# Leveraging Human Feedback for Semantically-Relevant Skill Discovery

arXiv: https://arxiv.org/abs/2604.24127 · HTML: https://mlsanity.com/paper/2604.24127/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Reward modeling and RLHF, one of 10 directions in LLM alignment / RLHF / preference optimisation.
- Builds on 29 of its 41 references that are in the map.
- First posted on arXiv 27 Apr 2026.

## Placed in

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

## Builds on (most cited first, 29 of 29)

- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Deep reinforcement learning from human preferences](https://mlsanity.com/paper/1706.03741/) (2017)
- [Continuous control with deep reinforcement learning](https://mlsanity.com/paper/1509.02971/) (2015)
- [Addressing Function Approximation Error in Actor-Critic Methods](https://mlsanity.com/paper/1802.09477/) (2018)
- [DeepMind Control Suite](https://mlsanity.com/paper/1801.00690/) (2018)
- [Deep Reinforcement Learning at the Edge of the Statistical Precipice](https://mlsanity.com/paper/2108.13264/) (2021)
- [A Distributional Perspective on Reinforcement Learning](https://mlsanity.com/paper/1707.06887/) (2017)
- [Diversity is All You Need: Learning Skills without a Reward Function](https://mlsanity.com/paper/1802.06070/) (2018)
- [Dynamics-Aware Unsupervised Discovery of Skills](https://mlsanity.com/paper/1907.01657/) (2019)
- [PEBBLE: Feedback-Efficient Interactive Reinforcement Learning via Relabeling Experience and Unsupervised Pre-training](https://mlsanity.com/paper/2106.05091/) (2021)
- [Variational Intrinsic Control](https://mlsanity.com/paper/1611.07507/) (2016)
- [Accounting for Variance in Machine Learning Benchmarks](https://mlsanity.com/paper/2103.03098/) (2021)
- [Behavior From the Void: Unsupervised Active Pre-Training](https://mlsanity.com/paper/2103.04551/) (2021)
- [Controlling Overestimation Bias with Truncated Mixture of Continuous Distributional Quantile Critics](https://mlsanity.com/paper/2005.04269/) (2020)
- [URLB: Unsupervised Reinforcement Learning Benchmark](https://mlsanity.com/paper/2110.15191/) (2021)
- [Variational Option Discovery Algorithms](https://mlsanity.com/paper/1807.10299/) (2018)
- [Explore, Discover and Learn: Unsupervised Discovery of State-Covering Skills](https://mlsanity.com/paper/2002.03647/) (2020)
- [B-Pref: Benchmarking Preference-Based Reinforcement Learning](https://mlsanity.com/paper/2111.03026/) (2021)
- [SURF: Semi-supervised Reward Learning with Data Augmentation for Feedback-efficient Preference-based Reinforcement Learning](https://mlsanity.com/paper/2203.10050/) (2022)
- [METRA: Scalable Unsupervised RL with Metric-Aware Abstraction](https://mlsanity.com/paper/2310.08887/) (2023)
- [XSkill: Cross Embodiment Skill Discovery](https://mlsanity.com/paper/2307.09955/) (2023)
- [LOTUS: Continual Imitation Learning for Robot Manipulation Through Unsupervised Skill Discovery](https://mlsanity.com/paper/2311.02058/) (2023)
- [Lipschitz-constrained Unsupervised Skill Discovery](https://mlsanity.com/paper/2202.00914/) (2022)
- [Controllability-Aware Unsupervised Skill Discovery](https://mlsanity.com/paper/2302.05103/) (2023)
- [Learning Mixtures of Plackett-Luce Models](https://mlsanity.com/paper/1603.07323/) (2016)
- [Language Guided Skill Discovery](https://mlsanity.com/paper/2406.06615/) (2024)
- [Do's and Don'ts: Learning Desirable Skills with Instruction Videos](https://mlsanity.com/paper/2406.00324/) (2024)
- [Controlled Diversity with Preference : Towards Learning a Diverse Set of Desired Skills](https://mlsanity.com/paper/2303.04592/) (2023)
- [Human-Aligned Skill Discovery: Balancing Behaviour Exploration and Alignment](https://mlsanity.com/paper/2501.17431/) (2025)

## Abstract (arXiv)

Unsupervised skill discovery in reinforcement learning aims to intrinsically motivate agents to discover diverse and useful behaviours. However, unconstrained approaches can produce unsafe, unethical, or misaligned behaviours. To mitigate these risks and improve the practical desireability of discovered skills, recent work grounds the discovery process by leveraging human preference feedback. However, preference-based approaches are feedback-inefficient and inherently ill-equipped to deal with skill spaces composed of a variety of different skills such as running, jumping, walking, etc. To overcome this limitation, we introduce semantic labelling, a novel and feedback-efficient approach that leverages human cognitive strengths to identify and label semantically meaningful behaviours. Based on semantic labelling, we propose Semantically Relevant Skill Discovery (SRSD), a novel human-in-the-loop approach that collects semantic labels from human feedback and learns a reward function to encourage skills to be more semantically diverse and relevant. Through our experiments in a 2D navigation environment and four locomotion environments, we demonstrate that SRSD can improve semantic diversity and discover relevant behaviours while scaling effectively to a large variety of behaviours.