Proceedings ArticleDOI
Bridge Bidding with Imperfect Information
Lori L. DeLooze,J. Downey +1 more
- pp 368-373
Reads0
Chats0
TLDR
It is shown that a special form of a neural network, called a self-organizing map (SOM), can be used to effectively bid no trump hands and is an ideal mechanism for modeling the imprecise and ambiguous nature of the game.Abstract:
Multiplayer games with imperfect information, such as Bridge, are especially challenging for game theory researchers. Although several algorithmic techniques have been successfully applied to the card play phase of the game, bidding requires a much different approach. We have shown that a special form of a neural network, called a self-organizing map (SOM), can be used to effectively bid no trump hands. The characteristic boundary that forms between resulting neighboring nodes in a SOM is an ideal mechanism for modeling the imprecise and ambiguous nature of the gameread more
Citations
More filters
Posted Content
Automatic Bridge Bidding Using Deep Reinforcement Learning
Chih-Kuan Yeh,Hsuan-Tien Lin +1 more
TL;DR: In this paper, a deep reinforcement learning model was proposed to learn to bid automatically based on the raw card data for bridge zero-sum games without the aid of human domain knowledge.
Posted Content
Learning to Communicate Implicitly By Actions
TL;DR: This work introduces a novel algorithm: Policy Belief Learning (PBL), which uses a belief module to model the other agent's private information and a policy module to form a distribution over actions informed by the belief module and proposes a novel auxiliary reward which incentivizes one agent to help its partner to make correct inferences about its private information.
Proceedings Article
Contract Bridge Bidding by Learning.
Chun-Yen Ho,Hsuan-Tien Lin +1 more
TL;DR: A novel learning framework to let a computer program learn its own bidding decisions is proposed and it is found that it performs competitively to the champion computer bridge program that mimics human bidding decisions.
Proceedings ArticleDOI
A study on constructing fuzzy systems for high-level decision making in a car racing game
TL;DR: The performance of fuzzy rule-based systems in a car racing domain is examined and the effect of sensory information on the high-level decision making is examined.
Journal ArticleDOI
Automatic Bridge Bidding Using Deep Reinforcement Learning
TL;DR: A flexible and pioneering bridge-bidding system, which can learn either with or without the aid of human domain knowledge, based on a novel deep reinforcement learning model, which extracts sophisticated features and learns to bid automatically based on raw card data.
References
More filters
Book
Self-Organizing Maps
TL;DR: The Self-Organising Map (SOM) algorithm was introduced by the author in 1981 as mentioned in this paper, and many applications form one of the major approaches to the contemporary artificial neural networks field, and new technologies have already been based on it.
Book
Self-Organizing Maps
TL;DR: The mathematical preliminaries, background, basic ideas, and implications are expounded in a clear, well-organized form, accessible without prior expert knowledge, and the contents are handled with theoretical rigor.
Journal ArticleDOI
GIB: imperfect information in a computationally challenging game
TL;DR: GIB, the program being described, involves five separate technical advances: partition search, the practical application of Monte Carlo techniques to realistic problems, a focus on achievable sets to solve problems inherent in the Monte Carlo approach, an extension of alpha-beta pruning from total orders to arbitrary distributive lattices, and the use of squeaky wheel optimization to find approximately optimal solutions to cardplay problems.
Journal ArticleDOI
Uncovering hierarchical structure in data using the growing hierarchical self-organizing map
TL;DR: The main feature of this novel architecture is its capability of growing both in terms of map size as well as in a three-dimensional tree-structure in order to represent the hierarchical structure present in a data collection during an unsupervised training process, which makes it an ideal tool for data analysis and exploration.
Journal Article
A comparison of algorithms for multi-player games
TL;DR: Quantitative results derived from playing max n and the paranoid algorithm against each other on various multi-player game domains are presented, showing that paranoid widely outperforms max n in Chinese checkers, by a lesser amount in Hearts and that they are evenly matched in Spades.
Related Papers (5)
Mastering the game of Go with deep neural networks and tree search
David Silver,Aja Huang,Chris J. Maddison,Arthur Guez,Laurent Sifre,George van den Driessche,Julian Schrittwieser,Ioannis Antonoglou,Veda Panneershelvam,Marc Lanctot,Sander Dieleman,Dominik Grewe,John Nham,Nal Kalchbrenner,Ilya Sutskever,Timothy P. Lillicrap,Madeleine Leach,Koray Kavukcuoglu,Thore Graepel,Demis Hassabis +19 more