What you reward is what you learn: Comparing rewards for online speech policy optimization in public HRI

• URL: http://arxiv.org/abs/2601.01969v1
• Date: Mon, 05 Jan 2026 10:22:58 GMT
• Title: What you reward is what you learn: Comparing rewards for online speech policy optimization in public HRI
• Abstract summary: We study how to adapt a social robot's speech policy in the wild.<n>During a 12-day in-situ deployment with over 1,400 public encounters, we cast online policy optimization as a multi-armed bandit problem.<n>We distill ready-to-use design lessons for deploying online optimization of speech policies in real public HRI settings.
• Score: 15.072441840105824
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Designing policies that are both efficient and acceptable for conversational service robots in open and diverse environments is non-trivial. Unlike fixed, hand-tuned parameters, online learning can adapt to non-stationary conditions. In this paper, we study how to adapt a social robot's speech policy in the wild. During a 12-day in-situ deployment with over 1,400 public encounters, we cast online policy optimization as a multi-armed bandit problem and use Thompson sampling to select among six actions defined by speech rate (slow/normal/fast) and verbosity (concise/detailed). We compare three complementary binary rewards--Ru (user rating), Rc (conversation closure), and Rt (>=2 turns)--and show that each induces distinct arm distributions and interaction behaviors. We complement the online results with offline evaluations that analyze contextual factors (e.g., crowd level, group size) using video-annotated data. Taken together, we distill ready-to-use design lessons for deploying online optimization of speech policies in real public HRI settings.

Related papers

• Co-Evolving LLM Evaluators and Policies via DynamicRubric [67.2962847914162]
  Post-training with evaluator feedback on policy-induced samples serves as a major mechanism for improving large language models.<n>We propose DynamicRubric, a response-set-conditioned evaluator--policy co-evolution framework.<n>In experiments with 8B backbones, DynamicRubric improves evaluator performance and provides stronger policy supervision than baselines.
  arXiv  Detail & Related papers  (2026-07-22T12:35:40Z)
• Beyond Survival: Evaluating LLMs in Social Deduction Games with Human-Aligned Strategies [54.08697738311866]
  Social deduction games like Werewolf combine language, reasoning, and strategy.<n>We curate a high-quality, human-verified multimodal Werewolf dataset containing over 100 hours of video, 32.4M utterance tokens, and 15 rule variants.<n>We propose a novel strategy-alignment evaluation that leverages the winning faction's strategies as ground truth in two stages.
  arXiv  Detail & Related papers  (2025-10-13T13:33:30Z)
• Ready-to-React: Online Reaction Policy for Two-Character Interaction Generation [82.73098356401725]
  We propose an online reaction policy, called Ready-to-React, to generate the next character pose based on past observed motions.<n>Each character has its own reaction policy as its "brain", enabling them to interact like real humans in a streaming manner.<n>Our approach can be controlled by sparse signals, making it well-suited for VR and other online interactive environments.
  arXiv  Detail & Related papers  (2025-02-27T18:40:30Z)
• OMPO: A Unified Framework for RL under Policy and Dynamics Shifts [42.57662196581823]
  Training reinforcement learning policies using environment interaction data collected from varying policies or dynamics presents a fundamental challenge. Existing works often overlook the distribution discrepancies induced by policy or dynamics shifts, or rely on specialized algorithms with task priors. In this paper, we identify a unified strategy for online RL policy learning under diverse settings of policy and dynamics shifts: transition occupancy matching.
  arXiv  Detail & Related papers  (2024-05-29T13:36:36Z)
• PREDILECT: Preferences Delineated with Zero-Shot Language-based Reasoning in Reinforcement Learning [2.7387720378113554]
  Preference-based reinforcement learning (RL) has emerged as a new field in robot learning. We use the zero-shot capabilities of a large language model (LLM) to reason from the text provided by humans. In both a simulated scenario and a user study, we reveal the effectiveness of our work by analyzing the feedback and its implications.
  arXiv  Detail & Related papers  (2024-02-23T16:30:05Z)
• Is Inverse Reinforcement Learning Harder than Standard Reinforcement Learning? A Theoretical Perspective [55.36819597141271]
  Inverse Reinforcement Learning (IRL) -- the problem of learning reward functions from demonstrations of an emphexpert policy -- plays a critical role in developing intelligent systems. This paper provides the first line of efficient IRL in vanilla offline and online settings using samples and runtime. As an application, we show that the learned rewards can emphtransfer to another target MDP with suitable guarantees.
  arXiv  Detail & Related papers  (2023-11-29T00:09:01Z)
• Offline Retraining for Online RL: Decoupled Policy Learning to Mitigate Exploration Bias [96.14064037614942]
  offline retraining, a policy extraction step at the end of online fine-tuning, is proposed. An optimistic (exploration) policy is used to interact with the environment, and a separate pessimistic (exploitation) policy is trained on all the observed data for evaluation.
  arXiv  Detail & Related papers  (2023-10-12T17:50:09Z)
• Increasing Students' Engagement to Reminder Emails Through Multi-Armed Bandits [60.4933541247257]
  This paper shows a real-world adaptive experiment on how students engage with instructors' weekly email reminders to build their time management habits. Using Multi-Armed Bandits (MAB) algorithms in adaptive experiments can increase students' chances of obtaining better outcomes. We highlight problems with these adaptive algorithms - such as possible exploitation of an arm when there is no significant difference.
  arXiv  Detail & Related papers  (2022-08-10T00:30:52Z)
• Online vs. Offline Adaptive Domain Randomization Benchmark [20.69035879843824]
  We present an open benchmark for both offline and online methods (SimOpt, BayRn, DROID, DROPO) to shed light on which are most suitable for each setting and task at hand. We found that online methods are limited by the quality of the currently learned policy for the next iteration, while offline methods may sometimes fail when replaying trajectories in simulation with open-loop commands.
  arXiv  Detail & Related papers  (2022-06-29T14:03:53Z)
• Learning a subspace of policies for online adaptation in Reinforcement Learning [14.7945053644125]
  In control systems, the robot on which a policy is learned might differ from the robot on which a policy will run. There is a need to develop RL methods that generalize well to variations of the training conditions. In this article, we consider the simplest yet hard to tackle generalization setting where the test environment is unknown at train time.
  arXiv  Detail & Related papers  (2021-10-11T11:43:34Z)
• Non-Stationary Off-Policy Optimization [50.41335279896062]
  We study the novel problem of off-policy optimization in piecewise-stationary contextual bandits. In the offline learning phase, we partition logged data into categorical latent states and learn a near-optimal sub-policy for each state. In the online deployment phase, we adaptively switch between the learned sub-policies based on their performance.
  arXiv  Detail & Related papers  (2020-06-15T09:16:09Z)

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.