andrewzhang505

Andrewzhang505's group workspace

Group: mujoco_ant

1-1

of 1

Tags

envpool_doublebuffer

Author

andrewzhang505

State

Finished

Start time

December 13th, 2022 2:36:07 AM

Runtime

21m 55s

Tracked hours

21m 45s

Run path

andrewzhang505/sample_factory/envpool_ant_doublebuffer_20221213_023606_475048

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_ant_doublebuffer_20221213_023606_475048" 0319b736bfad9cf54f8f3ad6ab669193d3ca1d8b

Command

-m sf_examples.envpool.mujoco.train_envpool_mujoco --algo=APPO --env=mujoco_ant --experiment=envpool_ant_doublebuffer --with_wandb=True --wandb_tags envpool_doublebuffer

System Hardware

CPU count	8
GPU count	1
GPU type	Tesla T4

W&B CLI Version

0.12.20

Group

mujoco_ant

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:{} 5 keys
- command_line:
  "--algo=APPO --env=mujoco_ant --experiment=envpool_ant_doublebuffer --with_wandb=True --wandb_tags envpool_doublebuffer"
- 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_ant"
- env_agents:
  32
- 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_ant_doublebuffer"
- 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:
  2

Summary metrics are your model's outputs. Learn more

▶
Summary metrics:{} 63 keys
- global_step:
  9,936,896
- len/len:
  969.3099975585938
- len/len_max:
  1,000
- len/len_min:
  205
- perf/_fps:
  8,194.5419921875
- perf/_sample_throughput:
  7,922.6640625
- policy_stats/avg_max_raw_reward:
  8.483712196350098
- policy_stats/avg_min_raw_reward:
  -1.50512433052063
- reward/reward:
  6,048.70361328125
- reward/reward_max:
  6,707.3974609375
- reward/reward_min:
  1,215.1627197265625
- stats/avg_request_count:
  2
- stats/gpu_cache_learner:
  31.457279205322266
- stats/gpu_cache_policy_worker:
  31.457279205322266
- stats/gpu_mem_learner:
  2.9061119556427
- stats/gpu_mem_policy_worker:
  2.203648090362549
- stats/master_process_memory_mb:
  3,156.76171875
- stats/memory_learner:
  3,156.76171875
- stats/memory_policy_worker:
  3,156.76171875
- stats/step_policy:
  0.001596054993569851
- stats/wait_policy:
  0
- train/action_log_std_max:
  -1.9939621686935425
- train/action_log_std_mean:
  -2.2467947006225586
- train/action_log_std_min:
  -2.694455862045288
- train/action_mean:
  -0.002763079944998026
- train/action_mean_max:
  1.6965559720993042
- train/action_mean_min:
  -1.841118097305298
- train/action_stddev_max:
  0.1361548900604248
- train/action_stddev_mean:
  0.10818690061569214
- train/action_stddev_min:
  0.06757914274930954
- train/actual_lr:
  0.00013333333481568843
- train/adam_max_second_moment:
  0.021916618570685387
- train/adv_max:
  7.762033462524414
- train/adv_min:
  -4.368725299835205
- train/adv_std:
  1.0660021305084229
- train/entropy:
  -6.622849464416504
- train/exploration_loss:
  0
- train/fraction_clipped:
  0.24853515625
- train/grad_norm:
  1
- train/kl_divergence:
  0.014196175150573254
- train/kl_divergence_max:
  0.16953618824481964
- train/kl_loss:
  0.0011723212664946914
- train/loss:
  0.003183234017342329
- train/lr:
  0.00013333333481568843
- train/max_abs_logprob:
  2.6945154666900635
- train/num_sgd_steps:
  8
- train/value_loss:
  0.0050620632246136665
- train/version_diff_avg:
  3
- train/version_diff_max:
  3
- train/version_diff_min:
  3

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

wandb-history

run-envpool_ant_doublebuffer_20221213_023606_475048-history:v0