Inducing Cooperation via Learning to reshape rewards in semi-cooperative multi-agent reinforcement learning

no code implementations • ICLR 2019 • David Earl Hostallero, Daewoo Kim, Kyunghwan Son, Yung Yi

Under these semi-cooperative scenarios, popular methods of centralized training with decentralized execution for inducing cooperation and removing the non-stationarity problem do not work well due to lack of a common shared reward as well as inscalability in centralized training.

Multi-agent Reinforcement Learning Reinforcement Learning (RL)

Imitating Graph-Based Planning with Goal-Conditioned Policies

1 code implementation • 20 Mar 2023 • Junsu Kim, Younggyo Seo, Sungsoo Ahn, Kyunghwan Son, Jinwoo Shin

Recently, graph-based planning algorithms have gained much attention to solve goal-conditioned reinforcement learning (RL) tasks: they provide a sequence of subgoals to reach the target-goal, and the agents learn to execute subgoal-conditioned policies.

Reinforcement Learning (RL)

Curiosity-Driven Multi-Agent Exploration with Mixed Objectives

no code implementations • 29 Oct 2022 • Roben Delos Reyes, Kyunghwan Son, Jinhwan Jung, Wan Ju Kang, Yung Yi

First, we develop a two-headed curiosity module that is trained to predict the corresponding agent's next observation in the first head and the next joint observation in the second head.

Disentangling Sources of Risk for Distributional Multi-Agent Reinforcement Learning

no code implementations • 29 Sep 2021 • Kyunghwan Son, Junsu Kim, Yung Yi, Jinwoo Shin

Although these two sources are both important factors for learning robust policies of agents, prior works do not separate them or deal with only a single risk source, which could lead to suboptimal equilibria.

Multi-agent Reinforcement Learning reinforcement-learning +3

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

no code implementations • 22 Jun 2020 • Kyunghwan Son, Sung-Soo Ahn, Roben Delos Reyes, Jinwoo Shin, Yung Yi

QTRAN is a multi-agent reinforcement learning (MARL) algorithm capable of learning the largest class of joint-action value functions up to date.

reinforcement-learning Reinforcement Learning (RL) +2

Solving Continual Combinatorial Selection via Deep Reinforcement Learning

no code implementations • 9 Sep 2019 • Hyungseok Song, Hyeryung Jang, Hai H. Tran, Se-eun Yoon, Kyunghwan Son, Donggyu Yun, Hyoju Chung, Yung Yi

IS-MDP decomposes a joint action of selecting K items simultaneously into K iterative selections resulting in the decrease of actions at the expense of an exponential increase of states.

reinforcement-learning Reinforcement Learning (RL)

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

3 code implementations • 14 May 2019 • Kyunghwan Son, Daewoo Kim, Wan Ju Kang, David Earl Hostallero, Yung Yi

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

Multi-agent Reinforcement Learning reinforcement-learning +2

Learning to Schedule Communication in Multi-agent Reinforcement Learning

1 code implementation • ICLR 2019 • Daewoo Kim, Sangwoo Moon, David Hostallero, Wan Ju Kang, Taeyoung Lee, Kyunghwan Son, Yung Yi

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 crucial to achieve the target goal better at these tasks.

Multi-agent Reinforcement Learning reinforcement-learning +2