Formulating Reinforcement Learning for Human-Robot Collaboration through Off-Policy Evaluation

• URL: http://arxiv.org/abs/2602.02530v1
• Date: Tue, 27 Jan 2026 21:35:13 GMT
• Title: Formulating Reinforcement Learning for Human-Robot Collaboration through Off-Policy Evaluation
• Authors: Saurav Singh, Rodney Sanchez, Alexander Ororbia, Jamison Heard,
• Abstract summary: Reinforcement learning (RL) has the potential to transform real-world decision-making systems.<n>Traditional RL approaches often rely on domain expertise and trial-and-error.<n>This work proposes a novel RL framework that leverages off-policy evaluation for state space and reward function selection.
• Score: 42.19772341787033
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Reinforcement learning (RL) has the potential to transform real-world decision-making systems by enabling autonomous agents to learn from experience. Deploying RL in real-world settings, especially in the context of human-robot interaction, requires defining state representations and reward functions, which are critical for learning efficiency and policy performance. Traditional RL approaches often rely on domain expertise and trial-and-error, necessitating extensive human involvement as well as direct interaction with the environment, which can be costly and impractical, especially in complex and safety-critical applications. This work proposes a novel RL framework that leverages off-policy evaluation (OPE) for state space and reward function selection, using only logged interaction data. This approach eliminates the need for real-time access to the environment or human-in-the-loop feedback, greatly reducing the dependency on costly real-time interactions. The proposed approach systematically evaluates multiple candidate state representations and reward functions by training offline RL agents and applying OPE to estimate policy performance. The optimal state space and reward function are selected based on their ability to produce high-performing policies under OPE metrics. Our method is validated on two environments: the Lunar Lander environment by OpenAI Gym, which provides a controlled setting for assessing state space and reward function selection, and a NASA-MATB-II human subjects study environment, which evaluates the approach's real-world applicability to human-robot teaming scenarios. This work enhances the feasibility and scalability of offline RL for real-world environments by automating critical RL design decisions through a data-driven OPE-based evaluation, enabling more reliable, effective, and sustainable RL formulation for complex human-robot interaction settings.

Related papers

• Autonomous Continual Learning of Computer-Use Agents for Environment Adaptation [57.65688895630163]
  We introduce ACuRL, an Autonomous Curriculum Reinforcement Learning framework that continually adapts agents to specific environments with zero human data.<n>Our method effectively enables both intra-environment and cross-environment continual learning, yielding 4-22% performance gains without forgetting existing environments.
  arXiv  Detail & Related papers  (2026-02-10T23:06:02Z)
• Scaling Agent Learning via Experience Synthesis [100.42712232390532]
  Reinforcement learning can empower autonomous agents by enabling self-improvement through interaction.<n>But its practical adoption remains challenging due to costly rollouts, limited task diversity, unreliable reward signals, and infrastructure complexity.<n>We introduce DreamGym, the first unified framework designed to synthesize diverse experiences with scalability in mind.
  arXiv  Detail & Related papers  (2025-11-05T18:58:48Z)
• UserRL: Training Interactive User-Centric Agent via Reinforcement Learning [104.63494870852894]
  Reinforcement learning (RL) has shown promise in training agentic models that engage in dynamic, multi-turn interactions.<n>We propose UserRL, a unified framework for training and evaluating user-centric abilities through standardized gym environments.
  arXiv  Detail & Related papers  (2025-09-24T03:33:20Z)
• Residual Off-Policy RL for Finetuning Behavior Cloning Policies [41.99435186991878]
  We present a recipe that combines the benefits of behavior cloning (BC) and reinforcement learning (RL) through a residual learning framework.<n>Our method requires only sparse binary reward signals and can effectively improve manipulation policies on high-degree-of-freedom (DoF) systems.<n>In particular, we demonstrate, to the best of our knowledge, the first successful real-world RL training on a humanoid robot with dexterous hands.
  arXiv  Detail & Related papers  (2025-09-23T17:59:46Z)
• Mind the Gap: Towards Generalizable Autonomous Penetration Testing via Domain Randomization and Meta-Reinforcement Learning [15.619925926862235]
  GAP is a generalizable autonomous pentesting framework.<n>It aims to realizes efficient policy training in realistic environments.<n>It also trains agents capable of drawing inferences about other cases from one instance.
  arXiv  Detail & Related papers  (2024-12-05T11:24:27Z)
• OffRIPP: Offline RL-based Informative Path Planning [12.705099730591671]
  IPP is a crucial task in robotics, where agents must design paths to gather valuable information about a target environment. We propose an offline RL-based IPP framework that optimized information gain without requiring real-time interaction during training. We validate the framework through extensive simulations and real-world experiments.
  arXiv  Detail & Related papers  (2024-09-25T11:30:59Z)
• Preference Elicitation for Offline Reinforcement Learning [59.136381500967744]
  We propose Sim-OPRL, an offline preference-based reinforcement learning algorithm.<n>Our algorithm employs a pessimistic approach for out-of-distribution data, and an optimistic approach for acquiring informative preferences about the optimal policy.
  arXiv  Detail & Related papers  (2024-06-26T15:59:13Z)
• MEReQ: Max-Ent Residual-Q Inverse RL for Sample-Efficient Alignment from Intervention [76.83428371942735]
  We introduce MEReQ (Maximum-Entropy Residual-Q Inverse Reinforcement Learning), designed for sample-efficient alignment from human intervention.<n>MereQ infers a residual reward function that captures the discrepancy between the human expert's and the prior policy's underlying reward functions.<n>It then employs Residual Q-Learning (RQL) to align the policy with human preferences using this residual reward function.
  arXiv  Detail & Related papers  (2024-06-24T01:51:09Z)
• Leveraging Optimal Transport for Enhanced Offline Reinforcement Learning in Surgical Robotic Environments [4.2569494803130565]
  We introduce an innovative algorithm designed to assign rewards to offline trajectories, using a small number of high-quality expert demonstrations. This approach circumvents the need for handcrafted rewards, unlocking the potential to harness vast datasets for policy learning.
  arXiv  Detail & Related papers  (2023-10-13T03:39:15Z)
• Affordance Learning from Play for Sample-Efficient Policy Learning [30.701546777177555]
  We use a self-supervised visual affordance model from human teleoperated play data to enable efficient policy learning and motion planning. We combine model-based planning with model-free deep reinforcement learning to learn policies that favor the same object regions favored by people. We find that our policies train 4x faster than the baselines and generalize better to novel objects because our visual affordance model can anticipate their affordance regions.
  arXiv  Detail & Related papers  (2022-03-01T11:00:35Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.