An MDP Blackjack Agent
نویسنده
چکیده
In this paper an implementation of a Blackjack agent is discussed. The agent uses a Markov decision process (MDP) to learn about the game world of Blackjack and exploits its knowledge to play successfully. Value iteration and q-learning are used, allowing the agent to propagate its knowledge back to every state from the terminal states. Feature extraction is used to speed up this process, as the agent requires fewer training games to learn about the world. A user interactive game was created with the agent to demonstrate the choices it would make at each state. Author
منابع مشابه
Reinforcement Learning for Blackjack
This paper explores the development of an Artificial Intelligence system for an already existing framework of card games, called SKCards, and the experimental results obtained from this. The current Artificial intelligence in the SKCards Blackjack is highly flawed. Reinforcement Learning was chosen as the method to be employed. Reinforcement Learning attempts to teach a computer certain actions...
متن کاملSafe Policy Iteration – Supplementary Material
Matteo Pirotta [email protected] Marcello Restelli [email protected] Alessio Pecorino [email protected] Daniele Calandriello [email protected] Dept. Elect., Inf., and Bioeng., Politecnico di Milano, piazza Leonardo da Vinci 32, I-20133, Milan, ITALY Abstract This document provides additional material to the main paper. In particular, it provides:...
متن کاملOn evolutionary selection of blackjack strategies
We apply the approach of evolutionary programming to the problem of optimization of the blackjack basic strategy. We demonstrate that the population of initially random blackjack strategies evolves and saturates to a profitable performance in about one hundred generations. The resulting strategy resembles the known blackjack basic strategies in the specifics of its prescriptions, and has a simi...
متن کاملApplying Reinforcement Learning to Blackjack Using Q-Learning
Blackjack is a popular card game played in many casinos. The objective of the game is to win money by obtaining a point total higher than the dealer’s without exceeding 21. Determining an optimal blackjack strategy proves to be a difficult challenge due to the stochastic nature of the game. This presents an interesting opportunity for machine learning algorithms. Supervised learning techniques ...
متن کاملThe Evolution of Blackjack Strategies
In this paper we investigate the evolution of a blackjack player. We utilise three neural networks (one for splitting, one for doubling down and one for standing/hitting) to evolve blackjack strategies. Initially a pool of randomly generated players play 1000 hands of blackjack. An evolutionary strategy is used to mutate the best networks (with the worst networks being killed). We compare the b...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2012