single-shot-robot

Josselin's group workspace

Group: CARE_PTSL_deep

1-4

of 4

Tags

Notes

Author

josselin

State

Finished

Start time

September 15th, 2023 6:47:36 AM

Runtime

13h 58m 43s

Tracked hours

13h 58m 38s

Run path

single-shot-robot/PTSL_MTRL50-1M/sea2i652

Linux-5.15.0-83-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_deep_2" ea3e61c6ee556dec14f1592437e0c08362d94677

Command

main.py setup=metaworld env=metaworld-mt50 agent=state_sac agent.actor.hidden_dim=274 agent.actor.num_layers=3 experiment.num_eval_episodes=50 experiment.num_train_steps=1000000 setup.seed_ref=2 setup.num_seeds=1 setup.name=CARE_PTSL_deep 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=50 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=32 agent.multitask.pal_cfg.shared_projection=True agent.multitask.pal_cfg.residual_mode=none

System Hardware

CPU count	6
Logical CPU count	6
GPU count	1
GPU type	NVIDIA GeForce GTX 1060 6GB

W&B CLI Version

0.15.3

Group

CARE_PTSL_deep

Config parameters are your model's inputs. Learn more

▶
Config parameters:{} 21 keys
- actor/hidden_dim:
  274
- 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:
  50
- num_tasks:
  50
- num_train_steps:
  1,000,000
- pal/dim:
  32
- pal/residual:
  "none"
- pal/shared:
  true
- seed:
  2

Summary metrics are your model's outputs. Learn more

▶
Summary metrics:{} 112 keys
- Env 0/episode_reward_env_index_:
  328.3743725986721
- Env 0/success_env_index_:
  1
- Env 1/episode_reward_env_index_:
  329.80695910870656
- Env 1/success_env_index_:
  0
- Env 2/episode_reward_env_index_:
  -578.7995405721352
- Env 2/success_env_index_:
  0
- Env 3/episode_reward_env_index_:
  14.325172228949585
- Env 3/success_env_index_:
  0
- Env 4/episode_reward_env_index_:
  54.84572104239377
- Env 4/success_env_index_:
  0
- Env 5/episode_reward_env_index_:
  80.79713650314754
- Env 5/success_env_index_:
  1
- Env 6/episode_reward_env_index_:
  255.7153011779784
- Env 6/success_env_index_:
  1
- Env 7/episode_reward_env_index_:
  -0.09383100904515974
- Env 7/success_env_index_:
  0
- Env 8/episode_reward_env_index_:
  -0.050509166667750856
- Env 8/success_env_index_:
  0
- Env 9/episode_reward_env_index_:
  136.8769500496427
- Env 9/success_env_index_:
  0
- Env 10/episode_reward_env_index_:
  160.63678771450944
- Env 10/success_env_index_:
  1
- Env 11/episode_reward_env_index_:
  359.68557486700604
- Env 11/success_env_index_:
  1
- Env 12/episode_reward_env_index_:
  -509.3828039316003
- Env 12/success_env_index_:
  0
- Env 13/episode_reward_env_index_:
  141.1639288317051
- Env 13/success_env_index_:
  0
- Env 14/episode_reward_env_index_:
  466.0895186281691
- Env 14/success_env_index_:
  1
- Env 15/episode_reward_env_index_:
  210.40480987615487
- Env 15/success_env_index_:
  1
- Env 16/episode_reward_env_index_:
  328.7656645472694
- Env 16/success_env_index_:
  0
- Env 17/episode_reward_env_index_:
  68.20547848629175
- Env 17/success_env_index_:
  1
- Env 18/episode_reward_env_index_:
  -213.24441901014515
- Env 18/success_env_index_:
  0
- Env 19/episode_reward_env_index_:
  42.28154363858622
- Env 19/success_env_index_:
  0
- Env 20/episode_reward_env_index_:
  255.49217920155937
- Env 20/success_env_index_:
  1
- Env 21/episode_reward_env_index_:
  264.3864833163946
- Env 21/success_env_index_:
  1
- Env 22/episode_reward_env_index_:
  192.60131471408496
- Env 22/success_env_index_:
  0
- Train/critic_loss:
  56.57539693196615
- Train/duration:
  7.480013608932495
- Train/episode:
  6,666
- Train/success:
  0.38

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

wandb-history

run-sea2i652-history:v0