Offline Learning of Controllable Diverse Behaviors
On the map: Offline RL and imitation learning from data → Imitation learning methods
Abstract (arXiv)
Imitation Learning (IL) techniques aim to replicate human behaviors in specific tasks. While IL has gained prominence due to its effectiveness and efficiency, traditional methods often focus on datasets collected from experts to produce a single efficient policy. Recently, extensions have been proposed to handle datasets of diverse behaviors by mainly focusing on learning transition-level diverse policies or on performing entropy maximization at the trajectory level. While these methods may lead to diverse behaviors, they may not be sufficient to reproduce the actual diversity of demonstrations or to allow controlled trajectory generation. To overcome these drawbacks, we propose a different method based on two key features: a) Temporal Consistency that ensures consistent behaviors across entire episodes and not just at the transition level as well as b) Controllability obtained by constructing a latent space of behaviors that allows users to selectively activate specific behaviors based on their requirements. We compare our approach to state-of-the-art methods over a diverse set of tasks and environments. Project page: https://mathieu-petitbois.github.io/projects/swr/
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 16 of its 29 references that are in the map. First posted on arXiv 25 Apr 2025.
Builds on
16 of 29 references.
Closest ancestors · 1
Same direction, newest first
Other references · 15
- 2020Conservative Q-Learning for Offline Reinforcement Learningcited by 1,809
- 2016Generative Adversarial Imitation Learningcited by 1,597
- 2023Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardwarecited by 1,568
- 2021Decision Transformer: Reinforcement Learning via Sequence Modelingcited by 1,546
- 2021Offline Reinforcement Learning with Implicit Q-Learningcited by 1,293
- 2018Off-Policy Deep Reinforcement Learning without Explorationcited by 1,241
- 2021What Matters in Learning from Offline Human Demonstrations for Robot Manipulationcited by 725
- 2021Offline Reinforcement Learning as One Big Sequence Modeling Problemcited by 644
- 2022Is Conditional Generative Modeling all you need for Decision-Making?cited by 516
- 2015A note on the evaluation of generative modelscited by 292
- 2023Goal-Conditioned Imitation Learning using Score-based Diffusion Policiescited by 236
- 2022When Should We Prefer Offline Reinforcement Learning Over Behavioral Cloning?cited by 89
3 more
- 2017Robust Imitation of Diverse Behaviorscited by 86
- 2017Multi-Modal Imitation Learning from Unstructured Demonstrations using Generative Adversarial Netscited by 64
- 2019Diverse Behavior Is What Game AI Needs: Generating Varied Human-Like Playing Styles Using Evolutionary Multi-Objective Deep Reinforcement Learningcited by 1
Built on by
Citing papers per year: 2026: 2.
2 papers.
Similar, not cited
Close in wording, no citation either way
- 2024How to Leverage Diverse Demonstrations in Offline Imitation Learning
- 2024Towards Diverse Behaviors: A Benchmark for Imitation Learning with Human Demonstrations
- 2024Is Behavior Cloning All You Need? Understanding Horizon in Imitation Learning
- 2023Improving Behavioural Cloning with Positive Unlabeled Learning
- 2025Robust Offline Imitation Learning Through State-level Trajectory Stitching
- 2023Information Maximizing Curriculum: A Curriculum-Based Approach for Imitating Diverse Skills
- 2023Behavior Retrieval: Few-Shot Imitation Learning by Querying Unlabeled Datasets
- 2024Imitation from Diverse Behaviors: Wasserstein Quality Diversity Imitation Learning with Single-Step Archive Exploration