single-shot-robot

Josselin's group workspace

Group: CARE_PTSL_not_shared

1-10

of 10

Tags

Notes

Author

josselin

State

Finished

Start time

June 2nd, 2023 5:43:09 AM

Runtime

2h 26m 38s

Tracked hours

2h 26m 34s

Run path

single-shot-robot/PTSL_MTRL10-200k/gnz108vn

Linux-5.15.0-1031-aws-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_not_shared_5" b112a394c7c5e732c7a04da188a39c17d628378a

Command

main.py setup=metaworld env=metaworld-mt10 agent=state_sac experiment.num_eval_episodes=10 experiment.num_train_steps=200000 setup.seed=1 replay_buffer.batch_size=1280 agent.multitask.num_envs=10 agent.multitask.should_use_disentangled_alpha=True agent.multitask.should_use_task_encoder=True agent.encoder.type_to_select=moe agent.multitask.should_use_multi_head_policy=False agent.encoder.moe.task_id_to_encoder_id_cfg.mode=attention agent.encoder.moe.num_experts=4 agent.multitask.task_encoder_cfg.model_cfg.pretrained_embedding_cfg.should_use=True name=PAL_not_shared agent.multitask.should_use_pal=True num_seeds=5 agent.multitask.pal_cfg.shared_projection=False

System Hardware

CPU count	2
Logical CPU count	4
GPU count	1
GPU type	Tesla T4

Group

CARE_PTSL_not_shared

Config parameters are your model's inputs. Learn more

▶
Config parameters:{} 18 keys
- actor/hidden_dim:
  400
- 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
- seed:
  5

Summary metrics are your model's outputs. Learn more

▶
Summary metrics:{} 32 keys
- Env 0/episode_reward_env_index_:
  396.25348033759366
- Env 0/success_env_index_:
  1
- Env 1/episode_reward_env_index_:
  225.4822943375956
- Env 1/success_env_index_:
  1
- Env 2/episode_reward_env_index_:
  243.20465337227824
- Env 2/success_env_index_:
  1
- Env 3/episode_reward_env_index_:
  296.30853129921115
- Env 3/success_env_index_:
  1
- Env 4/episode_reward_env_index_:
  37.695328435243866
- Env 4/success_env_index_:
  0
- Env 5/episode_reward_env_index_:
  0.5988000802710197
- Env 5/success_env_index_:
  0
- Env 6/episode_reward_env_index_:
  301.96813407467806
- Env 6/success_env_index_:
  1
- Env 7/episode_reward_env_index_:
  -24.142186595054476
- Env 7/success_env_index_:
  0
- Env 8/episode_reward_env_index_:
  9.845094676629127
- Env 8/success_env_index_:
  0
- Env 9/episode_reward_env_index_:
  158.3408599993437
- Env 9/success_env_index_:
  0
- Eval/episode:
  1,200
- Eval/episode_reward:
  220.03015135910456
- Eval/success:
  0.5
- Train/actor_entropy:
  0.34486184547344845
- Train/actor_loss:
  -144.46584299723307
- Train/actor_target_entropy:
  -4
- Train/alpha_loss:
  0.0009958880685735493
- Train/batch_reward:
  0.919009788831075
- Train/critic_loss:
  52.50338191986084
- Train/duration:
  6.630008220672607
- Train/episode:
  1,333
- Train/success:
  0.5

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

wandb-history

run-gnz108vn-history:v0