andrewzhang505

Andrewzhang505's group workspace

Group: mujoco_doublependulum

1-1

of 1

Tags

async

mujoco

Author

andrewzhang505

State

Finished

Start time

July 13th, 2022 10:52:25 PM

Runtime

8m 48s

Tracked hours

8m 39s

Run path

andrewzhang505/sample_factory/81_mujoco_all_envs_see_4444_env_mujoco_doublependulum_a.rl_True_20220713_155223_994468

Linux-5.13.0-35-generic-x86_64-with-glibc2.31

Python version

3.10.5

Command

-m sf_examples.mujoco_examples.train_mujoco --algo=APPO --with_wandb=True --wandb_tags mujoco async --seed=4444 --env=mujoco_doublependulum --async_rl=True --experiment=81_mujoco_all_envs_see_4444_env_mujoco_doublependulum_a.rl_True --train_dir=./train_dir/mujoco_all_envs/mujoco_all_envs_slurm

System Hardware

CPU count	72
GPU count	1
GPU type	NVIDIA GeForce RTX 2080 Ti

W&B CLI Version

0.12.21

Group

mujoco_doublependulum

Job Type

Config parameters are your model's inputs. Learn more

▶
Config parameters:{} 110 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:
  true
- batch_size:
  1,024
- batched_sampling:
  false
- benchmark:
  false
- ▶
  cli_args:{} 8 keys
- command_line:
  "--algo=APPO --with_wandb=True --wandb_tags mujoco async --seed=4444 --env=mujoco_doublependulum --async_rl=True --experiment=81_mujoco_all_envs_see_4444_env_mujoco_doublependulum_a.rl_True --train_dir=./train_dir/mujoco_all_envs/mujoco_all_envs_slurm"
- decorrelate_envs_on_one_worker:
  true
- decorrelate_experience_max_seconds:
  10
- default_niceness:
  0
- device:
  "gpu"
- encoder_custom:
  null
- encoder_extra_fc_layers:
  0
- encoder_subtype:
  "mlp_mujoco"
- encoder_type:
  "mlp"
- env:
  "mujoco_doublependulum"
- env_frameskip:
  1
- env_framestack:
  4
- env_gpu_actions:
  false
- experiment:
  "81_mujoco_all_envs_see_4444_env_mujoco_doublependulum_a.rl_True"
- experiment_summaries_interval:
  3
- exploration_loss:
  "entropy"
- exploration_loss_coeff:
  0
- force_envs_single_thread:
  true
- gae_lambda:
  0.95
- gamma:
  0.99
- git_hash:
  "unknown"
- git_repo_name:
  "not a git repository"
- help:
  false
- hidden_size:
  64
- initial_stddev:
  1
- keep_checkpoints:
  3
- kl_loss_coeff:
  0.1
- learning_rate:
  0.00295
- load_checkpoint_kind:
  "latest"
- lr_schedule:
  "linear_decay"
- lr_schedule_kl_threshold:
  0.008
- max_grad_norm:
  3.5
- max_policy_lag:
  10,000
- nonlinearity:
  "tanh"
- with_pbt:
  false
- with_vtrace:
  false
- with_wandb:
  true
- worker_num_splits:
  2

Summary metrics are your model's outputs. Learn more

▶
Summary metrics:{} 63 keys
- global_step:
  9,986,048
- len/len:
  990.3400268554688
- len/len_max:
  1,000
- len/len_min:
  34
- perf/_fps:
  20,070.60546875
- perf/_sample_throughput:
  41,172.2890625
- policy_stats/avg_true_objective:
  9,265.025390625
- policy_stats/avg_true_objective_max:
  9,356.162109375
- policy_stats/avg_true_objective_min:
  316.13519287109375
- reward/reward:
  9,265.025390625
- reward/reward_max:
  9,356.162109375
- reward/reward_min:
  316.13519287109375
- stats/avg_request_count:
  6.400000095367432
- stats/gpu_cache_learner:
  4.1943039894104
- stats/gpu_cache_policy_worker:
  2.0971519947052
- stats/gpu_mem_learner:
  1.398784041404724
- stats/gpu_mem_policy_worker:
  0.027135999873280525
- stats/master_process_memory_mb:
  331.72265625
- stats/memory_learner:
  2,802.06640625
- stats/memory_policy_worker:
  2,809.53125
- stats/step_policy:
  0.0012115335557609797
- stats/wait_policy:
  0.00002677917473192792
- train/action_log_std_max:
  -2.528366804122925
- train/action_log_std_mean:
  -2.528366804122925
- train/action_log_std_min:
  -2.528366804122925
- train/action_mean:
  0.007389828097075224
- train/action_mean_max:
  1.3209435939788818
- train/action_mean_min:
  -1.2960169315338137
- train/action_stddev_max:
  0.07978922873735428
- train/action_stddev_mean:
  0.07978922873735428
- train/action_stddev_min:
  0.07978922873735428
- train/adam_max_second_moment:
  0.16130749881267548
- train/adv_max:
  1.02894926071167
- train/adv_min:
  -11.758828163146973
- train/adv_std:
  72.06507110595703
- train/entropy:
  -1.1094282865524292
- train/exploration_loss:
  0
- train/fraction_clipped:
  0.0009765625
- train/grad_norm:
  2.3225109577178955
- train/kl_divergence:
  0.0009306968422606588
- train/kl_divergence_max:
  0.0026545317377895117
- train/kl_loss:
  0.00009306968422606587
- train/loss:
  0.31604355573654175
- train/lr:
  0.00004259600609657355
- train/max_abs_logprob:
  2.528564214706421
- train/num_sgd_steps:
  8
- train/value_loss:
  0.3145906627178192
- train/version_diff_avg:
  9.59375
- train/version_diff_max:
  15
- train/version_diff_min:
  7

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

wandb-history

run-81_mujoco_all_envs_see_4444_env_mujoco_doublependulum_a.rl_True_20220713_155223_994468-history:v0