Accelerating Residual Reinforcement Learning with Uncertainty Estimation

TL;DR

This paper introduces uncertainty-aware residual reinforcement learning techniques that improve sample efficiency and handle stochastic base policies, demonstrated through simulation benchmarks and real-world deployment.

Contribution

It proposes two novel methods leveraging uncertainty estimates and a modification for stochastic policies, enhancing residual RL's effectiveness and applicability.

Findings

Significantly outperforms existing residual RL baselines.

Effective in both simulation and real-world tasks.

Handles stochastic base policies better than prior methods.

Abstract

Residual Reinforcement Learning (RL) is a popular approach for adapting pretrained policies by learning a lightweight residual policy that provides corrective actions. While Residual RL is more sample-efficient than finetuning the entire base policy, existing methods struggle with sparse rewards and are designed for deterministic base policies. We propose two improvements to Residual RL that further enhance its sample efficiency and make it suitable for stochastic base policies. First, we leverage uncertainty estimates of the base policy to focus exploration on regions in which the base policy is not confident. Second, we propose a simple modification to off-policy residual learning that allows it to observe base actions and better handle stochastic base policies. We evaluate our method with both Gaussian-based and Diffusion-based stochastic base policies on tasks from Robosuite and D4RL, and compare against state-of-the-art finetuning methods, demo-augmented RL methods, and other residual RL methods. Our algorithm significantly outperforms existing baselines in a variety of simulation benchmark environments. We also deploy our learned polices in the real world to demonstrate their robustness with zero-shot sim-to-real transfer. Paper homepage : lakshitadodeja.github.io/uncertainty-aware-residual-rl/