The development of a world class Othello program

Lee, Kai-Fu; Mahajan, Sanjoy

doi:10.1016/0004-3702(90)90068-b

Cited by 67 publications

(32 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The programmer selects static features that human experts hold in high regard. The tradeoff between the number of nodes searched and the time devoted to computation at each node is critical for real-time performance, and is well documented in the game-playing literature (Kierulf, 1989;Lee and Mahajan, 1990). Large-scale memory for endgames has resulted in strong play for checkers and nine-men's morris; statistics on the success of each previously encountered state have fared less well (DeJong and Schultz, 1988;Schaeffer, et al, 1991;Schultz and De Jong, 1988).…”

Section: Expert Game Players Human and Machinementioning

confidence: 99%

See 1 more Smart Citation

Pattern‐based Learning and Spatially Oriented Concept Formation in a Multi‐agent, Decision‐making Expert

Epstein

Gelfand

Lesniak

1996

Computational Intelligence

View full text Add to dashboard Cite

As they gain expertise in problem solving, people increasingly rely on patterns and spatially oriented reasoning. This paper describes an associative visual‐pattern classifier and the automated acquisition of new, spatially oriented reasoning agents that simulate such behavior. They are incorporated into a multi‐agent game‐learning program whose architecture robustly combines agents with conflicting perspectives. When tested on three games, the visual‐pattern classifier learns meaningful patterns, and the pattern‐based, spatially oriented agents generalized from these patterns are generally correct. The accuracy of the contribution of each of the newly created agents to the decision‐making process is measured against an expert opponent, and a perceptron‐Iike algorithm is used to learn game‐specific weights for these agents. Much of the knowledge encapsulated by the new agents was previously inexpressible in the program's representation and in some cases is not readily deducible from the rules.

show abstract

Section: Expert Game Players Human and Machinementioning

confidence: 99%

“…"Pure" pattern-oriented programs learn slowly and tend to be unreliable (Boyan, 1992;Michie, 1974;Painter, 1993). Nonetheless, many important game-playing programs have had strong, visually-oriented features in their evaluation functions (Kierulf, 1989;Lee and Mahajan, 1990;Samuel, 1963;Samuel, 1967).…”

Section: Pattern-oriented Playmentioning

confidence: 99%

Pattern‐based Learning and Spatially Oriented Concept Formation in a Multi‐agent, Decision‐making Expert

Epstein

Gelfand

Lesniak

1996

Computational Intelligence

View full text Add to dashboard Cite

show abstract

“…Such decisions can establish better play by effectively hiding bad states from the minimax search. Using the powerful evaluation function from Bill [Lee & Mahajan, 1990], the SANE network was able to generate better play while examining 33% fewer board positions than a normal, full-width minimax search using the same evaluation function.…”

Section: Extending Sanementioning

confidence: 99%

Efficient reinforcement learning through symbiotic evolution

1996

View full text Add to dashboard Cite

Abstract.This article presents a new reinforcement learning method called SANE (Symbiotic, Adaptive Neuro-Evolution), which evolves a population of neurons through genetic algorithms to form a neural network capable of performing a task. Symbiotic evolution promotes both cooperation and specialization, which results in a fast, efficient genetic search and discourages convergence to suboptimal solutions. In the inverted pendulum problem, SANE formed effective networks 9 to 16 times faster than the Adaptive Heuristic Critic and 2 times faster than Q-learning and the GENITOR neuro-evolution approach without loss of generalization. Such efficient learning, combined with few domain assumptions, make SANE a promising approach to a broad range of reinforcement learning problems, including many real-world applications.

show abstract

“…Reversi, also known as Othello, is a popular game with a rich research history [1,10,24,27]. The most popular Reversi variant is a board game played on an 8x8 board.…”

Section: Reversimentioning

confidence: 99%

EvoMCTS: Enhancing MCTS-based players through genetic programming

Benbassat

Sipper

2013

2013 IEEE Conference on Computational Inteligence in Games (CIG)

View full text Add to dashboard Cite

Abstract-We present EvoMCTS, a genetic programming method for enhancing level of play in games. Our work focuses on the zero-sum, deterministic, perfect-information board game of Reversi. Expanding on our previous work on evolving board-state evaluation functions for alpha-beta search algorithm variants, we now evolve evaluation functions that augment the MTCS algorithm. We use strongly typed genetic programming, explicitly defined introns, and a selective directional crossover method. Our system regularly evolves players that outperform MCTS players that use the same amount of search. Our results prove scalable and EvoMCTS players whose search is increased offline still outperform MCTS counterparts. To demonstrate the generality of our method we apply EvoMCTS successfully to the game of Dodgem.

show abstract

The development of a world class Othello program

Cited by 67 publications

References 5 publications

Pattern‐based Learning and Spatially Oriented Concept Formation in a Multi‐agent, Decision‐making Expert

Pattern‐based Learning and Spatially Oriented Concept Formation in a Multi‐agent, Decision‐making Expert

Efficient reinforcement learning through symbiotic evolution

EvoMCTS: Enhancing MCTS-based players through genetic programming

Contact Info

Product

Resources

About