Computer games 5th Workshop on Computer Games, CGW 2016, and 5th Workshop on General Intelligence in Game-Playing Agents, GIGA 2016, held in conjunction with the 25th International Conference on Artificial Intelligence, IJCAI 2016, New York, USA, July 9-10, 2016, Revised selected papers /
This book constitutes the refereed proceedings of the 5th Computer Games Workshop, CGW 2016, and the 5th Workshop on General Intelligence in Game-Playing Agents, GIGA 2016, held in conjunction with the 25th International Conference on Artificial Intelligence, IJCAI 2016, in New York, USA, in July 20...
| Other Authors: | Workshop on Computer Games, Cazenave, Tristan,, Winands, Mark H. M., 1978-, Edelkamp, Stefan,, Schiffel, Stephan, 1980-, Thielscher, Michael,, Togelius, Julian,, SpringerLink (Online service), Workshop on General Intelligence in Game-Playing Agents, International Joint Conference on Artificial Intelligence |
|---|---|
| Format: | eBook |
| Language: | English |
| Published: |
Cham, Switzerland :
Springer,
2017.
|
| Physical Description: |
1 online resource (xii, 179 pages) : illustrations. |
| Series: |
Communications in computer and information science ;
705. |
| Subjects: |
| Summary: |
This book constitutes the refereed proceedings of the 5th Computer Games Workshop, CGW 2016, and the 5th Workshop on General Intelligence in Game-Playing Agents, GIGA 2016, held in conjunction with the 25th International Conference on Artificial Intelligence, IJCAI 2016, in New York, USA, in July 2016. The 12 revised full papers presented were carefully reviewed and selected from 25 submissions. The papers address all aspects of artificial intelligence and computer game playing. They discuss topics such as Monte-Carlo methods; heuristic search; board games; card games; video games; perfect and imperfect information games; puzzles and single player games; multi-player games; combinatorial game theory; applications; computational creativity; computational game theory; evaluation and analysis; game design; knowledge representation; machine learning; multi-agent systems; opponent modeling; planning. |
|---|---|
| Item Description: |
Includes author index. This book constitutes the refereed proceedings of the 5th Computer Games Workshop, CGW 2016, and the 5th Workshop on General Intelligence in Game-Playing Agents, GIGA 2016, held in conjunction with the 25th International Conference on Artificial Intelligence, IJCAI 2016, in New York, USA, in July 2016. The 12 revised full papers presented were carefully reviewed and selected from 25 submissions. The papers address all aspects of artificial intelligence and computer game playing. They discuss topics such as Monte-Carlo methods; heuristic search; board games; card games; video games; perfect and imperfect information games; puzzles and single player games; multi-player games; combinatorial game theory; applications; computational creativity; computational game theory; evaluation and analysis; game design; knowledge representation; machine learning; multi-agent systems; opponent modeling; planning. Includes bibliographical references and author index. Intro -- Preface -- Computer Games Workshop -- GIGA Workshop -- Organization -- Contents -- Computer Games Workshop 2016 -- NeuroHex: A Deep Q-learning Hex Agent -- 1 Motivation, Introduction, Background -- 1.1 Motivation -- 1.2 The Game of Hex -- 1.3 Related Work -- 1.4 Overview of this Work -- 1.5 Reinforcement Learning -- 1.6 Deep Q-learning -- 2 Method -- 2.1 Problem Structure -- 2.2 State Representation -- 2.3 Model -- 2.4 Position Database -- 2.5 Mentoring -- 2.6 Q-learning Algorithm -- 3 Results -- 4 Discussion and Conclusion -- 5 Future Work -- References. Deep or Wide? Learning Policy and Value Neural Networks for Combinatorial Games -- 1 Introduction -- 2 Case Study: TicTacToe -- 2.1 Automated Generation of Games -- 2.2 Defining the Network -- 2.3 Training the Network -- 2.4 Using the Network -- 3 Case Study: SameGame -- 3.1 Randomized State-Space Search -- 3.2 Generating the Training Data -- 3.3 Defining the Network -- 3.4 Training the Network -- 3.5 Using the Network -- 4 Conclusion -- References -- Integrating Factorization Ranked Features in MCTS: An Experimental Study -- 1 Introduction. 2 Factorization Bradley-Terry Model for Move Prediction Problem -- 3 Integrating FBT Knowledge in MCTS -- 4 Experiments -- 4.1 Feature Knowledge for Move Selection in Fuego -- 4.2 Training Settlement for FBT Model -- 4.3 Setup -- 4.4 Experimental Results -- 5 Conclusion and Future Work -- References -- Nested Rollout Policy Adaptation with Selective Policies -- 1 Introduction -- 2 Related Work -- 3 Selective Policies -- 3.1 Bus Regulation -- 3.2 SameGame -- 3.3 Weak Schur Numbers -- 4 Experimental Results -- 4.1 Bus Regulation -- 4.2 SameGame -- 4.3 Weak Schur Numbers -- 5 Conclusion. 8 RAM Visualization -- 9 Conclusions -- 10 Future Work -- 10.1 Games with More Refined Logic -- 10.2 More Sophisticated Architecture and Better Hyperparameters -- 10.3 Recurrent Neural Networks and Patterns of Memory Usage -- 10.4 Patterns as Finite State Machines -- A Parameters -- References -- Clustering-Based Online Player Modeling -- 1 Introduction -- 2 Related Work -- 3 Application Environment -- 4 Methodology -- 4.1 Individual Player Models -- 4.2 Generate Response -- 5 Environment Considerations -- 5.1 Initial Data Capture Experiment -- 5.2 State Representation. |
| Physical Description: |
1 online resource (xii, 179 pages) : illustrations. |
| Bibliography: |
Includes bibliographical references and author index. |
| ISBN: |
9783319579696 331957969X 3319579681 9783319579689 |
| ISSN: |
1865-0929 ; |