Bayesian Offline-to-Online Reinforcement Learning

Requirements:

First, please install the corresponding dependencies:

For the offline training, please run:

python3 main.py --save_model --env hopper-medium-v2

For the online finetuning, please run:

python3 finetune.py --load_model --offdataset --env hopper-medium-v2

Name		Name	Last commit message	Last commit date
Latest commit History 4 Commits
README.md		README.md
TD3_BC.py		TD3_BC.py
TD3_BC_ensemble.py		TD3_BC_ensemble.py
finetune.py		finetune.py
main.py		main.py
utils.py		utils.py