Woojun Kim       

[CV] [Google scholar] [Github]

Postdoctoral Fellow (Advised by Prof. Katia Sycara)

Advanced Agent-Robotics Technology Lab 

Robotics Institute, School of Computer Science, Carnegie Mellon University

Contact -> woojunk [at] andrew [dot] cmu [dot] edu & kwj123123 [at] gmail [dot] com

Research Interests

My research currently focuses on multi-agent reinforcement learning (MARL). Specifically, I'm interested in developing MARL algorithms that achieve high coordination among multiple agents and consider practical issues such as scalability, robustness, and generalization, and their applications to real-world problems such as autonomous driving and robotics. My research on MARL can be organized into three intertwined thrusts:

(1) Correlated exploration method in MARL; 

(2) Learning to communicate among multiple agents in MARL; and

(3) Development of scalable and robust MARL algorithms.

Besides the research on MARL, I'm also interested in {single-agent, multi-task, offline} reinforcement learning and other broad topics in machine learning such as imitation learning, transfer learning, and active learning.

Recent News

Employment

Education

Publications

(C: conference / P: preprint / W: workshop / U: under-review)

* denotes equal contribution or equal advising


Journal and Conference Publications

[C15] Distributed Multi-robot Source Seeking in Unknown Environments with Unknown Number of Sources  

[C14] Escaping Local Minima: Hybrid Artificial Potential Field with Wall-Follower for Decentralized Multi-Robot Navigation

[C13] Integrating Multi-Robot Adaptive Sampling and Informative Path Planning for Spatiotemporal Natural Environment Prediction

[J2] Performance of Large Language Models on the Korean Dental Licensing Examination: A Comparative Study

[C12] Adaptive Q-Aid for Conditional Supervised Learning in Offline Reinforcement Learning

[C11] ShapeGrasp: Zero-Shot Object Grasping with LLMs via Geometric Decomposition

[C10] Decision ConvFormer: Local Filtering in MetaFormer is Sufficient for Decision Making [pdf] [project]

[C9] Sample-Efficient and Safe Reinforcement Learning via Reset Deep Ensemble Agents [pdf]

[C8] Domain Adaptive Imitation Learning with Visual Observation [pdf]

[C7] LESSON: Learning to Integrate Exploration Strategies for Reinforcement Learning via an Option Framework [pdf] [code]

[C6] An Adaptive Entropy-Regularization Framework for Multi-Agent Reinforcement Learning [pdf]

[C5] Parameter Sharing with Network Pruning for Multi-Agent Deep Reinforcement Learning [pdf]

[C4] A Variational Approach to Mutual Information-Based Coordination for Multi-Agent Reinforcement Learning [pdf]

[J1] Enabling Technologies for AI Empowered 6G Massive Radio Access Networks [pdf]

[C3] MASER: Multi-Agent Reinforcement Learning with Subgoals Generated from Experience Replay Buffer [pdf]

[C2] Communication in Multi-Agent Reinforcement Learning: Intention Sharing [pdf]

[C1] Message-dropout: An Efficient Training Method for Multi-Agent Deep Reinforcement Learning [pdf]



Workshop Papers

[W6] ShapeGrasp: Zero-Shot Object Grasping with LLMs via Geometric Decomposition

[W5] ShapeGrasp: Zero-Shot Object Grasping with LLMs via Geometric Decomposition

[W4] Decision ConvFormer: Local Filtering in MetaFormer is Sufficient for Decision Making

[W3] Off-Policy Multi-Agent Policy Optimization with Multi-Step Counterfactual Advantage Estimation

[W2] An Adaptive Entropy-Regularization Framework for Multi-Agent Reinforcement Learning [pdf]

[W1] A Variational Approach to Mutual Information-Based Coordination for Multi-Agent Reinforcement Learning


Preprint Papers

[P3] OffRIPP: Offline RL-based Informative Path Planning

[P2] DyPNIPP: Predicting Environment Dynamics for RL-based Robust Informative Path Planning

[P1] A Maximum Mutual Information Framework for Multi-Agent Reinforcement Learning [pdf]

Awards & Honors

Invited Talks