single-shot-robot

Yonigoz's group workspace

Group: PCGrad

1-4

of 4

Tags

Notes

Author

josselin

State

Finished

Start time

May 27th, 2023 5:26:27 PM

Runtime

18h 37m 2s

Tracked hours

18h 36m 58s

Run path

single-shot-robot/PTSL_MTRL10-1M/6iiuxqbt

Linux-5.15.0-1031-aws-x86_64-with-glibc2.10

Python version

3.8.0

Git repository

git clone https://github.com/JosselinSomervilleRoberts/mtrl.git

Git state

git checkout -b "PCGrad_1" 007f017f0850a693791fd8e1bb9c64ab36c8b4d8

Command

main.py setup=metaworld env=metaworld-mt10 agent=pcgrad_state_sac experiment.num_eval_episodes=10 experiment.num_train_steps=1000000 replay_buffer.batch_size=1280 agent.multitask.num_envs=10 agent.multitask.should_use_disentangled_alpha=False agent.multitask.should_use_task_encoder=False agent.multitask.actor_cfg.should_condition_encoder_on_task_info=False agent.multitask.actor_cfg.should_concatenate_task_info_with_encoder=False agent.encoder.type_to_select=identity setup.seed=1 name=PCGrad

System Hardware

CPU count	2
Logical CPU count	4
GPU count	1
GPU type	Tesla T4

W&B CLI Version

0.15.3

Group

PCGrad

Config parameters are your model's inputs. Learn more

▶
Config parameters:{} 18 keys
- actor/hidden_dim:
  400
- actor/num_layer:
  3
- agent:
  "pcgrad_state_sac"
- agent/encoder_feature_dim:
  50
- agent/num_filters:
  0
- agent/num_layers:
  0
- batch_size:
  1,280
- encoder:
  "identity"
- eval_freq:
  10,000
- lr/actor:
  0.0003
- lr/alpha:
  0.0003
- lr/critic:
  0.0003
- lr/decoder:
  0.0003
- lr/encoder:
  0.0003
- num_eval_episodes:
  10
- num_tasks:
  10
- num_train_steps:
  1,000,000
- seed:
  1

Summary metrics are your model's outputs. Learn more

▶
Summary metrics:{} 32 keys
- Env 0/episode_reward_env_index_:
  454.86301107341274
- Env 0/success_env_index_:
  1
- Env 1/episode_reward_env_index_:
  180.84208835975693
- Env 1/success_env_index_:
  1
- Env 2/episode_reward_env_index_:
  112.42128685997032
- Env 2/success_env_index_:
  1
- Env 3/episode_reward_env_index_:
  17.283672497779584
- Env 3/success_env_index_:
  0
- Env 4/episode_reward_env_index_:
  262.0542491284178
- Env 4/success_env_index_:
  1
- Env 5/episode_reward_env_index_:
  224.7334510324711
- Env 5/success_env_index_:
  1
- Env 6/episode_reward_env_index_:
  248.1214983312256
- Env 6/success_env_index_:
  1
- Env 7/episode_reward_env_index_:
  203.49415226029652
- Env 7/success_env_index_:
  1
- Env 8/episode_reward_env_index_:
  137.98263509607617
- Env 8/success_env_index_:
  0
- Env 9/episode_reward_env_index_:
  73.01406425242314
- Env 9/success_env_index_:
  0
- Eval/episode:
  6,600
- Eval/episode_reward:
  196.18717653779527
- Eval/success:
  0.7
- Train/actor_entropy:
  1.0086787637074788
- Train/actor_loss:
  -134.5966896565755
- Train/actor_target_entropy:
  -4
- Train/alpha_loss:
  0.039022663086652754
- Train/batch_reward:
  1.315430657863617
- Train/critic_loss:
  45.50425179799398
- Train/duration:
  10.366211891174316
- Train/episode:
  6,666
- Train/success:
  0.7

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

wandb-history

run-6iiuxqbt-history:v0