A pattern classification approach to evaluation function learning

Lee, Kai-Fu; Mahajan, Sanjoy

doi:10.1016/0004-3702(88)90076-8

Cited by 60 publications

(18 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A direct comparison of learning the reduced set of 10 weights compared with learning the full 64 weights would be interesting future work. The first strong learning Othello program developed was Bill [6], [7]. Later, the first program to beat a human champion was Logistello [2], the best Othello program from 1993-1997.…”

Section: Othellomentioning

confidence: 99%

Temporal Difference Learning Versus Co-Evolution for Acquiring Othello Position Evaluation

Lucas

Rúnarsson

2006

2006 IEEE Symposium on Computational Intelligence and Games

View full text Add to dashboard Cite

Abstract-This paper compares the use of temporal difference learning (TDL) versus co-evolutionary learning (CEL) for acquiring position evaluation functions for the game of Othello. The paper provides important insights into the strengths and weaknesses of each approach. The main findings are that for Othello, TDL learns much faster than CEL, but that properly tuned CEL can learn better playing strategies. For CEL, it is essential to use parent-child weighted averaging in order to achieve good performance. Using this method a high quality weighted piece counter was evolved, and was shown to significantly outperform a set of standard heuristic weights.

show abstract

Section: Othellomentioning

confidence: 99%

Temporal Difference Learning Versus Co-Evolution for Acquiring Othello Position Evaluation

Lucas

Rúnarsson

2006

2006 IEEE Symposium on Computational Intelligence and Games

View full text Add to dashboard Cite

show abstract

“…There currently seems to be very little theoretical research that can help us here, and a great need for empirical investigation. The first strong learning Othello program developed was Bill [29,30] . Later, the first program to beat a human champion was Buro and Logistello [31] , the best Othello program from 1993-1997.…”

Section: Tdl Versus Evolution For Simulated Car Racingmentioning

confidence: 99%

Computational intelligence and games: Challenges and opportunities

Lucas

2008

Int. J. Autom. Comput.

View full text Add to dashboard Cite

The last few decades have seen a phenomenal increase in the quality, diversity and pervasiveness of computer games. The worldwide computer games market is estimated to be worth around USD 21bn annually, and is predicted to continue to grow rapidly. This paper reviews some of the recent developments in applying computational intelligence (CI) methods to games, points out some of the potential pitfalls, and suggests some fruitful directions for future research.

show abstract

“…The first strong learning Othello program developed was Bill [3], [4]. Later, the first program to beat a human champion was Logistello [2], the best Othello program from 1993-1997.…”

Section: Othellomentioning

confidence: 99%

Effect of look-ahead search depth in learning position evaluation functions for Othello using -greedy exploration

Rúnarsson

Jonsson

2007

2007 IEEE Symposium on Computational Intelligence and Games

View full text Add to dashboard Cite

Abstract-This paper studies the effect of varying the depth of look-ahead for heuristic search in temporal difference (TD) learning and game playing. The acquisition position evaluation functions for the game of Othello is studied. The paper provides important insights into the strengths and weaknesses of using different search depths during learning when -greedy exploration is applied. The main findings are that contrary to popular belief, for Othello, better playing strategies are found when TD learning is applied with lower look-ahead search depths.

show abstract

A pattern classification approach to evaluation function learning

Cited by 60 publications

References 8 publications

Temporal Difference Learning Versus Co-Evolution for Acquiring Othello Position Evaluation

Temporal Difference Learning Versus Co-Evolution for Acquiring Othello Position Evaluation

Computational intelligence and games: Challenges and opportunities

Effect of look-ahead search depth in learning position evaluation functions for Othello using -greedy exploration

Contact Info

Product

Resources

About