single-shot-robot

Josselin's group workspace

Group: SAC

1-4

of 4

Tags

Notes

Author

josselin

State

Finished

Start time

September 14th, 2023 1:10:38 AM

Runtime

6h 42m 41s

Tracked hours

6h 42m 36s

Run path

single-shot-robot/PTSL_MTRL50-1M/zo8rwxmx

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 "SAC_4" ea3e61c6ee556dec14f1592437e0c08362d94677

Command

main.py setup=metaworld env=metaworld-mt50 agent=state_sac agent.actor.hidden_dim=400 agent.actor.num_layers=3 agent.multitask.num_envs=50 experiment.num_eval_episodes=10 experiment.num_train_steps=1000000 setup.seed_ref=3 setup.num_seeds=2 setup.name=SAC replay_buffer.batch_size=1280 agent.encoder.type_to_select=identity agent.multitask.num_envs=50 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

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

SAC

Config parameters are your model's inputs. Learn more

▶
Config parameters:{} 21 keys
- actor/hidden_dim:
  400
- actor/num_layer:
  3
- agent:
  "state_sac"
- agent/encoder_feature_dim:
  12
- 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:
  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_:
  453.09992825695815
- Env 0/success_env_index_:
  1
- Env 1/episode_reward_env_index_:
  232.24629959513467
- Env 1/success_env_index_:
  1
- Env 2/episode_reward_env_index_:
  25.53786469801291
- Env 2/success_env_index_:
  0
- Env 3/episode_reward_env_index_:
  134.1562420520353
- Env 3/success_env_index_:
  1
- Env 4/episode_reward_env_index_:
  282.47534725532086
- Env 4/success_env_index_:
  0
- Env 5/episode_reward_env_index_:
  166.42051398081344
- Env 5/success_env_index_:
  1
- Env 6/episode_reward_env_index_:
  267.45526732029293
- Env 6/success_env_index_:
  1
- Env 7/episode_reward_env_index_:
  59.205228734713415
- Env 7/success_env_index_:
  1
- Env 8/episode_reward_env_index_:
  144.7289158358012
- Env 8/success_env_index_:
  0
- Env 9/episode_reward_env_index_:
  135.08255339528793
- Env 9/success_env_index_:
  0
- Env 10/episode_reward_env_index_:
  290.6067068807581
- Env 10/success_env_index_:
  0
- Env 11/episode_reward_env_index_:
  372.4486649072333
- Env 11/success_env_index_:
  1
- Env 12/episode_reward_env_index_:
  154.6946020087427
- Env 12/success_env_index_:
  1
- Env 13/episode_reward_env_index_:
  -0.044437915846965576
- Env 13/success_env_index_:
  0
- Env 14/episode_reward_env_index_:
  487.24048219074695
- Env 14/success_env_index_:
  1
- Env 15/episode_reward_env_index_:
  142.55307576270425
- Env 15/success_env_index_:
  1
- Env 16/episode_reward_env_index_:
  313.83729543458145
- Env 16/success_env_index_:
  0
- Env 17/episode_reward_env_index_:
  247.10085554381712
- Env 17/success_env_index_:
  1
- Env 18/episode_reward_env_index_:
  153.7430462766382
- Env 18/success_env_index_:
  0
- Env 19/episode_reward_env_index_:
  195.24574642339803
- Env 19/success_env_index_:
  0
- Env 20/episode_reward_env_index_:
  277.88578396909566
- Env 20/success_env_index_:
  0
- Env 21/episode_reward_env_index_:
  182.66169888583636
- Env 21/success_env_index_:
  1
- Env 22/episode_reward_env_index_:
  324.7169171007851
- Env 22/success_env_index_:
  0
- Train/critic_loss:
  50.74616563161214
- Train/duration:
  3.622872829437256
- Train/episode:
  6,666
- Train/success:
  0.5

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

wandb-history

run-zo8rwxmx-history:v0