single-shot-robot

Josselin's group workspace

Group: CARE_PTSL_deep

1-10

of 10

Tags

Notes

Author

josselin

State

Finished

Start time

June 3rd, 2023 11:00:39 AM

Runtime

2h 48m 6s

Tracked hours

2h 47m 59s

Run path

single-shot-robot/PTSL_MTRL10-200k/qdoyg083

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_deep_10" 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 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=none

System Hardware

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

Group

CARE_PTSL_deep

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:
  "none"
- pal/shared:
  true
- seed:
  10

Summary metrics are your model's outputs. Learn more

▶
Summary metrics:{} 32 keys
- Env 0/episode_reward_env_index_:
  437.52714314612894
- Env 0/success_env_index_:
  1
- Env 1/episode_reward_env_index_:
  138.0404229395928
- Env 1/success_env_index_:
  1
- Env 2/episode_reward_env_index_:
  199.6764431440155
- Env 2/success_env_index_:
  0
- Env 3/episode_reward_env_index_:
  142.54652341896082
- Env 3/success_env_index_:
  0
- Env 4/episode_reward_env_index_:
  573.4514961506615
- Env 4/success_env_index_:
  0
- Env 5/episode_reward_env_index_:
  128.97733506400292
- Env 5/success_env_index_:
  1
- Env 6/episode_reward_env_index_:
  283.48600674963876
- Env 6/success_env_index_:
  1
- Env 7/episode_reward_env_index_:
  141.58975863909137
- Env 7/success_env_index_:
  0
- Env 8/episode_reward_env_index_:
  117.43933729250104
- Env 8/success_env_index_:
  0
- Env 9/episode_reward_env_index_:
  52.21375013995967
- Env 9/success_env_index_:
  0
- Eval/episode:
  1,200
- Eval/episode_reward:
  323.2343068810582
- Eval/success:
  0.4
- Train/actor_entropy:
  1.2400127092997233
- Train/actor_loss:
  -135.8480662027995
- Train/actor_target_entropy:
  -4
- Train/alpha_loss:
  -0.0005089357505494263
- Train/batch_reward:
  1.175105917453766
- Train/critic_loss:
  38.8988447825114
- Train/duration:
  7.735539197921753
- Train/episode:
  1,333
- Train/success:
  0.4

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

wandb-history

run-qdoyg083-history:v0