single-shot-robot

Josselin's group workspace

Group: CARE_PTSL_res_project

1-10

of 10

Tags

Notes

Author

josselin

State

Finished

Start time

September 15th, 2023 9:40:25 AM

Runtime

1h 48m 39s

Tracked hours

1h 48m 32s

Run path

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

Linux-5.4.0-150-generic-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_project_10" db3d0484eb9ae1f31725752bd3e57305a2867bac

Command

main.py setup=metaworld env=metaworld-mt10 agent=state_sac agent.actor.hidden_dim=321 agent.actor.num_layers=3 experiment.num_eval_episodes=10 experiment.num_train_steps=200000 setup.seed_ref=10 setup.num_seeds=1 setup.name=PAL_shared 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=project

System Hardware

CPU count	8
Logical CPU count	8
GPU count	1
GPU type	NVIDIA GeForce RTX 2080

Group

CARE_PTSL_res_project

Config parameters are your model's inputs. Learn more

▶
Config parameters:{} 21 keys
- actor/hidden_dim:
  321
- 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:
  "project"
- pal/shared:
  true
- seed:
  10

Summary metrics are your model's outputs. Learn more

▶
Summary metrics:{} 32 keys
- Env 0/episode_reward_env_index_:
  429.54874615313304
- Env 0/success_env_index_:
  1
- Env 1/episode_reward_env_index_:
  36.37182106538025
- Env 1/success_env_index_:
  0
- Env 2/episode_reward_env_index_:
  2.9599598825276727
- Env 2/success_env_index_:
  0
- Env 3/episode_reward_env_index_:
  117.83457250888094
- Env 3/success_env_index_:
  1
- Env 4/episode_reward_env_index_:
  155.8707733003368
- Env 4/success_env_index_:
  0
- Env 5/episode_reward_env_index_:
  247.20993527989708
- Env 5/success_env_index_:
  1
- Env 6/episode_reward_env_index_:
  285.0991371415643
- Env 6/success_env_index_:
  1
- Env 7/episode_reward_env_index_:
  169.8324194846818
- Env 7/success_env_index_:
  0
- Env 8/episode_reward_env_index_:
  62.04939022956934
- Env 8/success_env_index_:
  0
- Env 9/episode_reward_env_index_:
  2.2943269501186356
- Env 9/success_env_index_:
  0
- Eval/episode:
  1,200
- Eval/episode_reward:
  149.71231522499585
- Eval/success:
  0.4
- Train/actor_entropy:
  1.6516820693016052
- Train/actor_loss:
  -114.72340861002604
- Train/actor_target_entropy:
  -4
- Train/alpha_loss:
  -0.0018692765277107052
- Train/batch_reward:
  1.0631700412432352
- Train/critic_loss:
  42.459976018269856
- Train/duration:
  4.8598010540008545
- Train/episode:
  1,333
- Train/success:
  0.4

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

wandb-history

run-lkbzusvx-history:v0