mlsanityData to 14 Oct 2026

Imagining In-distribution States: How Predictable Robot Behavior Can Enable User Control Over Learned Policies

arXiv 2406.13711 ↗First posted 19 Jun 2024cs.RO cs.AI cs.HCcited by 0

Not on the map. Why?

Abstract (arXiv)

It is crucial that users are empowered to take advantage of the functionality of a robot and use their understanding of that functionality to perform novel and creative tasks. Given a robot trained with Reinforcement Learning (RL), a user may wish to leverage that autonomy along with their familiarity of how they expect the robot to behave to collaborate with the robot. One technique is for the user to take control of some of the robot's action space through teleoperation, allowing the RL policy to simultaneously control the rest. We formalize this type of shared control as Partitioned Control (PC). However, this may not be possible using an out-of-the-box RL policy. For example, a user's control may bring the robot into a failure state from the policy's perspective, causing it to act unexpectedly and hindering the success of the user's desired task. In this work, we formalize this problem and present Imaginary Out-of-Distribution Actions, IODA, an initial algorithm which empowers users to leverage their expectations of a robot's behavior to accomplish new tasks. We deploy IODA in a user study with a real robot and find that IODA leads to both better task performance and a higher degree of alignment between robot behavior and user expectation. We also show that in PC, there is a strong and significant correlation between task performance and the robot's ability to meet user expectations, highlighting the need for approaches like IODA. Code is available at https://github.com/AABL-Lab/ioda_roman_2024

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 27 of its 44 references that are in the map. First posted on arXiv 19 Jun 2024.

Builds on

27 of 44 references.

References · 27

  1. 2017Deep reinforcement learning from human preferencescited by 3,912
  2. 2022Do As I Can, Not As I Say: Grounding Language in Robotic Affordancescited by 2,348
  3. 2023PaLM-E: An Embodied Multimodal Language Modelcited by 2,071
  4. 2018Soft Actor-Critic Algorithms and Applicationscited by 1,240
  5. 2022Code as Policies: Language Model Programs for Embodied Controlcited by 1,210
  6. 2021Generalized Out-of-Distribution Detection: A Surveycited by 802
  7. 2018Diversity is All You Need: Learning Skills without a Reward Functioncited by 752
  8. 2022Out-of-Distribution Detection with Deep Nearest Neighborscited by 600
  9. 2022Perceiver-Actor: A Multi-Task Transformer for Robotic Manipulationcited by 551
  10. 2021How to Train Your Robot with Deep Reinforcement Learning; Lessons We've Learnedcited by 213
  11. 2021Differentiable Quality Diversitycited by 72
  12. 2018Shared Autonomy via Deep Reinforcement Learningcited by 66
15 more
  1. 2015Shared Autonomy via Hindsight Optimizationcited by 46
  2. 2021A Survey on Interactive Reinforcement Learning: Design Principles and Open Challengescited by 41
  3. 2021Lifelong Robotic Reinforcement Learning by Retaining Experiencescited by 34
  4. 2021Explainable AI for Robot Failures: Generating Explanations that Improve User Assistance in Fault Recoverycited by 32
  5. 2022The Utility of Explainable AI in Ad Hoc Human-Machine Teamingcited by 30
  6. 2022Don't Start From Scratch: Leveraging Prior Data to Automate Robotic Reinforcement Learningcited by 29
  7. 2023To the Noise and Back: Diffusion for Shared Autonomycited by 22
  8. 2020Explainable robotic systems: Understanding goal-driven actions in a reinforcement learning scenariocited by 19
  9. 2021Discovering Diverse Solutions in Deep Reinforcement Learning by Maximizing State-Action-Based Mutual Informationcited by 19
  10. 2022PATO: Policy Assisted TeleOperation for Scalable Robot Data Collectioncited by 19
  11. 2021Situational Confidence Assistance for Lifelong Shared Autonomycited by 15
  12. 2021Explainable Autonomous Robots: A Survey and Perspectivecited by 15
  13. 2023Can Agents Run Relay Race with Strangers? Generalization of RL to Out-of-Distribution Trajectoriescited by 9
  14. 2022Shared Control in Human Robot Teaming: Toward Context-Aware Communicationcited by 3
  15. 2023Modifying RL Policies with Imagined Actions: How Predictable Policies Can Enable Users to Perform Novel Taskscited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026OHP-RL: Online Human Preference as Guidance in Reinforcement Learning for Robot Manipulation
  2. 2021Implicit Behavioral Cloning
  3. 2025FlashBack: Consistency Model-Accelerated Shared Autonomy
  4. 2019Operation and Imitation under Safety-Aware Shared Control
  5. 2024Online Behavior Modification for Expressive User Control of RL-Trained Robots
  6. 2025Steering Your Diffusion Policy with Latent Space Reinforcement Learning
  7. 2022How to Spend Your Robot Time: Bridging Kickstarting and Offline Reinforcement Learning for Vision-based Robotic Manipulation
  8. 2026SAPS: Shared Autonomy for Policy Steering by Blending Teleoperation with a Pretrained VLA