Data to 14 Oct 2026

Learning Robust Rewards with Adversarial Inverse Reinforcement Learning

arXiv 1710.11248 ↗First posted 30 Oct 2017cs.LGcited by 490

Not on the map. Why?

Cited by 319 in Offline RL and imitation learning from data, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Reinforcement learning provides a powerful and general framework for decision making and control, but its application in practice is often hindered by the need for extensive feature and reward engineering. Deep reinforcement learning methods can remove the need for explicit engineering of policy or value features, but still require a manually specified reward function. Inverse reinforcement learning holds the promise of automatic reward acquisition, but has proven exceptionally difficult to apply to large, high-dimensional problems with unknown dynamics. In this work, we propose adverserial inverse reinforcement learning (AIRL), a practical and scalable inverse reinforcement learning algorithm based on an adversarial reward learning formulation. We demonstrate that AIRL is able to recover reward functions that are robust to changes in dynamics, enabling us to learn policies even under significant variation in the environment seen during training. Our experiments show that AIRL greatly outperforms prior methods in these transfer settings.

Key facts. Cited by 490 papers in the map (data through 14 Oct 2026). First posted on arXiv 30 Oct 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2018: 9; 2019: 33; 2020: 39; 2021: 82; 2022: 76; 2023: 76; 2024: 73; 2025: 62; 2026: 40.

490 papers.

Sort:

By area:

2023VoxPoser: Composable 3D Value Maps for Robotic Manipulation with Language Modelscited by 750
2018A Survey of Inverse Reinforcement Learning: Challenges, Methods and Progresscited by 298
2019Extrapolating Beyond Suboptimal Demonstrations via Inverse Reinforcement Learning from Observationscited by 260
2022Contrastive Learning as Goal-Conditioned Reinforcement Learningcited by 253
2021DexMV: Imitation Learning for Dexterous Manipulation from Human Videoscited by 206
2018Discriminator-Actor-Critic: Addressing Sample Inefficiency and Reward Bias in Adversarial Imitation Learningcited by 204
2022Defining and Characterizing Reward Hackingcited by 203
2021IQ-Learn: Inverse soft-Q Learning for Imitationcited by 193
2019A Divergence Minimization Perspective on Imitation Learning Methodscited by 190
2019Imitation Learning via Off-Policy Distribution Matchingcited by 183
2019Goal-conditioned Imitation Learningcited by 162
2023A Survey of Imitation Learning: Algorithms, Recent Developments, and Challengescited by 148

38 more

2023Vision-Language Models as Success Detectorscited by 142
2023RoboCLIP: One Demonstration is Enough to Learn Robot Policiescited by 134
2019Imitation Learning as f-Divergence Minimizationcited by 123
2020Primal Wasserstein Imitation Learningcited by 121
2019Imitation Learning from Imperfect Demonstrationcited by 114
2023Policy Representation via Diffusion Probability Model for Reinforcement Learningcited by 112
2023UniDexGrasp++: Improving Dexterous Grasping Policy Learning via Geometry-aware Curriculum and Iterative Generalist-Specialist Learningcited by 107
2018Variational Discriminator Bottleneck: Improving Imitation Learning, Inverse RL, and GANs by Constraining Information Flowcited by 105
2021Reward (Mis)design for Autonomous Drivingcited by 104
2019Recent Advances in Imitation Learning from Observationcited by 93
2023PIRLNav: Pretraining with Imitation and RL Finetuning for ObjectNavcited by 93
2020State-Only Imitation Learning for Dexterous Manipulationcited by 91
2022From One Hand to Multiple Hands: Imitation Learning for Dexterous Manipulation from Single-Camera Teleoperationcited by 82
2021Of Moments and Matching: A Game-Theoretic Framework for Closing the Imitation Gapcited by 81
2021Demonstration-Guided Reinforcement Learning with Learned Skillscited by 76
2023Teach a Robot to FISH: Versatile Imitation from One Minute of Demonstrationscited by 75
2019State Alignment-based Imitation Learningcited by 73
2020Safe Imitation Learning via Fast Bayesian Reward Inference from Preferencescited by 73
2020Offline Learning from Demonstrations and Unlabeled Experiencecited by 72
2021Off-Policy Imitation Learning from Observationscited by 70
2021What Matters for Adversarial Imitation Learning?cited by 70
2019From Language to Goals: Inverse Reinforcement Learning for Vision-Based Instruction Followingcited by 67
2020f-IRL: Inverse Reinforcement Learning via State Marginal Matchingcited by 67
2022Watch and Match: Supercharging Imitation with Regularized Optimal Transportcited by 67
2022How to Leverage Unlabeled Data in Offline Reinforcement Learningcited by 62
2021A Survey of Deep RL and IL for Autonomous Driving Policy Learningcited by 61
2019Wasserstein Adversarial Imitation Learningcited by 60
2019Multi-Agent Adversarial Inverse Reinforcement Learningcited by 60
2026Robometer: Scaling General-Purpose Robotic Reward Models via Trajectory Comparisonscited by 60
2021Identifiability in inverse reinforcement learningcited by 55
2020Strictly Batch Imitation Learning by Energy-based Distribution Matchingcited by 54
2023Robot Fine-Tuning Made Easy: Pre-Training Rewards and Policies for Autonomous Real-World Reinforcement Learningcited by 54
2020Predicting Goal-directed Human Attention Using Inverse Reinforcement Learningcited by 53
2021Offline Meta-Reinforcement Learning with Online Self-Supervisioncited by 53
2021LazyDAgger: Reducing Context Switching in Interactive Imitation Learningcited by 51
2022Learning Generalizable Dexterous Manipulation from Human Grasp Affordancecited by 51
2023Zero-Shot Robot Manipulation from Passive Human Videoscited by 51
2019Meta-Inverse Reinforcement Learning with Probabilistic Context Variablescited by 50

50 most cited of 490 All 490 (JSON)