LEMUR: Learning to Align with Multi-Objective Reinforcement Learning from Preference Feedback

• URL: http://arxiv.org/abs/2607.29559v1
• Date: Fri, 31 Jul 2026 15:50:29 GMT
• Title: LEMUR: Learning to Align with Multi-Objective Reinforcement Learning from Preference Feedback
• Abstract summary: We present LEMUR: Learning to Align with Multi-Objective Reinforcement Learning with Preference feedback.<n>It is a novel framework where an agent interactively learns from the preferences of multiple humans to learn optimal multi-objective policies.<n>Our approach jointly learns policies and multiple objective-specific reward models from human feedback, enabling agents to effectively balance competing objectives.
• Score: 4.210862582629798
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Reinforcement Learning (RL) systems are typically trained using a single, well-specified scalar reward function. However, real-world decision-making tasks often involve multiple, competing objectives, such as performance versus efficiency, where ground-truth reward functions are difficult to specify or inaccessible. While Multi-Objective RL (MORL) addresses such trade-offs by modeling rewards as vectors, existing approaches typically assume access to a well-specified reward function for each objective, inheriting the same challenges faced by single-objective RL. Meanwhile, Preference-based RL (PbRL) has shown great potential in solving complex tasks without access to a pre-defined reward function through reward learning from human feedback, yet has largely been studied in single-objective settings. In this work, we bridge this gap with LEMUR: Learning to Align with Multi-Objective Reinforcement Learning with Preference feedback, a novel framework where an agent interactively learns from the preferences of multiple humans to learn optimal multi-objective policies. Our approach jointly learns policies and multiple objective-specific reward models from human feedback, enabling agents to effectively balance competing objectives during learning. We evaluate LEMUR on a variety of benchmark multi-objective tasks, and empirical results demonstrate its superior performance over baseline methods. Our method presents a promising direction for solving multi-objective decision-making tasks without pre-defined reward functions.

Related papers

• A Reward-Free Viewpoint on Multi-Objective Reinforcement Learning [19.061803766467627]
  We propose leveraging reward-free reinforcement learning (RFRL) for multi-objective reinforcement learning (MORL)<n>RFRL has historically been studied independently of MORL, making it a natural fit for MORL's challenge of handling unknown user preferences.<n>We show that our approach significantly outperforms the state-of-the-art MORL methods across diverse MO-Gymnasium tasks.
  arXiv  Detail & Related papers  (2026-04-27T14:32:44Z)
• MO-MIX: Multi-Objective Multi-Agent Cooperative Decision-Making With Deep Reinforcement Learning [68.91090643731987]
  Deep reinforcement learning (RL) has been applied extensively to solve complex decision-making problems.<n>Existing approaches are limited to separate fields and can only handle multi-agent decision-making with a single objective.<n>We propose MO-mix to solve the multi-objective multi-agent reinforcement learning (MOMARL) problem.
  arXiv  Detail & Related papers  (2026-02-28T16:25:22Z)
• Balancing Multiple Objectives in Urban Traffic Control with Reinforcement Learning from AI Feedback [14.81819959351561]
  We show that multi-objective RLAIF can produce policies that yield balanced trade-offs reflecting different user priorities without laborious reward engineering.<n>We argue that integrating RLAIF into multi-objective RL offers a scalable path toward user-aligned policy learning.
  arXiv  Detail & Related papers  (2026-02-24T09:47:25Z)
• EMORL: Ensemble Multi-Objective Reinforcement Learning for Efficient and Flexible LLM Fine-Tuning [6.675088737484839]
  We introduce an Ensemble Multi-Objective RL (EMORL) framework that fine-tunes multiple models with individual objectives to improve efficiency and flexibility.<n>Our method is the first to aggregate the hidden states of individual models, incorporating contextual information from multiple objectives.<n>We demonstrate the advantages of EMORL against existing baselines in experiments on the PAIR and Psych8k datasets.
  arXiv  Detail & Related papers  (2025-05-05T11:30:46Z)
• From Novice to Expert: LLM Agent Policy Optimization via Step-wise Reinforcement Learning [62.54484062185869]
  We introduce StepAgent, which utilizes step-wise reward to optimize the agent's reinforcement learning process.<n>We propose implicit-reward and inverse reinforcement learning techniques to facilitate agent reflection and policy adjustment.
  arXiv  Detail & Related papers  (2024-11-06T10:35:11Z)
• UCB-driven Utility Function Search for Multi-objective Reinforcement Learning [51.00436121587591]
  In Multi-objective Reinforcement Learning (MORL) agents are tasked with optimising decision-making behaviours.<n>We focus on the case of linear utility functions parametrised by weight vectors w.<n>We introduce a method based on Upper Confidence Bound to efficiently search for the most promising weight vectors during different stages of the learning process.
  arXiv  Detail & Related papers  (2024-05-01T09:34:42Z)
• MORL-Prompt: An Empirical Analysis of Multi-Objective Reinforcement Learning for Discrete Prompt Optimization [45.410121761165634]
  RL-based techniques can be employed to search for prompts that, when fed into a target language model, maximize a set of user-specified reward functions. Current techniques focus on maximizing the average of reward functions, which does not necessarily lead to prompts that achieve balance across rewards.
  arXiv  Detail & Related papers  (2024-02-18T21:25:09Z)
• Utility-Based Reinforcement Learning: Unifying Single-objective and Multi-objective Reinforcement Learning [3.292607871053364]
  We extend the utility-based paradigm to the context of single-objective reinforcement learning (RL) We outline multiple potential benefits including the ability to perform multi-policy learning across tasks relating to uncertain objectives, risk-aware RL, discounting, and safe RL. We also examine the algorithmic implications of adopting a utility-based approach.
  arXiv  Detail & Related papers  (2024-02-05T01:42:28Z)
• MORAL: Aligning AI with Human Norms through Multi-Objective Reinforced Active Learning [14.06682547001011]
  State-of-the art methods typically focus on learning a single reward model. We propose Multi-Objective Reinforced Active Learning (MORAL), a novel method for combining diverse demonstrations of social norms. Our approach is able to interactively tune a deep RL agent towards a variety of preferences, while eliminating the need for computing multiple policies.
  arXiv  Detail & Related papers  (2021-12-30T19:21:03Z)
• Information Directed Reward Learning for Reinforcement Learning [64.33774245655401]
  We learn a model of the reward function that allows standard RL algorithms to achieve high expected return with as few expert queries as possible. In contrast to prior active reward learning methods designed for specific types of queries, IDRL naturally accommodates different query types. We support our findings with extensive evaluations in multiple environments and with different types of queries.
  arXiv  Detail & Related papers  (2021-02-24T18:46:42Z)
• Provable Multi-Objective Reinforcement Learning with Generative Models [98.19879408649848]
  We study the problem of single policy MORL, which learns an optimal policy given the preference of objectives. Existing methods require strong assumptions such as exact knowledge of the multi-objective decision process. We propose a new algorithm called model-based envelop value (EVI) which generalizes the enveloped multi-objective $Q$-learning algorithm.
  arXiv  Detail & Related papers  (2020-11-19T22:35:31Z)
• Task-Feature Collaborative Learning with Application to Personalized Attribute Prediction [166.87111665908333]
  We propose a novel multi-task learning method called Task-Feature Collaborative Learning (TFCL) Specifically, we first propose a base model with a heterogeneous block-diagonal structure regularizer to leverage the collaborative grouping of features and tasks. As a practical extension, we extend the base model by allowing overlapping features and differentiating the hard tasks.
  arXiv  Detail & Related papers  (2020-04-29T02:32:04Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.