tangger/lerobot
1
0
Fork 1
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

Added support for checkpointing the policy. We can save and load the policy state dict, optimizers state, optimization step and interaction step

Browse Source 
Added functions for converting the replay buffer from and to LeRobotDataset. When we want to save the replay buffer, we convert it first to LeRobotDataset format and save it locally and vice-versa.

Co-authored-by: Adil Zouitine <adilzouitinegm@gmail.com>
This commit is contained in:
Michel Aractingi
2025-01-30 17:39:41 +00:00
committed by AdilZouitine
parent 9afd093030
commit 2023289ce8
5 changed files with 215 additions and 91 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
lerobot/configs/policy/sac_maniskill.yaml
View File

@@ -8,7 +8,7 @@
# env.gym.obs_type=environment_state_agent_pos \
seed: 1
dataset_repo_id: null
dataset_repo_id: aractingi/hil-serl-maniskill-pushcube
training:
# Offline training dataloader
@@ -21,7 +21,7 @@ training:
eval_freq: 2500
log_freq: 500
save_freq: 50000
save_freq: 1000000
online_steps: 1000000
online_rollout_n_episodes: 10