mlsanityData to 14 Oct 2026

Semi-Supervised Imitation Learning of Team Policies from Suboptimal Demonstrations

arXiv 2205.02959 ↗First posted 5 May 2022cs.AI cs.LG cs.MAcited by 2

On the map: Offline RL and imitation learning from data → Imitation learning methods

Abstract (arXiv)

We present Bayesian Team Imitation Learner (BTIL), an imitation learning algorithm to model the behavior of teams performing sequential tasks in Markovian domains. In contrast to existing multi-agent imitation learning techniques, BTIL explicitly models and infers the time-varying mental states of team members, thereby enabling learning of decentralized team policies from demonstrations of suboptimal teamwork. Further, to allow for sample- and label-efficient policy learning from small datasets, BTIL employs a Bayesian perspective and is capable of learning from semi-supervised demonstrations. We demonstrate and benchmark the performance of BTIL on synthetic multi-agent tasks as well as a novel dataset of human-agent teamwork. Our experiments show that BTIL can successfully learn team policies from demonstrations despite the influence of team members' (time-varying and potentially misaligned) mental states on their behavior.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Placed in Imitation learning methods, one of 13 directions in Offline RL and imitation learning from data. Builds on 20 of its 53 references that are in the map. First posted on arXiv 5 May 2022.

Builds on

20 of 53 references.

Closest ancestors · 8

Same direction, newest first

  1. 2021TRAIL: Near-Optimal Imitation Learning with Suboptimal Data27 Oct
  2. 2021Confidence-Aware Imitation Learning from Demonstrations with Varying Optimality27 Oct
  3. 2020Multi-Agent Interactions Modeling with Correlated Policies4 Jan
  4. 2019Learning Belief Representations for Imitation Learning in POMDPs22 Jun
  5. 2019Adversarial Imitation Learning from Incomplete Demonstrations29 May
  6. 2018An Algorithmic Perspective on Imitation Learning16 Nov
  7. 2018Multi-Agent Generative Adversarial Imitation Learning26 Jul
  8. 2018Behavioral Cloning from Observation4 May

Other references · 12

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2016Generative Adversarial Imitation Learningcited by 1,597
  3. 2019Extrapolating Beyond Suboptimal Demonstrations via Inverse Reinforcement Learning from Observationscited by 260
  4. 2020Learning from Suboptimal Demonstration via Self-Supervised Reward Regressioncited by 84
  5. 2017Coordinated Multi-Agent Imitation Learningcited by 72
  6. 2019Multi-Agent Adversarial Inverse Reinforcement Learningcited by 60
  7. 2018Multi-Agent Imitation Learning for Driving Simulationcited by 50
  8. 2018Generative Modeling of Multimodal Multi-Human Behaviorcited by 24
  9. 2019Simulating Emergent Properties of Human Driving Behavior Using Multi-Agent Reward Augmented Imitation Learningcited by 24
  10. 2014Multi-agent Inverse Reinforcement Learning for Two-person Zero-sum Gamescited by 17
  11. 2018Competitive Multi-agent Inverse Reinforcement Learning with Sub-optimal Demonstrationscited by 11
  12. 2021Towards an AI Coach to Infer Team Mental Model Alignment in Healthcarecited by 11

Built on by

Cited by year

Citing papers per year: 2023: 1; 2024: 1.

2 papers.

  1. 2023Automated Task-Time Interventions to Improve Teamwork using Imitation Learningcited by 7
  2. 2024Open Human-Robot Collaboration using Decentralized Inverse Reinforcement Learningcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Hierarchical Imitation Learning of Team Behavior from Heterogeneous Demonstrations
  2. 2019Few-Shot Bayesian Imitation Learning with Logical Program Policies
  3. 2024A Bayesian Solution To The Imitation Gap
  4. 2022Coordination with Humans via Strategy Matching
  5. 2025Structured Imitation Learning of Interactive Policies through Inverse Games
  6. 2024A Dual Approach to Imitation Learning from Observations with Offline Datasets
  7. 2025R2BC: Multi-Agent Imitation Learning from Single-Agent Demonstrations
  8. 2021Bayesian Disturbance Injection: Robust Imitation Learning of Flexible Policies