LGMLMar 21, 2024

Rethinking Adversarial Inverse Reinforcement Learning: Policy Imitation, Transferable Reward Recovery and Algebraic Equilibrium Proof

arXiv:2403.14593v4h-index: 3
Originality Incremental advance
AI Analysis

This work incrementally improves AIRL for imitation learning, addressing specific bottlenecks in policy imitation and reward recovery.

The paper addresses three criticisms of Adversarial Inverse Reinforcement Learning (AIRL): inadequate policy imitation, limited transferable reward recovery, and unsatisfactory equilibrium proof. It shows that using soft actor-critic (SAC) improves policy imitation efficiency, proposes a hybrid PPO-AIRL + SAC framework for better reward transfer, and provides an algebraic theory-based proof.

Adversarial inverse reinforcement learning (AIRL) stands as a cornerstone approach in imitation learning, yet it faces criticisms from prior studies. In this paper, we rethink AIRL and respond to these criticisms. Criticism 1 lies in Inadequate Policy Imitation. We show that substituting the built-in algorithm with soft actor-critic (SAC) during policy updating (requires multi-iterations) significantly enhances the efficiency of policy imitation. Criticism 2 lies in Limited Performance in Transferable Reward Recovery Despite SAC Integration. While we find that SAC indeed exhibits a significant improvement in policy imitation, it introduces drawbacks to transferable reward recovery. We prove that the SAC algorithm itself is not feasible to disentangle the reward function comprehensively during the AIRL training process, and propose a hybrid framework, PPO-AIRL + SAC, for a satisfactory transfer effect. Criticism 3 lies in Unsatisfactory Proof from the Perspective of Potential Equilibrium. We reanalyze it from an algebraic theory perspective.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes