using frameskip 1 and render_action_repeat=4 for evaluation
|
908 |
+
[2023-02-23 10:07:58,269][11985] RunningMeanStd input shape: (3, 72, 128)
|
909 |
+
[2023-02-23 10:07:58,271][11985] RunningMeanStd input shape: (1,)
|
910 |
+
[2023-02-23 10:07:58,284][11985] ConvEncoder: input_channels=3
|
911 |
+
[2023-02-23 10:07:58,318][11985] Conv encoder output size: 512
|
912 |
+
[2023-02-23 10:07:58,319][11985] Policy head output size: 512
|
913 |
+
[2023-02-23 10:07:58,340][11985] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
|
914 |
+
[2023-02-23 10:07:58,739][11985] Num frames 100...
|
915 |
+
[2023-02-23 10:07:58,839][11985] Num frames 200...
|
916 |
+
[2023-02-23 10:07:58,936][11985] Num frames 300...
|
917 |
+
[2023-02-23 10:07:59,007][11985] Avg episode rewards: #0: 6.160, true rewards: #0: 3.160
|
918 |
+
[2023-02-23 10:07:59,009][11985] Avg episode reward: 6.160, avg true_objective: 3.160
|
919 |
+
[2023-02-23 10:07:59,101][11985] Num frames 400...
|
920 |
+
[2023-02-23 10:07:59,205][11985] Num frames 500...
|
921 |
+
[2023-02-23 10:07:59,304][11985] Num frames 600...
|
922 |
+
[2023-02-23 10:07:59,413][11985] Num frames 700...
|
923 |
+
[2023-02-23 10:07:59,514][11985] Num frames 800...
|
924 |
+
[2023-02-23 10:07:59,626][11985] Num frames 900...
|
925 |
+
[2023-02-23 10:07:59,728][11985] Num frames 1000...
|
926 |
+
[2023-02-23 10:07:59,835][11985] Num frames 1100...
|
927 |
+
[2023-02-23 10:07:59,973][11985] Avg episode rewards: #0: 14.400, true rewards: #0: 5.900
|
928 |
+
[2023-02-23 10:07:59,975][11985] Avg episode reward: 14.400, avg true_objective: 5.900
|
929 |
+
[2023-02-23 10:08:00,002][11985] Num frames 1200...
|
930 |
+
[2023-02-23 10:08:00,108][11985] Num frames 1300...
|
931 |
+
[2023-02-23 10:08:00,217][11985] Num frames 1400...
|
932 |
+
[2023-02-23 10:08:00,318][11985] Num frames 1500...
|
933 |
+
[2023-02-23 10:08:00,421][11985] Num frames 1600...
|
934 |
+
[2023-02-23 10:08:00,530][11985] Num frames 1700...
|
935 |
+
[2023-02-23 10:08:00,636][11985] Num frames 1800...
|
936 |
+
[2023-02-23 10:08:00,738][11985] Num frames 1900...
|
937 |
+
[2023-02-23 10:08:00,825][11985] Avg episode rewards: #0: 14.770, true rewards: #0: 6.437
|
938 |
+
[2023-02-23 10:08:00,827][11985] Avg episode reward: 14.770, avg true_objective: 6.437
|
939 |
+
[2023-02-23 10:08:00,904][11985] Num frames 2000...
|
940 |
+
[2023-02-23 10:08:01,013][11985] Num frames 2100...
|
941 |
+
[2023-02-23 10:08:01,114][11985] Num frames 2200...
|
942 |
+
[2023-02-23 10:08:01,229][11985] Num frames 2300...
|
943 |
+
[2023-02-23 10:08:01,332][11985] Num frames 2400...
|
944 |
+
[2023-02-23 10:08:01,435][11985] Num frames 2500...
|
945 |
+
[2023-02-23 10:08:01,546][11985] Num frames 2600...
|
946 |
+
[2023-02-23 10:08:01,694][11985] Avg episode rewards: #0: 15.210, true rewards: #0: 6.710
|
947 |
+
[2023-02-23 10:08:01,696][11985] Avg episode reward: 15.210, avg true_objective: 6.710
|
948 |
+
[2023-02-23 10:08:01,716][11985] Num frames 2700...
|
949 |
+
[2023-02-23 10:08:01,822][11985] Num frames 2800...
|
950 |
+
[2023-02-23 10:08:01,943][11985] Num frames 2900...
|
951 |
+
[2023-02-23 10:08:02,063][11985] Num frames 3000...
|
952 |
+
[2023-02-23 10:08:02,176][11985] Num frames 3100...
|
953 |
+
[2023-02-23 10:08:02,278][11985] Num frames 3200...
|
954 |
+
[2023-02-23 10:08:02,379][11985] Num frames 3300...
|
955 |
+
[2023-02-23 10:08:02,482][11985] Num frames 3400...
|
956 |
+
[2023-02-23 10:08:02,592][11985] Num frames 3500...
