Coevolutionary CMA-ES for Knowledge-Free Learning of Game Position Evaluation

Jaśkowski, Wojciech; Szubert, Marcin

doi:10.1109/tciaig.2015.2464711

Cited by 8 publications

(16 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Othello has for a long time been a popular benchmark for computational intelligence methods [29], [35], [5], [25], [26], [42], [40], [28], [16], [30], [18]. All strong Othello-playing programs use a variant of the minimax search [7] with a board evaluation function.…”

Section: Related Workmentioning

confidence: 99%

“…Past research suggested that more can be gained by improving the latter than the former; that is why recently the focus was mostly on training 1 look-ahead (a.k.a. 1-ply) agents using either self-play [26], [18], fixed opponents [20], [16], or expert game databases [30]. Multiple ways of training the agents have been proposed: value-based temporal difference learning [25], [42], [34], (co)evolution [26], [31], [17], [15], and hybrids thereof [39], [40].…”

Section: Related Workmentioning

confidence: 99%

“…A comparison of the state-of-the-art 1-ply players for Othello can be found in [18]. Among the published works, the best 1-ply player to date was obtained by Coevolutionary CMA-ES (covariance matrix adaptation evolution strategies) [18] and systematic n-tuple networks. Among the multi-ply Othello strategies, one of the contemporary leaders is Edax 1 , an open source player that uses tabular value functions, one for each stage of the game.…”

Section: Related Workmentioning

confidence: 99%

“…We consider a suite of thirteen 1-ply players proposed in previous research, gathered and compared in our former study [18]. The suite consists of players with board evaluation functions encoded by weighted piece counter and n-tuple networks, trained by different methods including hand-design, temporal difference learning, evolution, and coevolution (cf.…”

Section: A Experimental Setupmentioning

confidence: 99%

“…To this aim, we consider learning CNN-based move predictors for the game of Othello, a long-standing benchmark for AI [18]. This problem not only diverges from Go, but is also very different from analysis of images in computer vision: the input rasters are tiny (8 × 8 ternary board states), free from noise and distortions typical for real-world settings (sensor noise, lighting, perspective, etc.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Learning to Play Othello With Deep Neural Networks

2018

Self Cite

View full text Add to dashboard Cite

Abstract-Achieving superhuman playing level by AlphaGo corroborated the capabilities of convolutional neural architectures (CNNs) for capturing complex spatial patterns. This result was to a great extent due to several analogies between Go board states and 2D images CNNs have been designed for, in particular translational invariance and a relatively large board. In this paper, we verify whether CNN-based move predictors prove effective for Othello, a game with significantly different characteristics, including a much smaller board size and complete lack of translational invariance. We compare several CNN architectures and board encodings, augment them with state-of-theart extensions, train on an extensive database of experts' moves, and examine them with respect to move prediction accuracy and playing strength. The empirical evaluation confirms high capabilities of neural move predictors and suggests a strong correlation between prediction accuracy and playing strength. The best CNNs not only surpass all other 1-ply Othello players proposed to date but defeat (2-ply) Edax, the best open-source Othello player.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: A Experimental Setupmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Learning to Play Othello With Deep Neural Networks

2018

Self Cite

View full text Add to dashboard Cite

show abstract

Development of a Computer Player for Seejeh (A.K.A Seega, Siga, Kharbga) Board Game with Deep Reinforcement Learning

Aljaafreh

Al-Oudat

2019

Procedia Computer Science

View full text Add to dashboard Cite

Surprising Strategies Obtained by Stochastic Optimization in Partially Observable Games

Cauwet¹,

Teytaud

2018

2018 IEEE Congress on Evolutionary Computation (CEC)

View full text Add to dashboard Cite

This paper studies the optimization of strategies in the context of possibly randomized two players zero-sum games with incomplete information. We compare 5 algorithms for tuning the parameters of strategies over a benchmark of 12 games. A first evolutionary approach consists in designing a highly randomized opponent (called naive opponent) and optimizing the parametric strategy against it; a second one is optimizing iteratively the strategy, i.e. constructing a sequence of strategies starting from the naive one. 2 versions of coevolutions, real and approximate, are also tested as well as a seed method. The coevolution methods were performing well, but results were not stable from one game to another. In spite of its simplicity, the seed method, which can be seen as an extremal version of coevolution, works even when nothing else works. Incidentally, these methods brought out some unexpected strategies for some games, such as Batawaf or the game of War, which seem, at first view, purely random games without any structured actions possible for the players or Guess Who, where a dichotomy between the characters seems to be the most reasonable strategy. All source codes of games are written in Matlab/Octave and are freely available for download.

show abstract

Coevolutionary CMA-ES for Knowledge-Free Learning of Game Position Evaluation

Cited by 8 publications

References 45 publications

Learning to Play Othello With Deep Neural Networks

Learning to Play Othello With Deep Neural Networks

Development of a Computer Player for Seejeh (A.K.A Seega, Siga, Kharbga) Board Game with Deep Reinforcement Learning

Surprising Strategies Obtained by Stochastic Optimization in Partially Observable Games

Contact Info

Product

Resources

About