Knowledge-Free and Learning-Based Methods in Intelligent Game PlayingHumans and machines are very di?erent in their approaches to game pl- ing. Humans use intuition, perception mechanisms, selective search, creat- ity, abstraction, heuristic abilities and other cognitive skills to compensate their (comparably) slow information processing speed, relatively low m- ory capacity, and limited search abilities. Machines, on the other hand, are extremely fast and infallible in calculations, capable of e?ective brute-for- type search, use “unlimited” memory resources, but at the same time are poor at using reasoning-based approaches and abstraction-based methods. The above major discrepancies in the human and machine problem solving methods underlined the development of traditional machine game playing as being focused mainly on engineering advances rather than cognitive or psychological developments. In other words, as described by Winkler and F ̈ urnkranz [347, 348] with respect to chess, human and machine axes of game playing development are perpendicular, but the most interesting, most promising, and probably also most di?cult research area lies on the junction between human-compatible knowledge and machine compatible processing.I undoubtedly share this point of view and strongly believe that the future of machine game playing lies in implementation of human-type abilities (- straction,intuition,creativity,selectiveattention,andother)whilestilltaking advantage of intrinsic machine skills. Thebookisfocusedonthedevelopmentsandprospectivechallengingpr- lems in the area of mind gameplaying (i.e. playinggames that require mental skills) using Computational Intelligence (CI) methods, mainly neural n- works, genetic/evolutionary programming and reinforcement learning. |
Contents
Introduction | 1 |
Part l AI Tools and StateoftheArt Accomplishments in Mind Games | 8 |
Part ll CI Methods in Mind Games Towards HumanLike Playing | 51 |
Part lll An Overview of Challenges and Open Problems | 90 |
Part IV Grand Challenges | 181 |
References | 235 |
Other editions - View all
Knowledge-Free and Learning-Based Methods in Intelligent Game Playing Jacek Mandziuk Limited preview - 2010 |
Knowledge-Free and Learning-Based Methods in Intelligent Game Playing Jacek Mandziuk No preview available - 2012 |
Knowledge-Free and Learning-Based Methods in Intelligent Game Playing Jacek Mandziuk No preview available - 2010 |
Common terms and phrases
according achieved agent algorithm allows analysis applied approach Artificial assigned authors bridge calculated cards challenging chapter checkers chess choice combination compared complexity connection considered defined denoted depth described designed different discussed domain effective efficient equal estimation evaluation function evolutionary example experiment exploration first further game playing given goal hand heuristic hidden human idea implementation important individual initial input Intelligence interesting intuitive issues knowledge lead learning machine methods mind minimax modeling move neural network neurons node observation opening opponent opponent’s optimal Othello output particular patterns performed phase pieces players position possible presented probability problem procedure proposed random reasons representation represented respectively scheme selection similar simulations specific square strategy strength strong suit tables task tion tree universal usually various weights winning