|
957 |
+
[2023-02-23 10:08:02,698][11985] Num frames 3600...
|
958 |
+
[2023-02-23 10:08:02,800][11985] Num frames 3700...
|
959 |
+
[2023-02-23 10:08:02,902][11985] Num frames 3800...
|
960 |
+
[2023-02-23 10:08:03,008][11985] Num frames 3900...
|
961 |
+
[2023-02-23 10:08:03,114][11985] Num frames 4000...
|
962 |
+
[2023-02-23 10:08:03,222][11985] Num frames 4100...
|
963 |
+
[2023-02-23 10:08:03,334][11985] Num frames 4200...
|
964 |
+
[2023-02-23 10:08:03,450][11985] Num frames 4300...
|
965 |
+
[2023-02-23 10:08:03,508][11985] Avg episode rewards: #0: 20.202, true rewards: #0: 8.602
|
966 |
+
[2023-02-23 10:08:03,510][11985] Avg episode reward: 20.202, avg true_objective: 8.602
|
967 |
+
[2023-02-23 10:08:03,615][11985] Num frames 4400...
|
968 |
+
[2023-02-23 10:08:03,720][11985] Num frames 4500...
|
969 |
+
[2023-02-23 10:08:03,829][11985] Num frames 4600...
|
970 |
+
[2023-02-23 10:08:03,936][11985] Num frames 4700...
|
971 |
+
[2023-02-23 10:08:04,043][11985] Num frames 4800...
|
972 |
+
[2023-02-23 10:08:04,154][11985] Num frames 4900...
|
973 |
+
[2023-02-23 10:08:04,281][11985] Num frames 5000...
|
974 |
+
[2023-02-23 10:08:04,402][11985] Num frames 5100...
|
975 |
+
[2023-02-23 10:08:04,515][11985] Num frames 5200...
|
976 |
+
[2023-02-23 10:08:04,629][11985] Num frames 5300...
|
977 |
+
[2023-02-23 10:08:04,735][11985] Num frames 5400...
|
978 |
+
[2023-02-23 10:08:04,846][11985] Num frames 5500...
|
979 |
+
[2023-02-23 10:08:04,953][11985] Num frames 5600...
|
980 |
+
[2023-02-23 10:08:05,065][11985] Num frames 5700...
|
981 |
+
[2023-02-23 10:08:05,172][11985] Num frames 5800...
|
982 |
+
[2023-02-23 10:08:05,325][11985] Avg episode rewards: #0: 23.480, true rewards: #0: 9.813
|
983 |
+
[2023-02-23 10:08:05,327][11985] Avg episode reward: 23.480, avg true_objective: 9.813
|
984 |
+
[2023-02-23 10:08:05,342][11985] Num frames 5900...
|
985 |
+
[2023-02-23 10:08:05,447][11985] Num frames 6000...
|
986 |
+
[2023-02-23 10:08:05,547][11985] Num frames 6100...
|
987 |
+
[2023-02-23 10:08:05,651][11985] Num frames 6200...
|
988 |
+
[2023-02-23 10:08:05,751][11985] Num frames 6300...
|
989 |
+
[2023-02-23 10:08:05,852][11985] Num frames 6400...
|
990 |
+
[2023-02-23 10:08:05,958][11985] Num frames 6500...
|
991 |
+
[2023-02-23 10:08:06,065][11985] Num frames 6600...
|
992 |
+
[2023-02-23 10:08:06,170][11985] Num frames 6700...
|
993 |
+
[2023-02-23 10:08:06,275][11985] Num frames 6800...
|
994 |
+
[2023-02-23 10:08:06,402][11985] Num frames 6900...
|
995 |
+
[2023-02-23 10:08:06,518][11985] Num frames 7000...
|
996 |
+
[2023-02-23 10:08:06,635][11985] Num frames 7100...
|
997 |
+
[2023-02-23 10:08:06,751][11985] Num frames 7200...
|
998 |
+
[2023-02-23 10:08:06,866][11985] Num frames 7300...
|
999 |
+
[2023-02-23 10:08:06,984][11985] Num frames 7400...
|
1000 |
+
[2023-02-23 10:08:07,105][11985] Num frames 7500...
|
1001 |
+
[2023-02-23 10:08:07,221][11985] Avg episode rewards: #0: 26.217, true rewards: #0: 10.789
|
1002 |
+
[2023-02-23 10:08:07,223][11985] Avg episode reward: 26.217, avg true_objective: 10.789
|
1003 |
+
[2023-02-23 10:08:07,284][11985] Num frames 7600...
|
1004 |
+
[2023-02-23 10:08:07,394][11985] Num frames 7700...
|
1005 |
+
[2023-02-23 10:08:07,512][11985] Num frames 7800...
|
1006 |
+
[2023-02-23 10:08:07,642][11985] Num frames 7900...
