# DAPPER: Discriminability-Aware Policy-to-Policy Preference-Based Reinforcement Learning for Query-Efficient Robot Skill Acquisition

arXiv: https://arxiv.org/abs/2505.06357 · HTML: https://mlsanity.com/paper/2505.06357/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in RL training of language and agent models, one of 15 directions in Deep reinforcement learning methods.
- Builds on 22 of its 30 references that are in the map.
- First posted on arXiv 9 May 2025.

## Placed in

- Deep reinforcement learning methods / [RL training of language and agent models](https://mlsanity.com/deeprl/rl-training-of-language-and-agent-models/)

## Builds on (most cited first, 22 of 22)

- [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)
- [Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning](https://mlsanity.com/paper/1506.02142/) (2015)
- [Deep reinforcement learning from human preferences](https://mlsanity.com/paper/1706.03741/) (2017)
- [Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2307.15217/) (2023)
- [SpatialVLM: Endowing Vision-Language Models with Spatial Reasoning Capabilities](https://mlsanity.com/paper/2401.12168/) (2024)
- [Sim-to-Real Transfer of Robotic Control with Dynamics Randomization](https://mlsanity.com/paper/1710.06537/) (2017)
- [Learning to Walk in Minutes Using Massively Parallel Deep Reinforcement Learning](https://mlsanity.com/paper/2109.11978/) (2021)
- [PEBBLE: Feedback-Efficient Interactive Reinforcement Learning via Relabeling Experience and Unsupervised Pre-training](https://mlsanity.com/paper/2106.05091/) (2021)
- [Vision-Language Models are Zero-Shot Reward Models for Reinforcement Learning](https://mlsanity.com/paper/2310.12921/) (2023)
- [SURF: Semi-supervised Reward Learning with Data Augmentation for Feedback-efficient Preference-based Reinforcement Learning](https://mlsanity.com/paper/2203.10050/) (2022)
- [Asking Easy Questions: A User-Friendly Approach to Active Reward Learning](https://mlsanity.com/paper/1910.04365/) (2019)
- [Penalized Proximal Policy Optimization for Safe Reinforcement Learning](https://mlsanity.com/paper/2205.11814/) (2022)
- [Learning Agile Skills via Adversarial Imitation of Rough Partial Demonstrations](https://mlsanity.com/paper/2206.11693/) (2022)
- [Overcoming Model Bias for Robust Offline Deep Reinforcement Learning](https://mlsanity.com/paper/2008.05533/) (2020)
- [RIME: Robust Preference-based Reinforcement Learning with Noisy Preferences](https://mlsanity.com/paper/2402.17257/) (2024)
- [Model-based Safe Deep Reinforcement Learning via a Constrained Proximal Policy Optimization Algorithm](https://mlsanity.com/paper/2210.07573/) (2022)
- [Reinforcement learning with human advice: a survey](https://mlsanity.com/paper/2005.11016/) (2020)
- [Discovering Diverse Solutions in Deep Reinforcement Learning by Maximizing State-Action-Based Mutual Information](https://mlsanity.com/paper/2103.07084/) (2021)
- [Query-Policy Misalignment in Preference-Based Reinforcement Learning](https://mlsanity.com/paper/2305.17400/) (2023)
- [Disturbance-Injected Robust Imitation Learning with Task Achievement](https://mlsanity.com/paper/2205.04195/) (2022)
- [Rewards Encoding Environment Dynamics Improves Preference-based Reinforcement Learning](https://mlsanity.com/paper/2211.06527/) (2022)

## Built on by (most cited first, 1 of 1)

- [Co-Evolution in Agentic Systems: Toward Self-Directed Evolution Beyond Human Design](https://mlsanity.com/paper/2608.10299/) (2026)

## Abstract (arXiv)

Preference-based Reinforcement Learning (PbRL) enables policy learning through simple queries comparing trajectories from a single policy. While human responses to these queries make it possible to learn policies aligned with human preferences, PbRL suffers from low query efficiency, as policy bias limits trajectory diversity and reduces the number of discriminable queries available for learning preferences. This paper identifies preference discriminability, which quantifies how easily a human can judge which trajectory is closer to their ideal behavior, as a key metric for improving query efficiency. To address this, we move beyond comparisons within a single policy and instead generate queries by comparing trajectories from multiple policies, as training them from scratch promotes diversity without policy bias. We propose Discriminability-Aware Policy-to-Policy Preference-Based Efficient Reinforcement Learning (DAPPER), which integrates preference discriminability with trajectory diversification achieved by multiple policies. DAPPER trains new policies from scratch after each reward update and employs a discriminator that learns to estimate preference discriminability, enabling the prioritized sampling of more discriminable queries. During training, it jointly maximizes the preference reward and preference discriminability score, encouraging the discovery of highly rewarding and easily distinguishable policies. Experiments in simulated and real-world legged robot environments demonstrate that DAPPER outperforms previous methods in query efficiency, particularly under challenging preference discriminability conditions. A supplementary video that facilitates understanding of the proposed framework and its experimental results is available at: https://youtu.be/lRwX8FNN8n4