Continuous Doubly Constrained Batch Reinforcement Learning

Rasool Fakoor, Jonas Mueller, Kavosh Asadi, Pratik Chaudhari, Alex Smola

Keywords: batch reinforcement learning, overestimation bias, extrapolation, offline reinforcement learning, batch rl, offline rl

Abstract: Reliant on too many experiments to learn good actions, current Reinforcement Learning (RL) algorithms have limited applicability in real-world settings, which can be too expensive to allow exploration. We propose an algorithm for batch RL, where effective policies are learned using only a fixed offline dataset instead of online interactions with the environment. The limited data in batch RL produces inherent uncertainty in value estimates of states/actions that were insufficiently represented in the training data. This leads to particularly severe extrapolation when our candidate policies diverge from one that generated the data. We propose to mitigate this issue via two straightforward penalties: a policy-constraint to reduce this divergence and a value-constraint that discourages overly optimistic estimates. Over a comprehensive set of $32$ continuous-action batch RL benchmarks, our approach compares favorably to state-of-the-art methods, regardless of how the offline data were collected.

Code Of Conduct: I certify that all co-authors of this work have read and commit to adhering to the NeurIPS Statement on Ethics, Fairness, Inclusivity, and Code of Conduct.

TL;DR: CDC is an effective batch RL algorithm that addresses overestimation bias and extrapolation errors by a simple pair of regularizers.

Community Implementations: [ 2 code implementations](https://www.catalyzex.com/paper/arxiv:2102.09225/code)