|
1007 |
+
[2023-02-23 10:08:07,762][11985] Num frames 8000...
|
1008 |
+
[2023-02-23 10:08:07,877][11985] Num frames 8100...
|
1009 |
+
[2023-02-23 10:08:07,989][11985] Num frames 8200...
|
1010 |
+
[2023-02-23 10:08:08,103][11985] Num frames 8300...
|
1011 |
+
[2023-02-23 10:08:08,218][11985] Num frames 8400...
|
1012 |
+
[2023-02-23 10:08:08,333][11985] Num frames 8500...
|
1013 |
+
[2023-02-23 10:08:08,445][11985] Num frames 8600...
|
1014 |
+
[2023-02-23 10:08:08,554][11985] Num frames 8700...
|
1015 |
+
[2023-02-23 10:08:08,666][11985] Num frames 8800...
|
1016 |
+
[2023-02-23 10:08:08,775][11985] Num frames 8900...
|
1017 |
+
[2023-02-23 10:08:08,888][11985] Num frames 9000...
|
1018 |
+
[2023-02-23 10:08:08,989][11985] Num frames 9100...
|
1019 |
+
[2023-02-23 10:08:09,108][11985] Num frames 9200...
|
1020 |
+
[2023-02-23 10:08:09,220][11985] Num frames 9300...
|
1021 |
+
[2023-02-23 10:08:09,328][11985] Num frames 9400...
|
1022 |
+
[2023-02-23 10:08:09,426][11985] Num frames 9500...
|
1023 |
+
[2023-02-23 10:08:09,537][11985] Num frames 9600...
|
1024 |
+
[2023-02-23 10:08:09,648][11985] Avg episode rewards: #0: 29.565, true rewards: #0: 12.065
|
1025 |
+
[2023-02-23 10:08:09,650][11985] Avg episode reward: 29.565, avg true_objective: 12.065
|
1026 |
+
[2023-02-23 10:08:09,703][11985] Num frames 9700...
|
1027 |
+
[2023-02-23 10:08:09,813][11985] Num frames 9800...
|
1028 |
+
[2023-02-23 10:08:09,922][11985] Num frames 9900...
|
1029 |
+
[2023-02-23 10:08:10,030][11985] Num frames 10000...
|
1030 |
+
[2023-02-23 10:08:10,133][11985] Num frames 10100...
|
1031 |
+
[2023-02-23 10:08:10,245][11985] Num frames 10200...
|
1032 |
+
[2023-02-23 10:08:10,356][11985] Num frames 10300...
|
1033 |
+
[2023-02-23 10:08:10,415][11985] Avg episode rewards: #0: 28.447, true rewards: #0: 11.447
|
1034 |
+
[2023-02-23 10:08:10,417][11985] Avg episode reward: 28.447, avg true_objective: 11.447
|
1035 |
+
[2023-02-23 10:08:10,517][11985] Num frames 10400...
|
1036 |
+
[2023-02-23 10:08:10,622][11985] Num frames 10500...
|
1037 |
+
[2023-02-23 10:08:10,733][11985] Num frames 10600...
|
1038 |
+
[2023-02-23 10:08:10,835][11985] Num frames 10700...
|
1039 |
+
[2023-02-23 10:08:10,941][11985] Num frames 10800...
|
1040 |
+
[2023-02-23 10:08:11,043][11985] Num frames 10900...
|
1041 |
+
[2023-02-23 10:08:11,147][11985] Num frames 11000...
|
1042 |
+
[2023-02-23 10:08:11,247][11985] Num frames 11100...
|
1043 |
+
[2023-02-23 10:08:11,358][11985] Num frames 11200...
|
1044 |
+
[2023-02-23 10:08:11,466][11985] Num frames 11300...
|
1045 |
+
[2023-02-23 10:08:11,574][11985] Num frames 11400...
|
1046 |
+
[2023-02-23 10:08:11,690][11985] Num frames 11500...
|
1047 |
+
[2023-02-23 10:08:11,796][11985] Num frames 11600...
|
1048 |
+
[2023-02-23 10:08:11,907][11985] Num frames 11700...
|
1049 |
+
[2023-02-23 10:08:12,012][11985] Num frames 11800...
|
1050 |
+
[2023-02-23 10:08:12,116][11985] Num frames 11900...
|
1051 |
+
[2023-02-23 10:08:12,219][11985] Num frames 12000...
|
1052 |
+
[2023-02-23 10:08:12,330][11985] Num frames 12100...
|
1053 |
+
[2023-02-23 10:08:12,413][11985] Avg episode rewards: #0: 30.325, true rewards: #0: 12.125
|
1054 |
+
[2023-02-23 10:08:12,415][11985] Avg episode reward: 30.325, avg true_objective: 12.125
|
1055 |
+
[2023-02-23 10:08:52,893][11985] Replay video saved to /content/train_dir/default_experiment/replay.mp4!
|