mlsanityData to 14 Oct 2026

Deep Adaptive Multi-Intention Inverse Reinforcement Learning

arXiv 2107.06692 ↗First posted 14 Jul 2021cs.LG cs.AIcited by 6

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

Abstract (arXiv)

This paper presents a deep Inverse Reinforcement Learning (IRL) framework that can learn an a priori unknown number of nonlinear reward functions from unlabeled experts' demonstrations. For this purpose, we employ the tools from Dirichlet processes and propose an adaptive approach to simultaneously account for both complex and unknown number of reward functions. Using the conditional maximum entropy principle, we model the experts' multi-intention behaviors as a mixture of latent intention distributions and derive two algorithms to estimate the parameters of the deep reward network along with the number of experts' intentions from unlabeled demonstrations. The proposed algorithms are evaluated on three benchmarks, two of which have been specifically extended in this study for multi-intention IRL, and compared with well-known baselines. We demonstrate through several experiments the advantages of our algorithms over the existing approaches and the benefits of online inferring, rather than fixing beforehand, the number of expert's intentions.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Placed in Inverse reinforcement learning, one of 13 directions in Offline RL and imitation learning from data. Builds on 9 of its 39 references that are in the map. First posted on arXiv 14 Jul 2021.

Builds on

9 of 39 references.

References · 9

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2015Maximum Entropy Deep Inverse Reinforcement Learningcited by 176
  3. 2017Multi-Modal Imitation Learning from Unstructured Demonstrations using Generative Adversarial Netscited by 64
  4. 2016Stick-Breaking Variational Autoencoderscited by 44
  5. 2019Learning a Multi-Modal Policy via Imitating Demonstrations with Mixed Behaviorscited by 9
  6. 2021Learning to Simulate on Sparse Trajectory Datacited by 6
  7. 2017Inverse Reinforce Learning with Nonparametric Behavior Clusteringcited by 4
  8. 2018Robot eye-hand coordination learning by watching human demonstrations: a task function approximation approachcited by 4
  9. 2020On the Variational Posterior of Dirichlet Process Deep Latent Gaussian Mixture Modelscited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 2; 2023: 2; 2024: 1; 2025: 0; 2026: 1.

6 papers.

  1. 2022Fast Lifelong Adaptive Inverse Reinforcement Learning from Demonstrationscited by 14
  2. 2023Multi-intention Inverse Q-learning for Interpretable Behavior Representationcited by 9
  3. 2024Towards Sample-Efficiency and Generalization of Transfer and Inverse Reinforcement Learning: A Comprehensive Literature Reviewcited by 3
  4. 2026CoMI-IRL: Contrastive Multi-Intention Inverse Reinforcement Learningcited by 2
  5. 2022Strategy Discovery and Mixture in Lifelong Learning from Heterogeneous Demonstrationcited by 1
  6. 2023On Combining Expert Demonstrations in Imitation Learning via Optimal Transportcited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2022Basis for Intentions: Efficient Inverse Reinforcement Learning using Past Experience
  2. 2019Meta-Inverse Reinforcement Learning with Probabilistic Context Variables
  3. 2021Versatile Inverse Reinforcement Learning via Cumulative Rewards
  4. 2024Inverse Reinforcement Learning with Sub-optimal Experts
  5. 2018A Survey of Inverse Reinforcement Learning: Challenges, Methods and Progress
  6. 2023BC-IRL: Learning Generalizable Reward Functions from Demonstrations
  7. 2018Multi-task Maximum Entropy Inverse Reinforcement Learning
  8. 2020Inverse Reinforcement Learning from a Gradient-based Learner