arXiv Machine Learning September 3, 2026 By Antonio Mone, Zuzanna Osika, Florian Felten, Pradeep K. Murukannaiah, Mark Fuge, Frans A. Oliehoek, Luciano Cavalcante Siebert

Objective-Behavior Alignment: Diagnostics for MORL Policy Selection

Read the original on arXiv Machine Learning →

The paper introduces a diagnostic workflow for multi‑objective reinforcement learning (MORL) that reveals behavioral differences among policies on the Pareto front, which are not apparent from value vectors alone. It offers quantitative and visual tools to inspect these variations and demonstrates their effectiveness on both simple grid tasks and more complex continuous‑control benchmarks.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

arXiv AI

Aug 3

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

arXiv:2607. 29559v1 Announce Type: new Abstract: Reinforcement Learning (RL) systems are typically trained using a single, well-specified scalar reward function.

By Manith Adikari, Bei Peng, Samuele Vinanzi, Angelo Cangelosi

agents reinforcement-learning benchmarks

arXiv AI

Aug 3

Don't Mix Rewards, Mix Policies: Policy Decomposition and Optimization for Multi-Reward RL

arXiv:2607. 29246v1 Announce Type: new Abstract: Modern large language models (LLMs) are expected not just to answer correctly, but to adapt their behavior to different human values and use cases.

By Ruiming Liang, Yi Zhong, Yizhen Yuan, Yinan Zheng, Tianyi Tan, Tianyue Wang, Haiyun Guo, Jinqiao Wang, Xianyuan Zhan

llms reinforcement-learning safety

arXiv Machine Learning

Oct 7

MSPR: Multi-scale Predictive Representations for Goal-conditioned Reinforcement Learning

arXiv:2605.09364v2 Announce Type: replace Abstract: This paper investigates robust representation learning in offline goal-conditioned reinforcement learning (GCRL). Particularly in sparse reward sce...

By Valliappan Chidambaram Adaikkappan, Sai Rajeswar, Pietro Mazzaglia, David Meger

diffusion reinforcement-learning benchmarks safety

arXiv AI

Sep 10

A Better Spur Should Start From Each Objective

arXiv:2609.08211v1 Announce Type: new Abstract: Real-world Multi-Objective Reinforcement Learning (MORL) often suffers from sparse rewards, reward conflicts, and late-stage reward tug-of-war, causing...

By Shanwen Mao, Hao Zhang, Guangtao nie, Zhiheng Li, Huimu Wang, Sulong Xu, Gu Simiu

reinforcement-learning safety

arXiv AI

Jul 13

Preference Conditioned Multi-Objective Reinforcement Learning: Decomposed, Diversity-Driven Policy Optimization

arXiv:2602. 07764v2 Announce Type: replace-cross Abstract: Multi-objective reinforcement learning (MORL) seeks to train agents capable of balancing conflicting objectives.

By Tanmay Ambadkar, Sourav Panda, Shreyash Kale, Jonathan Dodge, Abhinav Verma

agents reinforcement-learning benchmarks

arXiv Machine Learning

Oct 28

Preference-Guided Cooperation in Multi-Objective Multi-Agent Reinforcement Learning

The paper introduces Meta-Gradient Informed Multi-Objective Multi-Agent Reinforcement Learning (MIRL), a framework that leverages the structure of multiple objectives to enhance cooperation among agents. By formulating MOMARL at both team and individual levels and using objective-wise counterfactual credit assignment, MIRL allows agents to learn how to prioritize objectives individually while jointly optimizing a system-level objective. Experiments on a multi-objective particle environment demonstrate that MIRL, especially its dynamic variant, improves Pareto-front quality compared to baseline methods.

By Qiyue Xia, J. Michael Herrmann

agents reinforcement-learning

One email a morning, machine-written

Related stories

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

Don't Mix Rewards, Mix Policies: Policy Decomposition and Optimization for Multi-Reward RL

MSPR: Multi-scale Predictive Representations for Goal-conditioned Reinforcement Learning

A Better Spur Should Start From Each Objective

Preference Conditioned Multi-Objective Reinforcement Learning: Decomposed, Diversity-Driven Policy Optimization

Preference-Guided Cooperation in Multi-Objective Multi-Agent Reinforcement Learning