no code implementations • 31 May 2022 • Yiwei Fu, Dheeraj S. K. Kapilavai, Elliot Way
Factored decentralized Markov decision process (Dec-MDP) is a framework for modeling sequential decision making problems in multi-agent systems.
no code implementations • 16 Mar 2022 • Elliot Way, Dheeraj S. K. Kapilavai, Yiwei Fu, Lei Yu
We introduce Backpropagation Through Time and Space (BPTTS), a method for training a recurrent spatio-temporal neural network, that is used in a homogeneous multi-agent reinforcement learning (MARL) setting to learn numerical methods for hyperbolic conservation laws.
Multi-agent Reinforcement Learning reinforcement-learning +1
no code implementations • 10 Feb 2019 • Andrew Cohen, Xingye Qiao, Lei Yu, Elliot Way, Xiangrong Tong
We address the challenge of effective exploration while maintaining good performance in policy gradient methods.