# Aligning Humans and Robots via Reinforcement Learning from Implicit Human Feedback

arXiv: https://arxiv.org/abs/2507.13171 · HTML: https://mlsanity.com/paper/2507.13171/

## Key facts

- Cited by 3 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 16 of its 31 references that are in the map.
- First posted on arXiv 17 Jul 2025.

## Placed in

- LLM alignment / RLHF / preference optimisation / [Reward modeling and RLHF](https://mlsanity.com/alignment/reward-modeling-and-rlhf/)

## Builds on (most cited first, 16 of 16)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor](https://mlsanity.com/paper/1801.01290/) (2018)
- [Deep reinforcement learning from human preferences](https://mlsanity.com/paper/1706.03741/) (2017)
- [EEGNet: A Compact Convolutional Network for EEG-based Brain-Computer Interfaces](https://mlsanity.com/paper/1611.08024/) (2016)
- [robosuite: A Modular Simulation Framework and Benchmark for Robot Learning](https://mlsanity.com/paper/2009.12293/) (2020)
- [PEBBLE: Feedback-Efficient Interactive Reinforcement Learning via Relabeling Experience and Unsupervised Pre-training](https://mlsanity.com/paper/2106.05091/) (2021)
- [Interactive Learning from Policy-Dependent Human Feedback](https://mlsanity.com/paper/1701.06049/) (2017)
- [Deep TAMER: Interactive Agent Shaping in High-Dimensional State Spaces](https://mlsanity.com/paper/1709.10163/) (2017)
- [SURF: Semi-supervised Reward Learning with Data Augmentation for Feedback-efficient Preference-based Reinforcement Learning](https://mlsanity.com/paper/2203.10050/) (2022)
- [Preference Transformer: Modeling Human Preferences using Transformers for RL](https://mlsanity.com/paper/2303.00957/) (2023)
- [Reward Uncertainty for Exploration in Preference-based Reinforcement Learning](https://mlsanity.com/paper/2205.12401/) (2022)
- [LATTE: LAnguage Trajectory TransformEr](https://mlsanity.com/paper/2208.02918/) (2022)
- [RIME: Robust Preference-based Reinforcement Learning with Noisy Preferences](https://mlsanity.com/paper/2402.17257/) (2024)
- [Accelerated Robot Learning via Human Brain Signals](https://mlsanity.com/paper/1910.00682/) (2019)
- [Breadcrumbs to the Goal: Goal-Conditioned Exploration from Human-in-the-Loop Feedback](https://mlsanity.com/paper/2307.11049/) (2023)
- [Maximizing BCI Human Feedback using Active Learning](https://mlsanity.com/paper/2008.04873/) (2020)

## Built on by (most cited first, 3 of 3)

- [Accelerating Reinforcement Learning via Error-Related Human Brain Signals](https://mlsanity.com/paper/2511.18878/) (2025)
- [Efficient Federated RLHF via Zeroth-Order Policy Optimization](https://mlsanity.com/paper/2604.17747/) (2026)
- [An offline approach to fNIRS-guided reinforcement learning for robot behavior](https://mlsanity.com/paper/2607.14393/) (2026)

## Abstract (arXiv)

Conventional reinforcement learning (RL) ap proaches often struggle to learn effective policies under sparse reward conditions, necessitating the manual design of complex, task-specific reward functions. To address this limitation, rein forcement learning from human feedback (RLHF) has emerged as a promising strategy that complements hand-crafted rewards with human-derived evaluation signals. However, most existing RLHF methods depend on explicit feedback mechanisms such as button presses or preference labels, which disrupt the natural interaction process and impose a substantial cognitive load on the user. We propose a novel reinforcement learning from implicit human feedback (RLIHF) framework that utilizes non-invasive electroencephalography (EEG) signals, specifically error-related potentials (ErrPs), to provide continuous, implicit feedback without requiring explicit user intervention. The proposed method adopts a pre-trained decoder to transform raw EEG signals into probabilistic reward components, en abling effective policy learning even in the presence of sparse external rewards. We evaluate our approach in a simulation environment built on the MuJoCo physics engine, using a Kinova Gen2 robotic arm to perform a complex pick-and-place task that requires avoiding obstacles while manipulating target objects. The results show that agents trained with decoded EEG feedback achieve performance comparable to those trained with dense, manually designed rewards. These findings validate the potential of using implicit neural feedback for scalable and human-aligned reinforcement learning in interactive robotics.