Provably Efficient Adversarial Imitation Learning With Unknown Transitions

Abstract

Imitation learning (IL) has proven to be an effective method for learning good policies from expert demonstrations. Adversarial imitation learning (AIL), a subset of IL methods, is particularly promising, but its theoretical foundation in the presence of unknown transitions has yet to be fully developed. This paper explores the theoretical underpinnings of AIL in this context, where the stochastic and uncertain nature of environment transitions presents a challenge. We examine the expert sample complexity and interaction complexity required to recover good policies. To this end, we establish a framework connecting reward-free exploration and AIL, and propose an algorithm, MB-TAIL, that achieves the minimax optimal expert sample complexity of \(\widetilde\{O\} (H^\{3/2\} |S|/\epsilon)\) and interaction complexity of \(\widetilde\{O\} (H^\{3\} |S|^2 |A|/\epsilon^2)\). Here, \(H\) represents the planning horizon, \(|S|\) is the state space size, \(|A|\) is the action space size, and \(\ep

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyxu2023provably

Related papers

• Provably Efficient Off-policy Adversarial Imitation Learning With Convergence Guarantees (2024)0.00
• State-only Imitation With Transition Dynamics Mismatch (2020)0.00
• On Discovering Algorithms For Adversarial Imitation Learning (2025)0.00
• Toward The Fundamental Limits Of Imitation Learning (2020)0.00
• Provably Efficient Imitation Learning From Observation Alone (2019)0.00
• Diffail: Diffusion Adversarial Imitation Learning (2023)9.13
• A New Framework For Query Efficient Active Imitation Learning (2019)0.00
• Provably Efficient Generative Adversarial Imitation Learning For Online And Offline Setting With Linear Function Approximation (2021)0.00