Adversarial Imitation Learning

Follow this topic Ask about this topic

Adversarial imitation learning uses a discriminator or learned reward to compare an agent’s behavior with expert demonstrations, often avoiding the need to hand-design a reward function. Common approaches match state-action or occupancy distributions, including generative adversarial imitation learning and Wasserstein methods, with extensions for learning from observations, reusing off-policy data, and combining policy and reward training. Methods are studied in control benchmarks such as MuJoCo, robot navigation and manipulation, multi-agent swarms, and increasingly generative language and image tasks. A central challenge is making learning both sample-efficient and reliable when demonstrations are scarce, dynamics or embodiments differ, or safety and generalization matter; theoretical guarantees are improving, but these settings remain difficult.

Latest papers

17 papers2 papers in the last four weeks, against 1 the four weeks before. 0.0% of all new papers.

Uncovering the Turing Test's Latent Signal: Indistinguishability as a Reward
Oct 26, 2026Emanuele Rimoldi, Riccardo Neumarker, Tomaso Poggio +1Adversarial Imitation Learning RL for Language Models
MIT · EPFL · ETH Zurich +1
Experience-Based Feasibility-Aware Generative Adversarial Imitation from Observation under Embodiment Mismatch
Oct 1, 2026Yoshiki Takebayashi, Giovanni Perantoni, Hikaru Sasaki +2Cross-Embodiment Robot Learning Adversarial Imitation Learning
Division of Information Science, Graduate School of Information Science, Nara Institute of Science and Technology (NAIST), Nara, Japan · Department of Industrial Engineering of the University of Trento, Trento, Italy
Provable Benefits of Regularization: Fast Rates for Adversarial Imitation Learning
Sep 28, 2026Hanbin Zhou, Shangzhe Li, Alexander Braverman +1Reinforcement Learning Adversarial Imitation Learning
HKUST(GZ) · UNC Chapel Hill · Cornell University
GLARE: Generative Learning via Adversarial Reward Estimation For Social Dynamics Forecasting
Sep 10, 2026Tenghao Huang, Zhaoxuan Tan, Muhao Chen +5RL for Language Models Adversarial Imitation Learning
Microsoft · University of Notre Dame · University of California, Davis +1
Learning Stock Trading Policies via Barycenter-Based Adversarial Inverse Reinforcement Learning
Aug 16, 2026Arishi Orra, Himanshu Choudhary, Manoj ThakurReinforcement Learning Finance
School of Mathematical and Statistical Sciences Indian Institue of Technology Mandi Mandi, Himachal Pradesh, India, 175005
Discriminative Barrier Functions for Safe Adversarial Imitation Learning from Observation
Jul 15, 2026Anubhav Vishwakarma, Bhaumik Mehta, Caleb Hsu +3Reinforcement Learning Control Barrier Functions
University of Washington
Right in the Right Way: LM Training with Verifiable Rewards and Human Demonstrations
Jul 1, 2026Mehul Damani, Isha Puri, Idan Shenfeld +1Reward Hacking RL for Language Models
MIT EECS
Provably Efficient Policy-Reward Co-Pretraining for Adversarial Imitation Learning
Jun 20, 2026Tian Xu, Zexuan Chen, Zhilong Zhang +4Adversarial Imitation Learning Imitation Learning
National Key Laboratory for Novel Software Technology and School of Artificial Intelligence, Nanjing University, China.
Adversarial Dual On-Policy Distillation from Expressive Teacher
May 26, 2026Zhenglin Wan, Jingxuan Wu, Xingrui Yu +5Robot Policy Learning Adversarial Imitation Learning
School of Computing, National University of Singapore · Department of Statistics and Operations Research, UNC-Chapel Hill, America · CFAR, Agency for Science, Technology and Research, Singapore +4
Population-Aware Imitation Learning in Mean-field Games with Common Noise
May 5, 2026Grégoire Lambrecht, Mathieu LaurièreMean Field Games Adversarial Imitation Learning
Center for Data Science, New York University and NYU Shanghai, New York, United States of America · Shanghai Center for Data Science; NYU-ECNU Institute of Mathematical Sciences at NYU Shanghai; NYU Shanghai, Shanghai, People’s Republic of China.
Adversarial Imitation Learning with General Function Approximation: Theoretical Analysis and Practical Algorithms
May 3, 2026Tian Xu, Zhilong Zhang, Zexuan Chen +3Reinforcement Learning Adversarial Imitation Learning
National Key Laboratory for Novel Software Technology and School of Artificial Intelligence, Nanjing University · School of Mathematics, Nanjing University
Zero-Shot Scalable Resilience in UAV Swarms: A Decentralized Imitation Learning Framework with Physics-Informed Graph Interactions
Apr 17, 2026Huan Lin, Lianghui DingMulti-Robot Systems Swarm Robotics
Institute of Image Communication and Network Engineering, School of Integrated Circuits, Shanghai Jiao Tong University, Shanghai 200240, China
Latent Wasserstein Adversarial Imitation Learning
Mar 5, 2026Siqi Yang, Kai Yan, Alexander G. Schwing +1Imitation Learning Adversarial Imitation Learning
University of Illinois Urbana-Champaign
Generative adversarial imitation learning for robot swarms: Learning from human demonstrations and trained policies
Mar 3, 2026Mattes Kraus, Jonas KucklingRobot Imitation Learning Learning from Demonstration
University of Konstanz, Department of Computer and Information Science, Konstanz, Germany · Cluster of Excellence “Centre for the Advanced Study of Collective Behavior”, University of Konstanz · Zukunftskolleg, University of Konstanz
FAIL: Flow Matching Adversarial Imitation Learning for Image Generation
Feb 12, 2026Yeyao Ma, Chen Li, Xiaosong Zhang +2Flow Matching Conditional Image Generation
Shanghai Jiao Tong University · Xi’an Jiaotong University · Tencent
How Vulnerable Is My Learned Policy? Universal Adversarial Perturbation Attacks On Modern Behavior Cloning Policies
Feb 6, 2025Akansha Kalra, Basavasagar Patil, Guanhong Tao +1Adversarial Robustness Adversarial Imitation Learning
University of Utah
Provably Efficient Off-Policy Adversarial Imitation Learning with Convergence Guarantees
May 26, 2024Yilei Chen, Vittorio Giammarino, James Queeney +1Adversarial Imitation Learning Imitation Learning
Division of Systems Engineering Boston University Boston, MA 02215, USA · Department of Computer Science Purdue University West Lafayette, IN 47907, USA · Amazon Robotics North Reading, MA 01864, USA +1

