Critic Regularized Regression
Authors:
Preprint
Abstract
Offline reinforcement learning (RL), also known as batch RL, offers the prospect of policy optimization from large pre-recorded datasets without online environment interaction. It addresses challenges with regard to the cost of data collection and safety, both of which are particularly pertinent to real-world applications of RL. Unfortunately, most off-policy algorithms perform poorly when learning from a fixed dataset. In this paper, we propose a novel offline RL algorithm to learn policies from data using a form of critic-regularized regression (CRR). We find that CRR performs surprisingly well and scales to tasks with high-dimensional state and action spaces -- outperforming several state-of-the-art offline RL algorithms by a significant margin on a wide range of benchmark tasks.Keywords
All Related Versions
This publication has 4 references indexed in Scilit:
- Challenges of real-world reinforcement learning: definitions, benchmarks and analysisMachine Learning, 2021
- Scaling data-driven robotics with reward sketching and batch reinforcement learning2020
- A general reinforcement learning algorithm that masters chess, shogi, and Go through self-playScience, 2018
- Overcoming Exploration in Reinforcement Learning with Demonstrations2018