mlsanityData to 14 Oct 2026

Inverse Reinforcement Learning with Simultaneous Estimation of Rewards and Dynamics

arXiv 1604.03912 ↗First posted 13 Apr 2016cs.AI cs.LG cs.SYcited by 24

Not on the map. Why?

Abstract (arXiv)

Inverse Reinforcement Learning (IRL) describes the problem of learning an unknown reward function of a Markov Decision Process (MDP) from observed behavior of an agent. Since the agent's behavior originates in its policy and MDP policies depend on both the stochastic system dynamics as well as the reward function, the solution of the inverse problem is significantly influenced by both. Current IRL approaches assume that if the transition model is unknown, additional samples from the system's dynamics are accessible, or the observed behavior provides enough samples of the system's dynamics to solve the inverse problem accurately. These assumptions are often not satisfied. To overcome this, we present a gradient-based IRL approach that simultaneously estimates the system's dynamics. By solving the combined optimization problem, our approach takes into account the bias of the demonstrations, which stems from the generating policy. The evaluation on a synthetic MDP and a transfer learning task shows improvements regarding the sample efficiency as well as the accuracy of the estimated reward functions and transition models.

Key facts. Cited by 24 papers in the map (data through 14 Oct 2026). First posted on arXiv 13 Apr 2016.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2020: 3; 2021: 2; 2022: 2; 2023: 8; 2024: 4; 2025: 5.

24 papers.

Sort:

By area:

  1. 2021IQ-Learn: Inverse soft-Q Learning for Imitationcited by 193
  2. 2021Scalable Bayesian Inverse Reinforcement Learningcited by 56
  3. 2020Strictly Batch Imitation Learning by Energy-based Distribution Matchingcited by 54
  4. 2020Robust Inverse Reinforcement Learning under Transition Dynamics Mismatchcited by 33
  5. 2023When Demonstrations Meet Generative World Models: A Maximum Likelihood Framework for Offline Inverse Reinforcement Learningcited by 26
  6. 2023CLARE: Conservative Model-Based Reward Learning for Offline Inverse Reinforcement Learningcited by 20
  7. 2024How to Leverage Diverse Demonstrations in Offline Imitation Learningcited by 12
  8. 2023Inverse Decision Modeling: Learning Interpretable Representations of Behaviorcited by 10
  9. 2023A Bayesian Approach to Robust Inverse Reinforcement Learningcited by 9
  10. 2025Performative Policy Gradient: Optimality in Performative Reinforcement Learningcited by 6
  11. 2023Explaining by Imitating: Understanding Decisions by Interpretable Policy Learningcited by 3
  12. 2024Enhancing Inverse Reinforcement Learning through Encoding Dynamic Information in Reward Shapingcited by 3
12 more
  1. 2020Necessary and Sufficient Conditions for Inverse Reinforcement Learning of Bayesian Stopping Time Problemscited by 2
  2. 2022Modeling Mobile Health Users as Reinforcement Learning Agentscited by 2
  3. 2022Model-Based Imitation Learning Using Entropy Regularization of Model and Policycited by 1
  4. 2023AI Alignment Dialogues: An Interactive Approach to AI Alignment in Support Agentscited by 1
  5. 2024OMG-RL:Offline Model-based Guided Reward Learning for Heparin Treatmentcited by 1
  6. 2025Inversely Learning Transferable Rewards via Abstracted Statescited by 1
  7. 2025Model-Based Reinforcement Learning Under Confoundingcited by 1
  8. 2023FP-IRL: Fokker--Planck Inverse Reinforcement Learning -- A Physics-Constrained Approach to Markov Decision Processescited by 0
  9. 2023Bayesian Inverse Transition Learning for Offline Settingscited by 0
  10. 2024Bayesian Inverse Transition Learning: Learning Dynamics From Near-Optimal Trajectoriescited by 0
  11. 2025DO-IQS: Dynamics-Aware Offline Inverse Q-Learning for Optimal Stopping with Unknown Gain Functionscited by 0
  12. 2025Safe Explicable Policy Searchcited by 0