activity
20192022
most citedQTRAN: Learning to Factorize with Transformation for Cooperative Multi-Agent Reinforcement Learning

220 citations · 298 across the 4 of their papers we have counts for

collaborators

6 papers

cs.AI20223 cited

Curiosity-Driven Multi-Agent Exploration with Mixed Objectives

Roben Delos Reyes, Kyunghwan Son, Jinhwan Jung +2

Intrinsic rewards have been increasingly used to mitigate the sparse reward problem in single-agent reinforcement learning. These intrinsic rewards encourage the agent to look for…

cs.SI2020

Information Source Finding in Networks: Querying with Budgets

Jaeyoung Choi, Sangwoo Moon, Jiin Woo +3

In this paper, we study a problem of detecting the source of diffused information by querying individuals, given a sample snapshot of the information diffusion graph, where two que…

cs.LG202017 cited

QTRAN++: Improved Value Transformation for Cooperative Multi-Agent Reinforcement Learning

Kyunghwan Son, Sungsoo Ahn, Roben Delos Reyes +2

QTRAN is a multi-agent reinforcement learning (MARL) algorithm capable of learning the largest class of joint-action value functions up to date. However, despite its strong theoret…

cs.LG2019

Solving Continual Combinatorial Selection via Deep Reinforcement Learning

Hyungseok Song, Hyeryung Jang, Hai H. Tran +5

We consider the Markov Decision Process (MDP) of selecting a subset of items at each step, termed the Select-MDP (S-MDP). The large state and action spaces of S-MDPs make them intr…

cs.LG2019220 cited

QTRAN: Learning to Factorize with Transformation for Cooperative Multi-Agent Reinforcement Learning

Kyunghwan Son, Daewoo Kim, Wan Ju Kang +2

We explore value-based solutions for multi-agent reinforcement learning (MARL) tasks in the centralized training with decentralized execution (CTDE) regime popularized recently. Ho…

cs.AI201958 cited

Learning to Schedule Communication in Multi-agent Reinforcement Learning

Daewoo Kim, Sangwoo Moon, David Hostallero +4

Many real-world reinforcement learning tasks require multiple agents to make sequential decisions under the agents' interaction, where well-coordinated actions among the agents are…