Oct 26, 2026J/K move · Enter open · S save

Uncovering the Turing Test's Latent Signal: Indistinguishability as a Reward

Emanuele Rimoldi, Riccardo Neumarker, Tomaso Poggio, Daniel Mitropolsky

MIT · EPFL · ETH Zurich+1

Adversarial Imitation Learning RL for Language Models RL for Language Model Reasoning

Open paper AskPDF arXiv

Can a model learn by trying to fool another model? We show that it can. Inspired by the Turing Test and its recent generalization to arbitrary distinguishers, we introduce a domain-based teacher-Turing-Test, in which a stronger teacher model serves as both the target of imitation and the distinguisher, and a weaker student model is trained to make the teacher attribute responses to itself. We use this self-attribution (or fooling) probability as a reinforcement learning reward, without ever providing the student ground-truth answers, nor requiring the teacher to generate responses. We test our approach independently in four domains with verifiable answers: CommonsenseQA (reasoning), GSM8K (mathematics), KodCode (programming), and Spider (SQL), training a Qwen2.5-1.5B student/imitator model using DeepSeek V4 Flash as teacher/distinguisher. Beyond improving at passing the Turing Test, the student improves on independent, held-out evaluations in all domains and runs. To probe why being mistaken for the teacher can improve capability, our analyses reveal that self-attribution is associated with correctness -- substantially more than formatting changes -- and that it rewards partial correctness. Our results demonstrate a new, simple teacher-student training paradigm with a private and/or high-cost teacher. They also suggest that indistinguishability need not merely measure behavior -- it can also be a mechanism for learning.