activity
20182022
collaborators

7 papers

cs.GT2022

Game-Theoretical Perspectives on Active Equilibria: A Preferred Solution Concept over Nash Equilibria

Dong-Ki Kim, Matthew Riemer, Miao Liu +3

Multiagent learning settings are inherently more difficult than single-agent learning because each agent interacts with other simultaneously learning agents in a shared environment…

cs.RO2021

Demonstration-Efficient Guided Policy Search via Imitation of Robust Tube MPC

Andrea Tagliabue, Dong-Ki Kim, Michael Everett +1

We propose a demonstration-efficient strategy to compress a computationally expensive Model Predictive Controller (MPC) into a more computationally efficient representation based o…

cs.LG2021

ROMAX: Certifiably Robust Deep Multiagent Reinforcement Learning via Convex Relaxation

Chuangchuang Sun, Dong-Ki Kim, Jonathan P. How

In a multirobot system, a number of cyber-physical attacks (e.g., communication hijack, observation perturbations) can challenge the robustness of agents. This robustness issue wor…

cs.LG2020

A Policy Gradient Algorithm for Learning to Learn in Multiagent Reinforcement Learning

Dong-Ki Kim, Miao Liu, Matthew Riemer +6

A fundamental challenge in multiagent reinforcement learning is to learn beneficial behaviors in a shared environment with other simultaneously learning agents. In particular, each…

cs.LG2019

Policy Distillation and Value Matching in Multiagent Reinforcement Learning

Samir Wadhwania, Dong-Ki Kim, Shayegan Omidshafiei +1

Multiagent reinforcement learning algorithms (MARL) have been demonstrated on complex tasks that require the coordination of a team of multiple agents to complete. Existing works h…

cs.LG2019

Learning Hierarchical Teaching Policies for Cooperative Agents

Dong-Ki Kim, Miao Liu, Shayegan Omidshafiei +7

Collective learning can be greatly enhanced when agents effectively exchange knowledge with their peers. In particular, recent work studying agents that learn to teach other teamma…