Provably Efficient Off-policy Adversarial Imitation Learning With Convergence Guarantees

Abstract

Adversarial Imitation Learning (AIL) faces challenges with sample inefficiency because of its reliance on sufficient on-policy data to evaluate the performance of the current policy during reward function updates. In this work, we study the convergence properties and sample complexity of off-policy AIL algorithms. We show that, even in the absence of importance sampling correction, reusing samples generated by the \(o(\sqrt\{K\})\) most recent policies, where \(K\) is the number of iterations of policy updates and reward updates, does not undermine the convergence guarantees of this class of algorithms. Furthermore, our results indicate that the distribution shift error induced by off-policy updates is dominated by the benefits of having more data available. This result provides theoretical support for the sample efficiency of off-policy AIL algorithms. To the best of our knowledge, this is the first work that provides theoretical guarantees for off-policy AIL algorithms.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keychen2024provably

Related papers

• Provably Efficient Adversarial Imitation Learning With Unknown Transitions (2023)0.00
• On Discovering Algorithms For Adversarial Imitation Learning (2025)0.00
• Discriminator-actor-critic: Addressing Sample Inefficiency And Reward Bias In Adversarial Imitation Learning (2018)0.00
• Lipschitzness Is All You Need To Tame Off-policy Generative Adversarial Imitation Learning (2020)7.81
• Non-adversarial Imitation Learning And Its Connections To Adversarial Methods (2020)0.00
• Provably Efficient Generative Adversarial Imitation Learning For Online And Offline Setting With Linear Function Approximation (2021)0.00
• Rethinking Adversarial Inverse Reinforcement Learning: Policy Imitation, Transferable Reward Recovery And Algebraic Equilibrium Proof (2024)0.00
• Deterministic And Discriminative Imitation (d2-imitation): Revisiting Adversarial Imitation For Sample Efficiency (2021)0.00