AlignIQL: Policy Alignment in Implicit Q-Learning through Constrained Optimization

TL;DR

AlignIQL introduces a novel optimization-based approach to explicitly recover policies in implicit Q-learning, enhancing offline RL performance especially in complex tasks by decoupling actor and critic.

Contribution

The paper proposes AlignIQL and AlignIQL-hard algorithms that explicitly solve the implicit policy-finding problem, improving policy extraction and performance over existing methods.

Findings

Achieves competitive or superior results on D4RL datasets.

Outperforms IQL and IDQL in complex sparse reward tasks.

Maintains simplicity of IQL while solving the implicit policy problem.

Abstract

Implicit Q-learning (IQL) serves as a strong baseline for offline RL, which learns the value function using only dataset actions through quantile regression. However, it is unclear how to recover the implicit policy from the learned implicit Q-function and why IQL can utilize weighted regression for policy extraction. IDQL reinterprets IQL as an actor-critic method and gets weights of implicit policy, however, this weight only holds for the optimal value function. In this work, we introduce a different way to solve the implicit policy-finding problem (IPF) by formulating this problem as an optimization problem. Based on this optimization problem, we further propose two practical algorithms AlignIQL and AlignIQL-hard, which inherit the advantages of decoupling actor from critic in IQL and provide insights into why IQL can use weighted regression for policy extraction. Compared with IQL and IDQL, we find our method keeps the simplicity of IQL and solves the implicit policy-finding problem. Experimental results on D4RL datasets show that our method achieves competitive or superior results compared with other SOTA offline RL methods. Especially in complex sparse reward tasks like Antmaze and Adroit, our method outperforms IQL and IDQL by a significant margin.