B-Pref: Benchmark for Preference-based RL

Please check out a new offifical codebase at https://github.com/rll-research/BPref

Name		Name	Last commit message	Last commit date
Latest commit History 22 Commits
agent		agent
config		config
custom_dmc2gym		custom_dmc2gym
custom_dmcontrol		custom_dmcontrol
rlkit/envs		rlkit/envs
scripts		scripts
stable_baselines3		stable_baselines3
.gitignore		.gitignore
README.md		README.md
conda_env.yml		conda_env.yml
logger.py		logger.py
replay_buffer.py		replay_buffer.py
reward_model.py		reward_model.py
setup.cfg		setup.cfg
setup.py		setup.py
train_PEBBLE.py		train_PEBBLE.py
train_PPO.py		train_PPO.py
train_PPO_Unsuper.py		train_PPO_Unsuper.py
train_PrefPPO.py		train_PrefPPO.py
train_SAC.py		train_SAC.py
utils.py		utils.py

wx-b/B_Pref