single-shot-robot

Josselin's group workspace

Group: SAC

1-10

of 10

Tags

Notes

Author

josselin

State

Finished

Start time

May 30th, 2023 6:32:05 AM

Runtime

1h 1m 47s

Tracked hours

1h 1m 43s

Run path

single-shot-robot/PTSL_MTRL10-200k/kwuzkhcl

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 "SAC_10" e31b82b2afe6e5d1ceabde0d2895fff56ef02b42

Command

main.py setup=metaworld env=metaworld-mt10 agent=state_sac experiment.num_eval_episodes=1 experiment.eval_freq=10000 experiment.num_train_steps=200000 setup.seed=2 replay_buffer.batch_size=1280 agent.multitask.num_envs=10 agent.multitask.should_use_disentangled_alpha=True agent.encoder.type_to_select=identity agent.multitask.should_use_multi_head_policy=False agent.multitask.actor_cfg.should_condition_model_on_task_info=False agent.multitask.actor_cfg.should_condition_encoder_on_task_info=True agent.multitask.actor_cfg.should_concatenate_task_info_with_encoder=True name=SAC num_seeds=9

System Hardware

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

W&B CLI Version

0.15.3

Group

SAC

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:
  12
- 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:
  1
- num_tasks:
  10
- num_train_steps:
  200,000
- seed:
  10

Summary metrics are your model's outputs. Learn more

▶
Summary metrics:{} 32 keys
- Env 0/episode_reward_env_index_:
  435.2531124910228
- Env 0/success_env_index_:
  1
- Env 1/episode_reward_env_index_:
  223.01805205108136
- Env 1/success_env_index_:
  1
- Env 2/episode_reward_env_index_:
  36.80993333664134
- Env 2/success_env_index_:
  0
- Env 3/episode_reward_env_index_:
  21.68858875554452
- Env 3/success_env_index_:
  0
- Env 4/episode_reward_env_index_:
  205.594983395673
- Env 4/success_env_index_:
  1
- Env 5/episode_reward_env_index_:
  472.2272128528803
- Env 5/success_env_index_:
  0
- Env 6/episode_reward_env_index_:
  312.8862938331837
- Env 6/success_env_index_:
  1
- Env 7/episode_reward_env_index_:
  -0.32904898223279033
- Env 7/success_env_index_:
  0
- Env 8/episode_reward_env_index_:
  209.33552362928103
- Env 8/success_env_index_:
  0
- Env 9/episode_reward_env_index_:
  476.00418479158384
- Env 9/success_env_index_:
  0
- Eval/episode:
  1,200
- Eval/episode_reward:
  244.3735411860642
- Eval/success:
  0.4
- Train/actor_entropy:
  0.6476910235484441
- Train/actor_loss:
  -173.16345225016275
- Train/actor_target_entropy:
  -4
- Train/alpha_loss:
  -0.0035317477981880075
- Train/batch_reward:
  1.5851002828280132
- Train/critic_loss:
  39.30897746404012
- Train/duration:
  2.7822933197021484
- Train/episode:
  1,333
- Train/success:
  0.4

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

wandb-history

run-kwuzkhcl-history:v0