2 results found Sort:

MarcoMeter
endless-memory-gym MarcoMeter
2
86
mit
5
Challenging Memory-based Deep Reinforcement Learning Agents
gru lstm trxl gtrxl pomdp benchmark recurrence transformer transformer-xl gym-environment imperfect-information deep-reinforcement-learning
Created 2022-07-05
105 commits to main branch, last one 24 days ago
masterai-top
MasterAI-2.0-1vs1-NoLimit masterai-top
9
35
unknown
3
MasterAI is an AI poker dedicated to suport n-play (single- or multi-agent) Texas Hold'em imperfect-informatin games.。MasterAI v2.0是从MasterAI v1.0衍生出来的迭代算法，它在非完全信息游戏中利用了通用的强化学习+搜索，并在一对一无限押注的德州扑克中实现了超人...
cfr cmu dqn gto 1vs1 hunl mcmc mcts unlimit deepmind libratus pluribus poker-ai deepstack deep-learning neural-networks machine-learning perfect-information imperfect-information reinforcement-learning
Created 2021-09-22
9 commits to main branch, last one 10 hours ago