single-shot-robot

Josselin's group workspace

Group: soft_modularization

1-4

of 4

Tags

Notes

Author

josselin

State

Finished

Start time

September 14th, 2023 4:46:48 AM

Runtime

14h 1m 43s

Tracked hours

14h 1m 34s

Run path

single-shot-robot/PTSL_MTRL50-1M/zfvn513c

Linux-5.15.0-76-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 "soft_modularization_4" ea3e61c6ee556dec14f1592437e0c08362d94677

Command

main.py setup=metaworld env=metaworld-mt50 agent=state_sac experiment.num_eval_episodes=10 experiment.num_train_steps=1000000 setup.seed_ref=4 setup.num_seeds=1 setup.name=soft_modularization replay_buffer.batch_size=1280 agent.multitask.num_envs=50 agent.multitask.should_use_disentangled_alpha=True agent.multitask.should_use_task_encoder=True agent.encoder.type_to_select=feedforward agent.multitask.actor_cfg.should_condition_model_on_task_info=True agent.multitask.actor_cfg.should_condition_encoder_on_task_info=False agent.multitask.actor_cfg.should_concatenate_task_info_with_encoder=False agent.multitask.actor_cfg.moe_cfg.should_use=True agent.multitask.actor_cfg.moe_cfg.mode=soft_modularization agent.multitask.should_use_multi_head_policy=False agent.encoder.feedforward.hidden_dim=50 agent.encoder.feedforward.num_layers=2 agent.encoder.feedforward.feature_dim=50 agent.actor.num_layers=4 agent.multitask.task_encoder_cfg.model_cfg.pretrained_embedding_cfg.should_use=False

System Hardware

CPU count	6
Logical CPU count	12
GPU count	1
GPU type	NVIDIA GeForce GTX 1650

W&B CLI Version

0.15.3

Group

soft_modularization

Config parameters are your model's inputs. Learn more

▶
Config parameters:{} 21 keys
- actor/hidden_dim:
  326
- actor/num_layer:
  4
- agent:
  "state_sac"
- agent/encoder_feature_dim:
  50
- agent/num_filters:
  0
- agent/num_layers:
  0
- batch_size:
  1,280
- encoder:
  "feedforward"
- 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:
  50
- num_train_steps:
  1,000,000
- pal/dim:
  50
- pal/residual:
  "none"
- pal/shared:
  true
- seed:
  4

Summary metrics are your model's outputs. Learn more

▶
Summary metrics:{} 112 keys
- Env 0/episode_reward_env_index_:
  446.1634646226054
- Env 0/success_env_index_:
  0
- Env 1/episode_reward_env_index_:
  36.15405914013871
- Env 1/success_env_index_:
  0
- Env 2/episode_reward_env_index_:
  -462.3237910814264
- Env 2/success_env_index_:
  0
- Env 3/episode_reward_env_index_:
  -1,700.475336594404
- Env 3/success_env_index_:
  0
- Env 4/episode_reward_env_index_:
  340.2036387360566
- Env 4/success_env_index_:
  0
- Env 5/episode_reward_env_index_:
  134.6127354463489
- Env 5/success_env_index_:
  0
- Env 6/episode_reward_env_index_:
  272.69434418129987
- Env 6/success_env_index_:
  0
- Env 7/episode_reward_env_index_:
  -146.8015532980996
- Env 7/success_env_index_:
  0
- Env 8/episode_reward_env_index_:
  123.34472111998292
- Env 8/success_env_index_:
  0
- Env 9/episode_reward_env_index_:
  81.84319092538198
- Env 9/success_env_index_:
  0
- Env 10/episode_reward_env_index_:
  2.170348293869879
- Env 10/success_env_index_:
  1
- Env 11/episode_reward_env_index_:
  407.5051132944145
- Env 11/success_env_index_:
  1
- Env 12/episode_reward_env_index_:
  -8.058100205528875
- Env 12/success_env_index_:
  0
- Env 13/episode_reward_env_index_:
  72.83580844800748
- Env 13/success_env_index_:
  0
- Env 14/episode_reward_env_index_:
  592.5104576799075
- Env 14/success_env_index_:
  1
- Env 15/episode_reward_env_index_:
  237.65502111281737
- Env 15/success_env_index_:
  0
- Env 16/episode_reward_env_index_:
  362.92634004423263
- Env 16/success_env_index_:
  1
- Env 17/episode_reward_env_index_:
  389.5098182169704
- Env 17/success_env_index_:
  0
- Env 18/episode_reward_env_index_:
  -49.611152964959615
- Env 18/success_env_index_:
  0
- Env 19/episode_reward_env_index_:
  -7.178246026944359
- Env 19/success_env_index_:
  0
- Env 20/episode_reward_env_index_:
  0.36659489730643496
- Env 20/success_env_index_:
  0
- Env 21/episode_reward_env_index_:
  192.28967923883303
- Env 21/success_env_index_:
  0
- Env 22/episode_reward_env_index_:
  240.13881859518887
- Env 22/success_env_index_:
  0
- Train/critic_loss:
  84.54993893941243
- Train/duration:
  7.432565450668335
- Train/episode:
  6,665
- Train/success:
  0.14

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

wandb-history

run-zfvn513c-history:v2