Learning the Value Systems of Agents with Preference-based and Inverse Reinforcement Learning
Universidad Rey Juan Carlos（雷乌安卡洛斯大学）
Andrés Holgado-Sánchez, Holger Billhardt, Alberto Fernández, Sascha Ossowski
备注：
42 pages, 5 figures. Published in Journal of Autonomous Agents and Multi-Agent Systems
发表信息：
Holgado-Sánchez, A., Billhardt, H., Fernández, A., Ossowski, S. Learning the value systems of agents with preference-based and inverse reinforcement learning. Autonomous Agents Multi-Agent Systems 40, 4 (2026)
Agreement Technologies refer to open computer systems in which autonomous software agents interact with one another, typically on behalf of humans, in order to come to mutually acceptable agreements. With the advance of AI systems in recent years, it has become apparent that such agreements, in order to be acceptable to the involved parties, must remain aligned with ethical principles and moral values. However, this is notoriously difficult to ensure, especially as different human users (and their software agents) may hold different value systems, i.e. they may differently weigh the importance of individual moral values. Furthermore, it is often hard to specify the precise meaning of a value in a particular context in a computational manner. Methods to estimate value systems based on human-engineered specifications, e.g. based on value surveys, are limited in scale due to the need for intense human moderation. In this article, we propose a novel method to automatically \emph{learn} value systems from observations and human demonstrations. In particular, we propose a formal model of the \emph{value system learning} problem, its instantiation to sequential decision-making domains based on multi-objective Markov decision processes, as well as tailored preference-based and inverse reinforcement learning algorithms to infer value grounding functions and value systems. The approach is illustrated and evaluated by two simulated use cases.
We introduce a new algorithm for multi-objective reinforcement learning (MORL) with linear preferences, with the goal of enabling few-shot adaptation to new tasks. In MORL, the aim is to learn policies over multiple competing objectives whose relative importance (preferences) is unknown to the agent. While this alleviates dependence on scalar reward design, the expected return of a policy can change significantly with varying preferences, making it challenging to learn a single model to produce optimal policies under different preference conditions. We propose a generalized version of the Bell…
Reinforcement Learning has suffered from poor reward specification, and issues for reward hacking even in simple enough domains. Preference Based Reinforcement Learning attempts to solve the issue by utilizing binary feedbacks on queried trajectory pairs by a human in the loop indicating their preferences about the agent's behavior to learn a reward model. In this work, we present a state augmentation technique that allows the agent's reward model to be robust and follow an invariance consistency that significantly improved performance, i.e. the reward recovery and subsequent return computed u…
University of Bristol（布里斯托大学）；CortAIx, Thales（泰雷兹公司 CortAIx）
The potential of reinforcement learning (RL) to deliver aligned and performant agents is partially bottlenecked by the reward engineering problem. One alternative to heuristic trial-and-error is preference-based RL (PbRL), where a reward function is inferred from sparse human feedback. However, prior PbRL methods lack interpretability of the learned reward structure, which hampers the ability to assess robustness and alignment. We propose an online, active preference learning algorithm that constructs reward functions with the intrinsically interpretable, compositional structure of a tree. Usi…
Preference Elicitation for Offline Reinforcement Learning
ETH AI Center（ETH人工智能中心）；ETH Zürich（苏黎世联邦理工学院）；MPI for Intelligent Systems（智能系统马克斯·普朗克研究所）；ELLIS Institute Tübingen（图宾根ELLIS研究所）；University of Zürich（苏黎世大学）
Ubiquitous Knowledge Processing Lab (UKP-TUDA)（泛在知识处理实验室（UKP-TUDA））；Technische Universität Darmstadt（达姆施塔特工业大学）
We propose a method to perform automatic document summarisation without using reference summaries. Instead, our method interactively learns from users' preferences. The merit of preference-based interactive summarisation is that preferences are easier for users to provide than reference summaries. Existing preference-based interactive learning methods suffer from high sample complexity, i.e. they need to interact with the oracle for many rounds in order to converge. In this work, we propose a new objective function, which enables us to leverage active learning, preference learning and reinforc…
Microsoft Research（微软研究院）；MPI-SWS（马克斯·普朗克软件系统研究所）；ETH Zurich（苏黎世联邦理工学院）
