Multi-agent reinforcement learning: A selective overview of theories and algorithms
Recent years have witnessed significant advances in reinforcement learning (RL), which
has registered tremendous success in solving various sequential decision-making problems …
has registered tremendous success in solving various sequential decision-making problems …
Computer‐assisted synthetic planning: the end of the beginning
S Szymkuć, EP Gajewska, T Klucznik… - Angewandte Chemie …, 2016 - Wiley Online Library
Exactly half a century has passed since the launch of the first documented research project
(1965 Dendral) on computer‐assisted organic synthesis. Many more programs were created …
(1965 Dendral) on computer‐assisted organic synthesis. Many more programs were created …
Mastering chess and shogi by self-play with a general reinforcement learning algorithm
The game of chess is the most widely-studied domain in the history of artificial intelligence.
The strongest programs are based on a combination of sophisticated search techniques …
The strongest programs are based on a combination of sophisticated search techniques …
A general reinforcement learning algorithm that masters chess, shogi, and Go through self-play
The game of chess is the longest-studied domain in the history of artificial intelligence. The
strongest programs are based on a combination of sophisticated search techniques, domain …
strongest programs are based on a combination of sophisticated search techniques, domain …
Deepstack: Expert-level artificial intelligence in heads-up no-limit poker
Artificial intelligence has seen several breakthroughs in recent years, with games often
serving as milestones. A common feature of these games is that players have perfect …
serving as milestones. A common feature of these games is that players have perfect …
Heads-up limit hold'em poker is solved
Poker is a family of games that exhibit imperfect information, where players do not have full
knowledge of past events. Whereas many perfect-information games have been solved (eg …
knowledge of past events. Whereas many perfect-information games have been solved (eg …
Mastering the game of Go with deep neural networks and tree search
The game of Go has long been viewed as the most challenging of classic games for artificial
intelligence owing to its enormous search space and the difficulty of evaluating board …
intelligence owing to its enormous search space and the difficulty of evaluating board …
Efficient selectivity and backup operators in Monte-Carlo tree search
R Coulom - International conference on computers and games, 2006 - Springer
A Monte-Carlo evaluation consists in estimating a position by averaging the outcome of
several random continuations. The method can serve as an evaluation function at the leaves …
several random continuations. The method can serve as an evaluation function at the leaves …
Adversarial policies beat superhuman go AIs
We attack the state-of-the-art Go-playing AI system KataGo by training adversarial policies
against it, achieving a $> $97% win rate against KataGo running at superhuman settings …
against it, achieving a $> $97% win rate against KataGo running at superhuman settings …
Born to learn: the inspiration, progress, and future of evolved plastic artificial neural networks
Biological neural networks are systems of extraordinary computational capabilities shaped
by evolution, development, and lifelong learning. The interplay of these elements leads to …
by evolution, development, and lifelong learning. The interplay of these elements leads to …