mlsanityData to 7 Oct 2026

Weighted Maximum Entropy Inverse Reinforcement Learning

arXiv 2208.09611 ↗First posted 20 Aug 2022cs.LGcited by 0

On the map: Offline RL and imitation learning from data → Inverse reinforcement learning

Abstract (arXiv)

We study inverse reinforcement learning (IRL) and imitation learning (IM), the problems of recovering a reward or policy function from expert's demonstrated trajectories. We propose a new way to improve the learning process by adding a weight function to the maximum entropy framework, with the motivation of having the ability to learn and recover the stochasticity (or the bounded rationality) of the expert policy. Our framework and algorithms allow to learn both a reward (or policy) function and the structure of the entropy terms added to the Markov Decision Processes, thus enhancing the learning procedure. Our numerical experiments using human and simulated demonstrations and with discrete and continuous IRL/IM tasks show that our approach outperforms prior algorithms.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Inverse reinforcement learning, one of 13 directions in Offline RL and imitation learning from data. Builds on 8 of its 23 references that are in the map. First posted on arXiv 20 Aug 2022.

Builds on

8 of 23 references.

Closest ancestors · 2

Same direction, newest first

  1. 2020Off-Policy Adversarial Inverse Reinforcement Learning3 May
  2. 2019Multi-Agent Adversarial Inverse Reinforcement Learning30 Jul

Other references · 6

  1. 2016Generative Adversarial Imitation Learningcited by 1,576
  2. 2017Learning Robust Rewards with Adversarial Inverse Reinforcement Learningcited by 485
  3. 2016Guided Cost Learning: Deep Inverse Optimal Control via Policy Optimizationcited by 400
  4. 2019A Theory of Regularized Markov Decision Processescited by 279
  5. 2016A Connection between Generative Adversarial Networks, Inverse Reinforcement Learning, and Energy-Based Modelscited by 167
  6. 2015Inverse Reinforcement Learning via Deep Gaussian Processcited by 6

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2020Revisiting Maximum Entropy Inverse Reinforcement Learning: New Perspectives and Algorithms
  2. 2019Generalized Maximum Causal Entropy for Inverse Reinforcement Learning
  3. 2025Statistical analysis of Inverse Entropy-regularized Reinforcement Learning
  4. 2024Convergence of a model-free entropy-regularized inverse reinforcement learning algorithm
  5. 2021Task-Guided Inverse Reinforcement Learning Under Partial Information
  6. 2018Multi-task Maximum Entropy Inverse Reinforcement Learning
  7. 2021Inverse Reinforcement Learning with Explicit Policy Estimates
  8. 2023BC-IRL: Learning Generalizable Reward Functions from Demonstrations