LGFeb 4, 2024

The Virtues of Pessimism in Inverse Reinforcement Learning

arXiv:2402.02616v2h-index: 64
AI Analysis

This work addresses a computational bottleneck for researchers and practitioners in IRL, offering an incremental improvement in sample efficiency.

The paper tackles the computational inefficiency in Inverse Reinforcement Learning (IRL) by proposing a pessimism approach that uses offline RL algorithms to reduce the exploration burden, resulting in policies that match expert performance more efficiently than prior methods.

Inverse Reinforcement Learning (IRL) is a powerful framework for learning complex behaviors from expert demonstrations. However, it traditionally requires repeatedly solving a computationally expensive reinforcement learning (RL) problem in its inner loop. It is desirable to reduce the exploration burden by leveraging expert demonstrations in the inner-loop RL. As an example, recent work resets the learner to expert states in order to inform the learner of high-reward expert states. However, such an approach is infeasible in the real world. In this work, we consider an alternative approach to speeding up the RL subroutine in IRL: \emph{pessimism}, i.e., staying close to the expert's data distribution, instantiated via the use of offline RL algorithms. We formalize a connection between offline RL and IRL, enabling us to use an arbitrary offline RL algorithm to improve the sample efficiency of IRL. We validate our theory experimentally by demonstrating a strong correlation between the efficacy of an offline RL algorithm and how well it works as part of an IRL procedure. By using a strong offline RL algorithm as part of an IRL procedure, we are able to find policies that match expert performance significantly more efficiently than the prior art.

Foundations

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

Your Notes