rail-berkeley / rlkit

Collection of reinforcement learning algorithms
MIT License
2.43k stars 547 forks source link

IQL reimplementation and examples. #150

Closed anair13 closed 2 years ago

anair13 commented 2 years ago

IQL (https://arxiv.org/abs/2110.06169) reimplementation and examples. Also changed batch_rl_algorithm to be offline RL for negative epochs.