DouRN: Improving DouZero by Residual Neural Networks

arXiv:2403.14102v1 Announce Type: cross
Abstract: Deep reinforcement learning has made significant progress in games with imperfect information, but its performance in the card game Doudizhu (Chinese Poker/Fight the Landlord) remains unsatisfactory. Doudizhu is different from conventional games as it involves three players and combines elements of cooperation and confrontation, resulting in a large state and action space. In 2021, a Doudizhu program called DouZero\cite{zha2021douzero} surpassed previous models without prior knowledge by utilizing traditional Monte Carlo methods and multilayer perceptrons. Building …

arxiv cs.ai cs.lg improving networks neural networks residual type