185 citations · 757 across the 15 of their papers we have counts for
15 papers
Evolutionary Reinforcement Learning for Sample-Efficient Multiagent Coordination
Shauharda Khadka, Somdeb Majumdar, Santiago Miret +2
Many cooperative multiagent reinforcement learning environments provide agents with a sparse team-based reward, as well as a dense agent-specific reward that incentivizes learning…
Collaborative Evolutionary Reinforcement Learning
Shauharda Khadka, Somdeb Majumdar, Tarek Nassar +5
Deep reinforcement learning algorithms have been successfully applied to a range of challenging control tasks. However, these methods typically struggle with achieving effective ex…
Evolution-Guided Policy Gradient in Reinforcement Learning
Shauharda Khadka, Kagan Tumer
Deep Reinforcement Learning (DRL) algorithms have been successfully applied to a range of challenging control tasks. However, these methods typically suffer from three core difficu…
Collective Intelligence, Data Routing and Braess' Paradox
K. Tumer, D. H. Wolpert
We consider the problem of designing the the utility functions of the utility-maximizing agents in a multi-agent system so that they work synergistically to maximize a global utili…
Improving Search Algorithms by Using Intelligent Coordinates
David Wolpert, Kagan Tumer, Esfandiar Bandari
We consider the problem of designing a set of computational agents so that as they all pursue their self-interests a global function G of the collective system is optimized. Three…
Collectives for the Optimal Combination of Imperfect Objects
Kagan Tumer, David Wolpert
In this letter we summarize some recent theoretical work on the design of collectives, i.e., of systems containing many agents, each of which can be viewed as trying to maximize an…