single-shot-robot

Josselin's group workspace

Group: CARE_PTSL_res_sum

1-1

of 1

Tags

Notes

Author

josselin

State

Finished

Start time

June 2nd, 2023 10:44:07 AM

Runtime

18m 24s

Tracked hours

18m 20s

Run path

single-shot-robot/PTSL_MTRL10-200k/5z7k21ik

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_PTSL_res_sum_1" ab657e27077c3651fb35e14544c2f98c68907237

Command

main.py setup=metaworld env=metaworld-mt10 agent=state_sac agent.actor.hidden_dim=326 agent.actor.num_layers=3 experiment.num_eval_episodes=10 experiment.num_train_steps=200000 setup.seed_ref=1 setup.num_seeds=10 setup.name=PAL_same_sum replay_buffer.batch_size=1280 agent.encoder.type_to_select=moe agent.encoder.moe.task_id_to_encoder_id_cfg.mode=attention agent.encoder.moe.num_experts=4 agent.multitask.num_envs=10 agent.multitask.should_use_disentangled_alpha=True agent.multitask.should_use_task_encoder=True agent.multitask.should_use_multi_head_policy=False agent.multitask.task_encoder_cfg.model_cfg.pretrained_embedding_cfg.should_use=True agent.multitask.should_use_pal=True agent.multitask.pal_cfg.pal_dim=50 agent.multitask.pal_cfg.shared_projection=True agent.multitask.pal_cfg.residual_mode=sum

System Hardware

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

Group

CARE_PTSL_res_sum

Config parameters are your model's inputs. Learn more

▶
Config parameters:{} 21 keys
- actor/hidden_dim:
  326
- 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:
  200,000
- pal/dim:
  50
- pal/residual:
  "sum"
- pal/shared:
  true
- seed:
  1

Summary metrics are your model's outputs. Learn more

▶
Summary metrics:{} 32 keys
- Env 0/episode_reward_env_index_:
  38.86957877097501
- Env 0/success_env_index_:
  0
- Env 1/episode_reward_env_index_:
  -635.6066617626684
- Env 1/success_env_index_:
  0
- Env 2/episode_reward_env_index_:
  -505.7435875202741
- Env 2/success_env_index_:
  0
- Env 3/episode_reward_env_index_:
  -674.8722779285836
- Env 3/success_env_index_:
  0
- Env 4/episode_reward_env_index_:
  594.0659366439154
- Env 4/success_env_index_:
  0
- Env 5/episode_reward_env_index_:
  -593.3056467342718
- Env 5/success_env_index_:
  0
- Env 6/episode_reward_env_index_:
  -849.912043753589
- Env 6/success_env_index_:
  0
- Env 7/episode_reward_env_index_:
  -745.2982063406846
- Env 7/success_env_index_:
  0
- Env 8/episode_reward_env_index_:
  -577.7326328687918
- Env 8/success_env_index_:
  0
- Env 9/episode_reward_env_index_:
  -539.0985070020541
- Env 9/success_env_index_:
  0
- Eval/episode:
  0
- Eval/episode_reward:
  16.084828038748377
- Eval/success:
  0
- Train/actor_entropy:
  9.264066880544028
- Train/actor_loss:
  3,875,197.553333333
- Train/actor_target_entropy:
  -4
- Train/alpha_loss:
  -137,912.6465625
- Train/batch_reward:
  -1.976002790927887
- Train/critic_loss:
  57,778,227.22666667
- Train/duration:
  7.496419906616211
- Train/episode:
  138
- Train/success:
  0

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

wandb-history

run-5z7k21ik-history:v0