Revisiting the Minimalist Approach to Offline Reinforcement Learning

Denis Tarasov, Vladislav Kurenkov, Alexander Nikulin, Sergey Kolesnikov

Keywords: Offline Reinforcement Learning

TL;DR: We modify TD3+BC with [layer norm, deeper critic, higher discount factor, decoupled penalization] and find it can outperform SOTA ensemble-free offline RL algorithms

Abstract: Recent years have witnessed significant advancements in offline reinforcement learning (RL), resulting in the development of numerous algorithms with varying degrees of complexity. While these algorithms have led to noteworthy improvements, many incorporate seemingly minor design choices that impact their effectiveness beyond core algorithmic advances. However, the effect of these design choices on established baselines remains understudied. In this work, we aim to bridge this gap by conducting a retrospective analysis of recent works in offline RL and propose ReBRAC, a minimalistic algorithm that integrates such design elements built on top of the TD3+BC method. We evaluate ReBRAC on 51 datasets with both proprioceptive and visual state spaces using D4RL and V-D4RL benchmarks, demonstrating its state-of-the-art performance among ensemble-free methods in both offline and offline-to-online settings. To further illustrate the efficacy of these design choices, we perform a large-scale ablation study and hyperparameter sensitivity analysis on the scale of thousands of experiments.

Submission Number: 3667