mlsanityData to 7 Oct 2026

Provable Benefits of Regularization: Fast Rates for Adversarial Imitation Learning

arXiv 2609.35698 ↗First posted 28 Sep 2026cs.LGcited by 0

On the map: Offline RL and imitation learning from data → Imitation learning methods

Abstract (arXiv)

We study adversarial imitation learning (AIL), in which an agent learns to imitate expert demonstrations by optimizing a policy against an adversarial reward that distinguishes expert and learner behavior. Historically, reward regularization and entropy-based policy regularization are key components of empirically successful methods such as GAIL and LS-IQ, yet their finite-sample benefits remain underexplored. We establish fast rates for jointly regularized AIL in finite-horizon Markov decision processes with general function approximation. Our model-free algorithm, Dually Regularized AIL, combines KL policy regularization with a quadratic reward penalty weighted by expert and learner occupancies. With K online episodes and N expert trajectories, we prove a widetildeOleft(frac1K+frac1Nright) bound on the regularized imitation gap for fixed regularization parameters. Our analysis combines an online mirror descent construction for general convex reward classes to control estimation error from finite expert data and stochastic learner feedback, with a sharp analysis of optimistic KL-regularized policy learning. To the best of our knowledge, Dually Regularized AIL is the first algorithm to simultaneously achieve widetildeOleft(frac1εright) sample complexity in both expert demonstrations and online interactions for this regularized AIL objective, even with stochastic experts. These results provide a rigorous characterization of the complementary statistical benefits of reward and policy regularization in AIL.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Imitation learning methods, one of 13 directions in Offline RL and imitation learning from data. Builds on 20 of its 28 references that are in the map. First posted on arXiv 28 Sep 2026.

Builds on

20 of 28 references.

Closest ancestors · 10

Same direction, newest first

  1. 2025Near-Optimal Second-Order Guarantees for Model-Based Adversarial Imitation Learning10 Oct
  2. 2024Provably and Practically Efficient Adversarial Imitation Learning with General Function Approximation1 Nov
  3. 2024Is Behavior Cloning All You Need? Understanding Horizon in Imitation Learning20 Jul
  4. 2024Imitation Learning in Discounted Linear MDPs without exploration assumptions3 May
  5. 2023Provably Efficient Adversarial Imitation Learning with Unknown Transitions11 Jun
  6. 2021Provably Efficient Generative Adversarial Imitation Learning for Online and Offline Setting with Linear Function Approximation19 Aug
  7. 2021IQ-Learn: Inverse soft-Q Learning for Imitation23 Jun
  8. 2021What Matters for Adversarial Imitation Learning?1 Jun
  9. 2020Toward the Fundamental Limits of Imitation Learning13 Sep
  10. 2019Provably Efficient Imitation Learning from Observation Alone27 May

Other references · 10

  1. 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,635
  2. 2016Generative Adversarial Imitation Learningcited by 1,576
  3. 2019Introduction to Online Convex Optimizationcited by 793
  4. 2023Fast Rates for Maximum Entropy Explorationcited by 32
  5. 2021Online Apprenticeship Learningcited by 28
  6. 2023LS-IQ: Implicit Reward Regularization for Inverse Reinforcement Learningcited by 28
  7. 2023A Nearly Optimal and Low-Switching Algorithm for Reinforcement Learning with General Function Approximationcited by 14
  8. 2025Achieving Logarithmic Regret in KL-Regularized Zero-Sum Markov Gamescited by 11
  9. 2023Demonstration-Regularized RLcited by 8
  10. 2026Fast Rates for Inverse Reinforcement Learningcited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Adversarial Imitation Learning with General Function Approximation: Theoretical Analysis and Practical Algorithms
  2. 2026Provably Efficient Policy-Reward Co-Pretraining for Adversarial Imitation Learning
  3. 2023Regularizing Adversarial Imitation Learning Using Causal Invariance
  4. 2020Explaining Fast Improvement in Online Imitation Learning
  5. 2021On Generalization of Adversarial Imitation Learning and Beyond
  6. 2022Improved Policy Optimization for Online Imitation Learning
  7. 2020On Computation and Generalization of Generative Adversarial Imitation Learning
  8. 2022Model-Based Imitation Learning Using Entropy Regularization of Model and Policy