mlsanityData to 7 Oct 2026

Multi-task Maximum Entropy Inverse Reinforcement Learning

arXiv 1805.08882 ↗First posted 22 May 2018cs.LG cs.AI stat.MLcited by 20

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

Abstract (arXiv)

Multi-task Inverse Reinforcement Learning (IRL) is the problem of inferring multiple reward functions from expert demonstrations. Prior work, built on Bayesian IRL, is unable to scale to complex environments due to computational constraints. This paper contributes a formulation of multi-task IRL in the more computationally efficient Maximum Causal Entropy (MCE) IRL framework. Experiments show our approach can perform one-shot imitation learning in a gridworld environment that single-task IRL algorithms need hundreds of demonstrations to solve. We outline preliminary work using meta-learning to extend our method to the function approximator setting of modern MCE IRL algorithms. Evaluating on multi-task variants of common simulated robotics benchmarks, we discover serious limitations of these IRL algorithms, and conclude with suggestions for further work.

Key facts. Cited by 20 papers in the map (data through 7 Oct 2026). Placed in Inverse reinforcement learning, one of 13 directions in Offline RL and imitation learning from data. Builds on 10 of its 25 references that are in the map. First posted on arXiv 22 May 2018.

Builds on

10 of 25 references.

References · 10

  1. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  2. 2016Generative Adversarial Imitation Learningcited by 1,576
  3. 2018On First-Order Meta-Learning Algorithmscited by 1,003
  4. 2016Guided Cost Learning: Deep Inverse Optimal Control via Policy Optimizationcited by 400
  5. 2017One-Shot Imitation Learningcited by 232
  6. 2016Unrolled Generative Adversarial Networkscited by 208
  7. 2017VEEGAN: Reducing Mode Collapse in GANs using Implicit Variational Learningcited by 199
  8. 2017Robust Imitation of Diverse Behaviorscited by 85
  9. 2017Multi-Modal Imitation Learning from Unstructured Demonstrations using Generative Adversarial Netscited by 64
  10. 2017Repeated Inverse Reinforcement Learningcited by 29

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2019: 1; 2020: 0; 2021: 6; 2022: 2; 2023: 6; 2024: 3; 2025: 0; 2026: 2.

20 papers.

Sort:

By area:

  1. 2021Generalized Decision Transformer for Offline Hindsight Information Matchingcited by 105
  2. 2019Meta-Inverse Reinforcement Learning with Probabilistic Context Variablescited by 50
  3. 2022Robust Imitation Learning against Variations in Environment Dynamicscited by 26
  4. 2021MORAL: Aligning AI with Human Norms through Multi-Objective Reinforced Active Learningcited by 24
  5. 2023Learning Shared Safety Constraints from Multi-task Demonstrationscited by 15
  6. 2023SIRL: Similarity-based Implicit Representation Learningcited by 13
  7. 2023Aligning Robot and Human Representationscited by 11
  8. 2023Multi-intention Inverse Q-learning for Interpretable Behavior Representationcited by 9
  9. 2021Combining Reward Information from Multiple Sourcescited by 7
  10. 2023BC-IRL: Learning Generalizable Reward Functions from Demonstrationscited by 7
  11. 2021Meta-Adversarial Inverse Reinforcement Learning for Decision-making Taskscited by 6
  12. 2022Basis for Intentions: Efficient Inverse Reinforcement Learning using Past Experiencecited by 4
8 more
  1. 2024Few-Shot Task Learning through Inverse Generative Modelingcited by 4
  2. 2021LiMIIRL: Lightweight Multiple-Intent Inverse Reinforcement Learningcited by 2
  3. 2026Can Optimal Transport Improve Federated Inverse Reinforcement Learning?cited by 1
  4. 2021Quickest change detection with unknown parameters: Constant complexity and near optimalitycited by 0
  5. 2023Kernel Density Bayesian Inverse Reinforcement Learningcited by 0
  6. 2024Multi Task Inverse Reinforcement Learning for Common Sense Rewardcited by 0
  7. 2024Inverse Reinforcement Learning with Multiple Planning Horizonscited by 0
  8. 2026Generalize and Guide: Decomposing Rewards for Few-Shot Inverse Reinforcement Learningcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2022A Primer on Maximum Causal Entropy Inverse Reinforcement Learning
  2. 2019Generalized Maximum Causal Entropy for Inverse Reinforcement Learning
  3. 2022Weighted Maximum Entropy Inverse Reinforcement Learning
  4. 2020Revisiting Maximum Entropy Inverse Reinforcement Learning: New Perspectives and Algorithms
  5. 2022Task-Guided IRL in POMDPs that Scales
  6. 2021Task-Guided Inverse Reinforcement Learning Under Partial Information
  7. 2019Maximum Likelihood Constraint Inference for Inverse Reinforcement Learning
  8. 2020Efficient Exploration of Reward Functions in Inverse Reinforcement Learning via Bayesian Optimization