single-shot-robot

Yonigoz's group workspace

Group: SAC_PTSL

1-4

of 4

Tags

Notes

Author

yonigoz

State

Finished

Start time

September 15th, 2023 6:26:04 AM

Runtime

9h 9m 34s

Tracked hours

9h 9m 29s

Run path

single-shot-robot/PTSL_MTRL10-1M/gv3cmh61

Linux-6.2.0-32-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 "SAC_PTSL_3" db3d0484eb9ae1f31725752bd3e57305a2867bac

Command

main.py setup=metaworld env=metaworld-mt10 agent=state_sac agent.actor.hidden_dim=367 agent.actor.num_layers=3 agent.multitask.num_envs=10 experiment.num_eval_episodes=10 experiment.num_train_steps=1000000 setup.seed_ref=3 setup.num_seeds=1 setup.name=SAC_PTSL replay_buffer.batch_size=1280 agent.encoder.type_to_select=identity agent.multitask.num_envs=10 agent.multitask.should_use_disentangled_alpha=True agent.multitask.should_use_multi_head_policy=False agent.multitask.actor_cfg.should_condition_model_on_task_info=False agent.multitask.actor_cfg.should_condition_encoder_on_task_info=True agent.multitask.actor_cfg.should_concatenate_task_info_with_encoder=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	8
Logical CPU count	16
GPU count	1
GPU type	NVIDIA GeForce RTX 3050 Ti Laptop GPU

W&B CLI Version

0.15.3

Group

SAC_PTSL

Config parameters are your model's inputs. Learn more

▶
Config parameters:{} 21 keys
- actor/hidden_dim:
  367
- 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:
  "identity"
- 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:
  1,000,000
- pal/dim:
  50
- pal/residual:
  "none"
- pal/shared:
  true
- seed:
  3

Summary metrics are your model's outputs. Learn more

▶
Summary metrics:{} 32 keys
- Env 0/episode_reward_env_index_:
  420.25534112009433
- Env 0/success_env_index_:
  1
- Env 1/episode_reward_env_index_:
  211.26107773888387
- Env 1/success_env_index_:
  1
- Env 2/episode_reward_env_index_:
  0.08042427413143917
- Env 2/success_env_index_:
  0
- Env 3/episode_reward_env_index_:
  193.6229970341396
- Env 3/success_env_index_:
  1
- Env 4/episode_reward_env_index_:
  86.0495440513973
- Env 4/success_env_index_:
  1
- Env 5/episode_reward_env_index_:
  213.3853039523607
- Env 5/success_env_index_:
  1
- Env 6/episode_reward_env_index_:
  244.8780268807752
- Env 6/success_env_index_:
  1
- Env 7/episode_reward_env_index_:
  222.33570267314167
- Env 7/success_env_index_:
  0
- Env 8/episode_reward_env_index_:
  148.85564238901614
- Env 8/success_env_index_:
  0
- Env 9/episode_reward_env_index_:
  13.855209264197454
- Env 9/success_env_index_:
  0
- Eval/episode:
  6,600
- Eval/episode_reward:
  170.0922831803911
- Eval/success:
  0.6
- Train/actor_entropy:
  0.23026229677100976
- Train/actor_loss:
  -133.82656372070312
- Train/actor_target_entropy:
  -4
- Train/alpha_loss:
  0.00008649401880878334
- Train/batch_reward:
  1.1717817060152689
- Train/critic_loss:
  49.20649739583333
- Train/duration:
  5.734043598175049
- Train/episode:
  6,666
- Train/success:
  0.6

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

wandb-history

run-gv3cmh61-history:v0