CaralHsi / offline-RL-TR-BCQ Public

Notifications You must be signed in to change notification settings
Fork 1
Star 6

The benchmark platform for offline reinforcement reproduction and evaluation

6 stars 1 fork Branches Tags Activity

Notifications

Name		Name	Last commit message	Last commit date
Latest commit History 2 Commits
batch_rl		batch_rl
dopamine		dopamine
plot_utils		plot_utils
replay_memory		replay_memory
README.md		README.md
generator.py		generator.py
offline_train.py		offline_train.py
requirements.txt		requirements.txt

Repository files navigation

TR-BCQ

This is the code for paper: Interpretable performance analysis towards offline reinforcement learning: A dataset perspective

Algorithms included: BCQ, REM, Quantile, DQN, MultiHeadDQN, BAIL, TR-BCQ

About

The benchmark platform for offline reinforcement reproduction and evaluation

Report repository

Releases

No releases published

Packages

No packages published

Languages