Programming backgammon using self-teaching neural nets

DOI10.1016/S0004-3702(01)00110-2zbMath0982.68124OpenAlexW2014932765WikidataQ55889054 ScholiaQ55889054MaRDI QIDQ5958206

Gerald Tesauro

Publication date: 3 March 2002

Published in: Artificial Intelligence (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/s0004-3702(01)00110-2

zbMATH Keywords

neural networksreinforcement learninggamesBackgammondoubling strategyrolloutstemporal difference learning

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Game theory (91A99) Problem solving in the context of artificial intelligence (heuristics, search strategies, etc.) (68T20)

Related Items (9)

General game playing with stochastic CSP ⋮ Backgammon is hard ⋮ Similarity Suppresses Cyclicity: Why Similar Competitors Form Hierarchies ⋮ Preference-based reinforcement learning: a formal framework and a policy iteration algorithm ⋮ Abstraction from demonstration for efficient reinforcement learning in high-dimensional domains ⋮ Application of reinforcement learning to the game of Othello ⋮ The challenge of poker ⋮ PLAYER CO-MODELLING IN A STRATEGY BOARD GAME: DISCOVERING HOW TO PLAY FAST ⋮ OUTCOME UNCERTAINTY AND INTERESTEDNESS IN GAME-PLAYING: A CASE STUDY USING SYNCHRONIZED HEX

Cites Work

• Co-evolution in the successful learning of backgommon strategy
• Multilayer feedforward networks are universal approximators
• Practical issues in temporal difference learning
• Optimal Doubling in Backgammon
• On Optimal Doubling in Backgammon

This page was built for publication: Programming backgammon using self-teaching neural nets