Programming backgammon using self-teaching neural nets

DOI10.1016/S0004-3702(01)00110-2MaRDI QIDQ5958206zbMATH OpenOpenAlexWikidataFDO

Authors 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

Backgammondoubling strategygamesneural networksreinforcement learningrolloutstemporal difference learning

Mathematics Subject Classification ID

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

Recommendations

• scientific article; zbMATH DE number 1784983
• scientific article; zbMATH DE number 1759682
• A parallel network that learns to play backgammon
• Co-evolution in the successful learning of backgommon strategy
• Comments on ``co-evolution in the successful learning of backgammon strategy

Cites work

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

Cited in

(15)

• A parallel network that learns to play backgammon
• Co-evolution in the successful learning of backgommon strategy
• Comments on ``co-evolution in the successful learning of backgammon strategy
• Preference-based reinforcement learning: a formal framework and a policy iteration algorithm
• Backgammon is hard
• Application of reinforcement learning to the game of Othello
• General game playing with stochastic CSP
• PLAYER CO-MODELLING IN A STRATEGY BOARD GAME: DISCOVERING HOW TO PLAY FAST
• scientific article; zbMATH DE number 1784983 (Why is no real title available?)
• Abstraction from demonstration for efficient reinforcement learning in high-dimensional domains
• Artificial Intelligence and Soft Computing - ICAISC 2004
• OUTCOME UNCERTAINTY AND INTERESTEDNESS IN GAME-PLAYING: A CASE STUDY USING SYNCHRONIZED HEX
• The challenge of poker
• Similarity Suppresses Cyclicity: Why Similar Competitors Form Hierarchies
• The stochastic and dynamic inventory routing problem with fine time granularity: a reinforcement learning approach

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

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5958206)