single-shot-robot

Yonigoz's group workspace

Group: CARE

1-4

of 4

Tags

Notes

Author

josselin

State

Finished

Start time

May 28th, 2023 5:09:47 PM

Runtime

8h 7m 48s

Tracked hours

8h 7m 43s

Run path

single-shot-robot/PTSL_MTRL10-1M/owdhy3ap

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 "CARE_3" 3ae4a0f9340ecd88c4d0f774c985fc51ec7b0205

Command

main.py setup=metaworld env=metaworld-mt10 agent=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=True agent.multitask.should_use_task_encoder=True agent.encoder.type_to_select=moe agent.multitask.should_use_multi_head_policy=False agent.encoder.moe.task_id_to_encoder_id_cfg.mode=attention agent.encoder.moe.num_experts=4 agent.multitask.task_encoder_cfg.model_cfg.pretrained_embedding_cfg.should_use=True setup.seed=3 name=CARE

System Hardware

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

W&B CLI Version

0.15.3

Group

CARE

Config parameters are your model's inputs. Learn more

▶
Config parameters:{} 18 keys
- actor/hidden_dim:
  400
- actor/num_layer:
  3
- agent:
  "state_sac"
- agent/encoder_feature_dim:
  50
- agent/num_filters:
  0
- agent/num_layers:
  0
- batch_size:
  1,280
- encoder:
  "moe"
- 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:
  3

Summary metrics are your model's outputs. Learn more

▶
Summary metrics:{} 32 keys
- Env 0/episode_reward_env_index_:
  420.6599434761925
- Env 0/success_env_index_:
  1
- Env 1/episode_reward_env_index_:
  134.94382521743682
- Env 1/success_env_index_:
  1
- Env 2/episode_reward_env_index_:
  32.156130189502115
- Env 2/success_env_index_:
  0
- Env 3/episode_reward_env_index_:
  31.83010778455333
- Env 3/success_env_index_:
  1
- Env 4/episode_reward_env_index_:
  240.28234760512063
- Env 4/success_env_index_:
  1
- Env 5/episode_reward_env_index_:
  20.685329072868452
- Env 5/success_env_index_:
  0
- Env 6/episode_reward_env_index_:
  260.7726014569247
- Env 6/success_env_index_:
  1
- Env 7/episode_reward_env_index_:
  139.07956963744968
- Env 7/success_env_index_:
  0
- Env 8/episode_reward_env_index_:
  79.70137417059641
- Env 8/success_env_index_:
  0
- Env 9/episode_reward_env_index_:
  135.30952317186018
- Env 9/success_env_index_:
  0
- Eval/episode:
  6,600
- Eval/episode_reward:
  222.6522576990073
- Eval/success:
  0.6
- Train/actor_entropy:
  0.9944871274630228
- Train/actor_loss:
  -129.44297526041666
- Train/actor_target_entropy:
  -4
- Train/alpha_loss:
  -0.001264396146434592
- Train/batch_reward:
  1.2987798833847046
- Train/critic_loss:
  45.02742657979329
- Train/duration:
  4.193268060684204
- Train/episode:
  6,666
- Train/success:
  0.5

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

wandb-history

run-owdhy3ap-history:v0