mlsanityData to 14 Oct 2026

From "Thumbs Up" to "10 out of 10": Reconsidering Scalar Feedback in Interactive Reinforcement Learning

arXiv 2311.10284 ↗First posted 17 Nov 2023cs.RO cs.HCcited by 6

On the map: LLM alignment / RLHF / preference optimisation → Reward modeling and RLHF

Abstract (arXiv)

Learning from human feedback is an effective way to improve robotic learning in exploration-heavy tasks. Compared to the wide application of binary human feedback, scalar human feedback has been used less because it is believed to be noisy and unstable. In this paper, we compare scalar and binary feedback, and demonstrate that scalar feedback benefits learning when properly handled. We collected binary or scalar feedback respectively from two groups of crowdworkers on a robot task. We found that when considering how consistently a participant labeled the same data, scalar feedback led to less consistency than binary feedback; however, the difference vanishes if small mismatches are allowed. Additionally, scalar and binary feedback show no significant differences in their correlations with key Reinforcement Learning targets. We then introduce Stabilizing TEacher Assessment DYnamics (STEADY) to improve learning from scalar feedback. Based on the idea that scalar feedback is muti-distributional, STEADY re-constructs underlying positive and negative feedback distributions and re-scales scalar feedback based on feedback statistics. We show that models trained with textitscalar feedback + STEADY outperform baselines, including binary feedback and raw scalar feedback, in a robot reaching task with non-expert human feedback. Our results show that both binary feedback and scalar feedback are dynamic, and scalar feedback is a promising signal for use in interactive Reinforcement Learning.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Placed in Reward modeling and RLHF, one of 10 directions in LLM alignment / RLHF / preference optimisation. Builds on 15 of its 36 references that are in the map. First posted on arXiv 17 Nov 2023.

Builds on

15 of 36 references.

Closest ancestors · 5

Same direction, newest first

  1. 2020The EMPATHIC Framework for Task Learning from Implicit Human Feedback28 Sep
  2. 2018Scalable agent alignment via reward modeling: a research direction19 Nov
  3. 2018Reward learning from human preferences and demonstrations in Atari15 Nov
  4. 2018DQN-TAMER: Human-in-the-Loop Reinforcement Learning with Intractable Feedback28 Oct
  5. 2017Deep reinforcement learning from human preferences12 Jun

Other references · 10

  1. 2016Generative Adversarial Imitation Learningcited by 1,597
  2. 2017Curiosity-driven Exploration by Self-supervised Predictioncited by 1,194
  3. 2016Unifying Count-Based Exploration and Intrinsic Motivationcited by 639
  4. 2016Variational Intrinsic Controlcited by 267
  5. 2015On Wasserstein Two Sample Testing and Related Families of Nonparametric Testscited by 166
  6. 2017Interactive Learning from Policy-Dependent Human Feedbackcited by 158
  7. 2020On Reward-Free Reinforcement Learning with Linear Function Approximationcited by 89
  8. 2021A Survey on Interactive Reinforcement Learning: Design Principles and Open Challengescited by 41
  9. 2017Representation Learning and Pairwise Ranking for Implicit Feedback in Recommendation Systemscited by 11
  10. 2021Self-Initiated Open World Learning for Autonomous AI Agentscited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 2; 2025: 3; 2026: 1.

6 papers.

  1. 2024Enhancing Preference-based Linear Bandits via Human Response Timecited by 3
  2. 2024How Much Progress Did I Make? An Unexplored Human Feedback Signal for Teaching Robotscited by 2
  3. 2025Demonstration Sidetracks: Categorizing Systematic Non-Optimality in Human Demonstrationscited by 2
  4. 2025Towards Reinforcement Learning from Neural Feedback: Mapping fNIRS Signals to Agent Performancecited by 1
  5. 2025Granular feedback merits sophisticated aggregationcited by 0
  6. 2026PHIRL: Aligning Learned Rewards with Task Progress for Inverse Reinforcement Learningcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Mapping out the Space of Human Feedback for Reinforcement Learning: A Conceptual Framework
  2. 2025Pref-GUIDE: Continual Policy Learning from Real-Time Human Feedback via Preference-Based Learning
  3. 2023Boosting Feedback Efficiency of Interactive Reinforcement Learning by Adaptive Learning from Scores
  4. 2025Reinforcement Learning from Multi-level and Episodic Human Feedback
  5. 2021Learning Online from Corrective Feedback: A Meta-Algorithm for Robotics
  6. 2025Reinforcement Learning from Human Feedback
  7. 2026Reinforcement Learning from Human Feedback: A Statistical Perspective
  8. 2023Breadcrumbs to the Goal: Goal-Conditioned Exploration from Human-in-the-Loop Feedback