Inverse reinforcement learning (IRL) enables an agent to learn complex behavior by observing demonstrations from a (near-)optimal policy. The typical assumption is that the learner's goal is to match the teacher's demonstrated behavior. In this paper, we consider the setting where the learner has its own preferences that it additionally takes into consideration. These preferences can for example capture behavioral biases, mismatched worldviews, or physical constraints. We study two teaching approaches: learner-agnostic teaching, where the teacher provides demonstrations from an optimal policy …
Reinforcement Learning with Pairwise Preferences in Long-Term Decision Problems
School of Computer Science, McGill University, Montreal, Quebec, Canada（麦吉尔大学计算机科学学院）；Mila - Quebec AI Institute, Montreal, Quebec, Canada（魁北克人工智能研究所）；Department of Electrical Engineering, Stanford University, Stanford, California, USA（斯坦福大学电气工程系）
Conveying complex objectives to reinforcement learning (RL) agents often requires meticulous reward engineering. Preference-based RL methods are able to learn a more flexible reward model based on human preferences by actively incorporating human feedback, i.e. teacher's preferences between two clips of behaviors. However, poor feedback-efficiency still remains a problem in current preference-based RL algorithms, as tailored human feedback is very expensive. To handle this issue, previous methods have mainly focused on improving query selection and policy initialization. At the same time, rece…
Frankfurt Institute for Advanced Studies（法兰克福高等研究院）；EPFL（洛桑联邦理工学院）
We state the problem of inverse reinforcement learning in terms of preference elicitation, resulting in a principled (Bayesian) statistical formulation. This generalises previous work on Bayesian inverse reinforcement learning and allows us to obtain a posterior distribution on the agent's preferences, policy and optionally, the obtained reward sequence, from observations. We examine the relation of the resulting approach to other statistical methods for inverse reinforcement learning via analysis and experimental results. We show that preferences can be determined accurately, even if the obse…
Microsoft（微软）；Carnegie Mellon University（卡内基梅隆大学）；University of California, Los Angles（加利福尼亚大学洛杉矶分校）
Preference-based Reinforcement Learning (PbRL) replaces reward values in traditional reinforcement learning by preferences to better elicit human opinion on the target objective, especially when numerical reward values are hard to design or interpret. Despite promising results in applications, the theoretical understanding of PbRL is still in its infancy. In this paper, we present the first finite-time analysis for general PbRL problems. We first show that a unique optimal policy may not exist if preferences over trajectories are deterministic for PbRL. If preferences are stochastic, and the p…
Preference-based Reinforcement Learning (PbRL) methods utilize binary feedback from the human in the loop (HiL) over queried trajectory pairs to learn a reward model in an attempt to approximate the human's underlying reward function capturing their preferences. In this work, we investigate the issue of a high degree of variability in the initialized reward models which are sensitive to random seeds of the experiment. This further compounds the issue of degenerate reward functions PbRL methods already suffer from. We propose a data-driven reward initialization method that does not add any addi…
KAIST（韩国科学技术院）；University of Michigan（密歇根大学）；LG AI Research（LG人工智能研究院）；UC Berkeley（加州大学伯克利分校）
Preference-based reinforcement learning (RL) has shown potential for teaching agents to perform the target tasks without a costly, pre-defined reward function by learning the reward with a supervisor's preference between the two agent behaviors. However, preference-based learning often requires a large amount of human feedback, making it difficult to apply this approach to various applications. This data-efficiency problem, on the other hand, has been typically addressed by using unlabeled samples or data augmentation techniques in the context of supervised learning. Motivated by the recent su…
California Institute of Technology（加州理工学院）；Tsinghua University（清华大学）
In preference-based reinforcement learning (RL), an agent interacts with the environment while receiving preferences instead of absolute feedback. While there is increasing research activity in preference-based RL, the design of formal frameworks that admit tractable theoretical analysis remains an open challenge. Building upon ideas from preference-based bandit learning and posterior sampling in RL, we present DUELING POSTERIOR SAMPLING (DPS), which employs preference-based posterior sampling to learn both the system dynamics and the underlying utility function that governs the preference fee…
Preference-based reinforcement learning (RL) algorithms help avoid the pitfalls of hand-crafted reward functions by distilling them from human preference feedback, but they remain impractical due to the burdensome number of labels required from the human, even for relatively simple tasks. In this work, we demonstrate that encoding environment dynamics in the reward function (REED) dramatically reduces the number of preference labels required in state-of-the-art preference-based RL frameworks. We hypothesize that REED-based methods better partition the state-action space and facilitate generali…
