Hybrid-AIRL: Enhancing Inverse Reinforcement Learning with Supervised Expert Guidance

TL;DR

Hybrid-AIRL improves inverse reinforcement learning by integrating supervised expert guidance, leading to better reward inference and more stable, sample-efficient learning in complex, uncertain environments like poker.

Contribution

The paper introduces Hybrid-AIRL, a novel extension of AIRL that incorporates supervised expert data and stochastic regularization to enhance reward inference.

Findings

H-AIRL outperforms AIRL in sample efficiency and stability.

Incorporating supervised signals improves reward inference.

H-AIRL demonstrates effectiveness in complex environments like HULHE poker.

Abstract

Adversarial Inverse Reinforcement Learning (AIRL) has shown promise in addressing the sparse reward problem in reinforcement learning (RL) by inferring dense reward functions from expert demonstrations. However, its performance in highly complex, imperfect-information settings remains largely unexplored. To explore this gap, we evaluate AIRL in the context of Heads-Up Limit Hold'em (HULHE) poker, a domain characterized by sparse, delayed rewards and significant uncertainty. In this setting, we find that AIRL struggles to infer a sufficiently informative reward function. To overcome this limitation, we contribute Hybrid-AIRL (H-AIRL), an extension that enhances reward inference and policy learning by incorporating a supervised loss derived from expert data and a stochastic regularization mechanism. We evaluate H-AIRL on a carefully selected set of Gymnasium benchmarks and the HULHE poker setting. Additionally, we analyze the learned reward function through visualization to gain deeper insights into the learning process. Our experimental results show that H-AIRL achieves higher sample efficiency and more stable learning compared to AIRL. This highlights the benefits of incorporating supervised signals into inverse RL and establishes H-AIRL as a promising framework for tackling challenging, real-world settings.