Offline Reinforcement Learning with Value-based Episodic Memory

Abstract

Offline reinforcement learning (RL) shows promise of applying RL to real-world problems by effectively utilizing previously collected data. Most existing offline RL algorithms use regularization or constraints to suppress extrapolation error for actions outside the dataset. In this paper, we adopt a different framework, which learns the V-function instead of the Q-function to naturally keep the learning procedure within the support of an offline dataset. To enable effective generalization while maintaining proper conservatism in offline learning, we propose Expectile V-Learning (EVL), which smoothly interpolates between the optimal value learning and behavior cloning. Further, we introduce implicit planning along offline trajectories to enhance learned V-values and accelerate convergence. Together, we present a new offline method called Value-based Episodic Memory (VEM). We provide theoretical analysis for the convergence properties of our proposed VEM method, and empirical results in the D4RL benchmark show that our method achieves superior performance in most tasks, particularly in sparse-reward tasks.

References in corpus (9)

• Conservative Q-Learning for Offline Reinforcement Learning
• Advantage-Weighted Regression: Simple and Scalable Off-Policy Reinforcement Learning
• Distributional Reinforcement Learning with Quantile Regression
• Neural Episodic Control
• A Theory of Regularized Markov Decision Processes
• Statistics and Samples in Distributional Reinforcement Learning
• Uncertainty Weighted Actor-Critic for Offline Reinforcement Learning
• Believe What You See: Implicit Constraint Approach for Offline Multi-Agent Reinforcement Learning
• Instabilities of Offline RL with Pre-Trained Neural Representation