LEASE: Offline Preference-based Reinforcement Learning with High Sample Efficiency
State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences（多模态人工智能系统国家重点实验室，中国科学院自动化研究所）；School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）；CASIA-MUST Joint Laboratory of Intelligence Science and Technology, Institute of Systems Engineering, Macau University of Science and Technology（智能科学与技术CASIA-MUST联合实验室，澳门科学理工学院）
RIME: Robust Preference-based Reinforcement Learning with Noisy Preferences
State Key Laboratory of Multimodal Artificial Intelligence Systems, CASIA（中国科学院自动化研究所多模态人工智能系统国家重点实验室）；School of Artificial Intelligence, the University of Chinese Academy of Sciences（中国科学院大学人工智能学院）
A shortcoming of batch reinforcement learning is its requirement for rewards in data, thus not applicable to tasks without reward functions. Existing settings for lack of reward, such as behavioral cloning, rely on optimal demonstrations collected from humans. Unfortunately, extensive expertise is required for ensuring optimality, which hinder the acquisition of large-scale data for complex tasks. This paper addresses the lack of reward in a batch reinforcement learning setting by learning a reward function from preferences. Generating preferences only requires a basic understanding of a task.…
Reinforcement learning (RL) requires access to a reward function that incentivizes the right behavior, but these are notoriously hard to specify for complex tasks. Preference-based RL provides an alternative: learning policies using a teacher's preferences without pre-defined rewards, thus overcoming concerns associated with reward engineering. However, it is difficult to quantify the progress in preference-based RL due to the lack of a commonly adopted benchmark. In this paper, we introduce B-Pref: a benchmark specially designed for preference-based RL. A key challenge with such a benchmark i…
This paper focuses on reinforcement learning (RL) with limited prior knowledge. In the domain of swarm robotics for instance, the expert can hardly design a reward function or demonstrate the target behavior, forbidding the use of both standard RL and inverse reinforcement learning. Although with a limited expertise, the human expert is still often able to emit preferences and rank the agent demonstrations. Earlier work has presented an iterative preference-based RL framework: expert preferences are exploited to learn an approximate policy return, thus enabling the agent to achieve direct poli…
Learning in Context, Guided by Choice: A Reward-Free Paradigm for Reinforcement Learning with Transformers
Department of Electrical and Computer Engineering, Duke University, Durham, US（电子工程系，杜克大学，达勒姆，美国）；Department of Computer Science, Duke University, Durham, US（计算机科学系，杜克大学，达勒姆，美国）；Department of Biostatistics and Bioinformatics, Duke University, Durham, US（生物统计学与生物信息学系，杜克大学，达勒姆，美国）；Department of Statistics and Data Science, Yale University, New Haven, US（统计学与数据科学系，耶鲁大学，纽 Haven，美国）
Trust Region Preference Approximation: A simple and stable reinforcement learning algorithm for LLM reasoning
Beijing Jiaotong University（北京交通大学）；Microsoft Research AI for Science（微软研究院科学智能部）；Zhongguancun Academy（中关村学院）；University of Chinese Academy of Sciences（中国科学院大学）
Controllability in preference-conditioned multi-objective reinforcement learning
LTCI, Télécom Paris, Institut Polytechnique de Paris（LTCI，巴黎电信学院，巴黎理工学院）；University of California, Berkeley（加州大学伯克利分校）；TU Delft（代尔夫特理工大学）；The University of Texas at Austin（德克萨斯大学奥斯汀分校）
Massive practical works addressed by Deep Q-network (DQN) algorithm have indicated that stochastic policy, despite its simplicity, is the most frequently used exploration approach. However, most existing stochastic exploration approaches either explore new actions heuristically regardless of Q-values or inevitably introduce bias into the learning process to couple the sampling with Q-values. In this paper, we propose a novel preference-guided $ε$-greedy exploration algorithm that can efficiently learn the action distribution in line with the landscape of Q-values for DQN without introducing ad…
University of California, Los Angeles（加州大学洛杉矶分校）；Institute for AI Industry Research, Tsinghua University（清华大学人工智能产业研究院）；Helixon Ltd.（Helixon有限公司）；University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；Institute for Artificial Intelligence, Peking University（北京大学人工智能研究院）；Beijing Institute for General Artificial Intelligence（北京通用人工智能研究院）
Learning new task-specific skills from a few trials is a fundamental challenge for artificial intelligence. Meta reinforcement learning (meta-RL) tackles this problem by learning transferable policies that support few-shot adaptation to unseen tasks. Despite recent advances in meta-RL, most existing methods require the access to the environmental reward function of new tasks to infer the task objective, which is not realistic in many practical applications. To bridge this gap, we study the problem of few-shot adaptation in the context of human-in-the-loop reinforcement learning. We develop a m…
