Enregistré dans:
Détails bibliographiques
Auteurs principaux: Aydeniz, Ayhan Alp, Loftin, Robert, Tumer, Kagan
Format: Preprint
Publié: 2026
Sujets:
Accès en ligne:https://arxiv.org/abs/2602.11740
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866911442606751744
author Aydeniz, Ayhan Alp
Loftin, Robert
Tumer, Kagan
author_facet Aydeniz, Ayhan Alp
Loftin, Robert
Tumer, Kagan
contents Efficient exploration is critical for multiagent systems to discover coordinated strategies, particularly in open-ended domains such as search and rescue or planetary surveying. However, when exploration is encouraged only at the individual agent level, it often leads to redundancy, as agents act without awareness of how their teammates are exploring. In this work, we introduce Counterfactual Conditional Likelihood (CCL) rewards, which score each agent's exploration by isolating its unique contribution to team exploration. Unlike prior methods that reward agents solely for the novelty of their individual observations, CCL emphasizes observations that are informative with respect to the joint exploration of the team. Experiments in continuous multiagent domains show that CCL rewards accelerate learning for domains with sparse team rewards, where most joint actions yield zero rewards, and are particularly effective in tasks that require tight coordination among agents.
format Preprint
id arxiv_https___arxiv_org_abs_2602_11740
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Counterfactual Conditional Likelihood Rewards for Multiagent Exploration
Aydeniz, Ayhan Alp
Loftin, Robert
Tumer, Kagan
Multiagent Systems
Robotics
Efficient exploration is critical for multiagent systems to discover coordinated strategies, particularly in open-ended domains such as search and rescue or planetary surveying. However, when exploration is encouraged only at the individual agent level, it often leads to redundancy, as agents act without awareness of how their teammates are exploring. In this work, we introduce Counterfactual Conditional Likelihood (CCL) rewards, which score each agent's exploration by isolating its unique contribution to team exploration. Unlike prior methods that reward agents solely for the novelty of their individual observations, CCL emphasizes observations that are informative with respect to the joint exploration of the team. Experiments in continuous multiagent domains show that CCL rewards accelerate learning for domains with sparse team rewards, where most joint actions yield zero rewards, and are particularly effective in tasks that require tight coordination among agents.
title Counterfactual Conditional Likelihood Rewards for Multiagent Exploration
topic Multiagent Systems
Robotics
url https://arxiv.org/abs/2602.11740