andrewzhang505

Andrewzhang505's group workspace

Group: mujoco_walker

1-1

of 1

Tags

envpool

Author

andrewzhang505

State

Finished

Start time

December 14th, 2022 4:18:57 AM

Runtime

14m 7s

Tracked hours

13m 57s

Run path

andrewzhang505/sample_factory/envpool_walker_20221214_041856_142663

Linux-4.19.0-22-cloud-amd64-x86_64-with-glibc2.28

Python version

3.9.13

Git repository

git clone https://github.com/andrewzhang505/sample-factory.git

Git state

git checkout -b "envpool_walker_20221214_041856_142663" 0319b736bfad9cf54f8f3ad6ab669193d3ca1d8b

Command

-m sf_examples.envpool.mujoco.train_envpool_mujoco --algo=APPO --env=mujoco_walker --experiment=envpool_walker --with_wandb=True --wandb_tags envpool --seed=5555

System Hardware

CPU count	8
GPU count	1
GPU type	Tesla T4

W&B CLI Version

0.12.20

Group

mujoco_walker

Job Type

Config parameters are your model's inputs. Learn more

▶
Config parameters:{} 123 keys
- actor_critic_share_weights:
  true
- actor_worker_gpus:[] 0 items
- adam_beta1:
  0.9
- adam_beta2:
  0.999
- adam_eps:
  0.000001
- adaptive_stddev:
  false
- algo:
  "APPO"
- async_rl:
  false
- batch_size:
  2,048
- batched_sampling:
  true
- benchmark:
  false
- ▶
  cli_args:{} 6 keys
- command_line:
  "--algo=APPO --env=mujoco_walker --experiment=envpool_walker --with_wandb=True --wandb_tags envpool --seed=5555"
- continuous_tanh_scale:
  0
- decoder_mlp_layers:[] 0 items
- decorrelate_envs_on_one_worker:
  true
- decorrelate_experience_max_seconds:
  0
- default_niceness:
  0
- device:
  "gpu"
- encoder_conv_architecture:
  "convnet_simple"
- ▶
  encoder_conv_mlp_layers:[] 1 item
  - 0:
    512
- ▶
  encoder_mlp_layers:[] 3 items
  - 0:
    256
  - 1:
    128
  - 2:
    64
- env:
  "mujoco_walker"
- env_agents:
  64
- env_frameskip:
  1
- env_framestack:
  1
- env_gpu_actions:
  false
- env_gpu_observations:
  true
- envpool_num_threads:
  8
- envpool_thread_affinity_offset:
  -1
- experiment:
  "envpool_walker"
- experiment_summaries_interval:
  15
- exploration_loss:
  "entropy"
- exploration_loss_coeff:
  0
- flush_summaries_interval:
  30
- force_envs_single_thread:
  false
- gae_lambda:
  0.95
- gamma:
  0.99
- git_hash:
  "0319b736bfad9cf54f8f3ad6ab669193d3ca1d8b"
- git_repo_name:
  https://github.com/andrewzhang505/sample-factory.git
- heartbeat_interval:
  20
- heartbeat_reporting_interval:
  180
- help:
  false
- initial_stddev:
  1
- keep_checkpoints:
  2
- kl_loss_coeff:
  0.1
- with_pbt:
  false
- with_vtrace:
  false
- with_wandb:
  true
- worker_num_splits:
  1

Summary metrics are your model's outputs. Learn more

▶
Summary metrics:{} 63 keys
- global_step:
  9,953,280
- len/len:
  991.2999877929688
- len/len_max:
  1,000
- len/len_min:
  130
- perf/_fps:
  13,036.1767578125
- perf/_sample_throughput:
  12,164.642578125
- policy_stats/avg_max_raw_reward:
  11.54123306274414
- policy_stats/avg_min_raw_reward:
  -0.4414851665496826
- reward/reward:
  6,025.62060546875
- reward/reward_max:
  6,208.41455078125
- reward/reward_min:
  330.9393615722656
- stats/avg_request_count:
  1
- stats/gpu_cache_learner:
  29.36012840270996
- stats/gpu_cache_policy_worker:
  29.36012840270996
- stats/gpu_mem_learner:
  3.5297279357910156
- stats/gpu_mem_policy_worker:
  2.690560102462769
- stats/master_process_memory_mb:
  3,178.58203125
- stats/memory_learner:
  3,178.58203125
- stats/memory_policy_worker:
  3,178.58203125
- stats/step_policy:
  0.001466493587940931
- stats/wait_policy:
  0
- train/action_log_std_max:
  -1.0992203950881958
- train/action_log_std_mean:
  -1.3277108669281006
- train/action_log_std_min:
  -1.5235264301300049
- train/action_mean:
  0.42188435792922974
- train/action_mean_max:
  4.3115081787109375
- train/action_mean_min:
  -4.56080961227417
- train/action_stddev_max:
  0.33313068747520447
- train/action_stddev_mean:
  0.26849883794784546
- train/action_stddev_min:
  0.2179419696331024
- train/actual_lr:
  0.0003000000142492354
- train/adam_max_second_moment:
  0.01404708530753851
- train/adv_max:
  7.592462539672852
- train/adv_min:
  -7.751794815063477
- train/adv_std:
  0.5629323124885559
- train/entropy:
  0.5473653078079224
- train/exploration_loss:
  0
- train/fraction_clipped:
  0.23876953125
- train/grad_norm:
  0.9999997615814208
- train/kl_divergence:
  0.014372247271239758
- train/kl_divergence_max:
  0.07351213693618774
- train/kl_loss:
  0.0014372247969731688
- train/loss:
  -0.009720317088067532
- train/lr:
  0.0003000000142492354
- train/max_abs_logprob:
  4.559576988220215
- train/num_sgd_steps:
  20
- train/value_loss:
  0.0030097414273768663
- train/version_diff_avg:
  19
- train/version_diff_max:
  19
- train/version_diff_min:
  19

This run produced these artifacts as outputs. Total: 1. Learn more

wandb-history

run-envpool_walker_20221214_041856_142663-history:v0