Learning and Improving Backgammon Strategy

2025-04-03 · Gregory R. Galperin

A novel approach to learning is presented, combining features of on-line and off-line methods to achieve considerable performance in the task of learning a backgammon value function in a process that exploits the processing power of parallel supercomputers. The off-line methods comprise a set of techniques for parallelizing neural network training and $TD(\lambda)$ reinforcement learning; here Monte-Carlo ``Rollouts'' are introduced as a massively parallel on-line policy improvement technique which applies resources to the decision points encountered during the search of the game tree to further augment the learned value function estimate. A level of play roughly as good as, or possibly better than, the current champion human and computer backgammon players has been achieved in a short period of learning.

📄 PDF Abstract BibTeX arXiv:2504.02221

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically

Deep Reinforcement Learning for FlipIt Security Game

2020-02-28 · Laura Greige, Peter Chin

Reinforcement learning has shown much success in games such as chess, backgammon and Go. However, in most of these games, agents have full knowledge of the environment at all times. In this paper, we describe a deep lear…

Deep Reinforcement Learning Q-Learning reinforcement-learning Reinforcement Learning+1

Quantifying Skill and Chance: A Unified Framework for the Geometry of Games

2025-11-03 · David H. Silver arxiv

We introduce a quantitative framework for separating skill and chance in games by modeling them as complementary sources of control over stochastic decision trees. We define the Skill-Luck Index S(G) in [-1, 1] by decomp…

Leveling the Playing Field -- Fairness in AI Versus Human Game Benchmarks

2019-03-17 · Rodrigo Canaan, Christoph Salge, Julian Togelius, Andy Nealen

From the beginning if the history of AI, there has been interest in games as a platform of research. As the field developed, human-level competence in complex games became a target researchers worked to reach. Only relat…

Fairness

Pgx: Hardware-Accelerated Parallel Game Simulators for Reinforcement Learning

2023-03-29 · NeurIPS 2023 11 · Sotetsu Koyamada, Shinri Okano, Soichiro Nishimori, Yu Murata 외

We propose Pgx, a suite of board game reinforcement learning (RL) environments written in JAX and optimized for GPU/TPU accelerators. By leveraging JAX's auto-vectorization and parallelization over accelerators, Pgx can …

GPU reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

On-line Policy Improvement using Monte-Carlo Search

2025-01-09 · Gerald Tesauro, Gregory R. Galperin

We present a Monte-Carlo simulation algorithm for real-time policy improvement of an adaptive controller. In the Monte-Carlo simulation, the long-term expected reward of each possible action is statistically measured, us…