Advances in Computer Games : 15th International Conferences, ACG 2017, Leiden, the Netherlands, July 3-5, 2017 : revised selected papers / Mark H.M. Winands, H. Jaap van den Herik, Walter A. Kosters, editors.

This book constitutes the refereed conference proceedings of the 15th International Conference, ACG 2017, held in Leiden, The Netherlands, in July 2017. The 19 revised full papers were selected from 23 submissions and cover a wide range of computer games. They are grouped in four classes according to the order of publication: games and puzzles, go and chess, machine learning and MCTS, and gaming.

Analytical Solution for EinStein würfelt nicht!" with One Stone -- Toward Solving EinStein würfelt nicht! -- Analysis of Fred Horn's Gloop Puzzle -- Set Matching: An Enhancement of the Hales-Jewett Pairing Strategy Playing Hanabi Near-Optimally Optimal Play of the Farkle Dice Game -- Deep df-pn and its Efficient Implementations -- Improved Policy Networks for Computer Go -- Exploring Positional Linear Go -- Influence of Search Depth on Position Evaluation -- Evaluating Chess-like Games Using Generated Natural Language Descriptions -- Machine Learning in the Game of Breakthrough -- A Curling Agent Based on the Monte-Carlo Tree Search Considering the Similarity of the Best Action among Similar States -- Exploration Bonuses Based on Upper Confidence Bounds for Sparse Developing a 2048 Player with Backward Temporal Coherence Learning and Restart -- A Little Bit of Frustration Can Go a Long Way -- Automated Adaptation and Assessment in Serious Games: A Portable Tool for Supporting Learning -- An Analysis of Majority Voting in Homogeneous Groups for Checkers: Understanding Group Performance through Unbalance -- Yasol: An Open Source Solver for Quantified Mixed Integer Programs.

Analytical Solution for "EinStein würfelt nicht!" with One Stone -- Toward Solving EinStein würfelt nicht! -- Analysis of Fred Horn's Gloop Puzzle -- Set Matching: An Enhancement of the Hales-Jewett Pairing Strategy Playing Hanabi Near-Optimally Optimal Play of the Farkle Dice GameDeep df-pn and its Efficient Implementations -- Improved Policy Networks for Computer Go -- Exploring Positional Linear Go -- Influence of Search Depth on Position Evaluation -- Evaluating Chess-like Games Using Generated Natural Language Descriptions -- Machine Learning in the Game of Breakthrough -- A Curling Agent Based on the Monte-Carlo Tree Search Considering the Similarity of the Best Action among Similar States -- Exploration Bonuses Based on Upper Confidence Bounds for Sparse Developing a 2048 Player with Backward Temporal Coherence Learning and Restart -- A Little Bit of Frustration Can Go a Long Way -- Automated Adaptation and Assessment in Serious Games: A Portable Tool for Supporting Learning -- An Analysis of Majority Voting in Homogeneous Groups for Checkers: Understanding Group Performance through Unbalance -- Yasol: An Open Source Solver for Quantified Mixed Integer Programs.