Reinforcement Learning on Tic-Tac-Toe : SARSA and Q-Learning Approach (Presentation)

Описание

Exploring the application of reinforcement learning techniques, specifically Q-learning and SARSA, to the classic game of Tic Tac Toe.

Objective : To develop an AI agent capable of playing the game at a competitive level. By iteratively training the agent using these algorithms, it learns optimal strategies and makes intelligent decisions based on learned Q-values.

The effectiveness of reinforcement learning in solving simple games is demonstrated, paving the way for further exploration in more complex environments.

Github link : https://github.com/rfeinman/tictactoe-reinforcement-learning

Report : https://www.overleaf.com/read/syvtfhhbvbxc


#ReinforcementLearning #TicTacToeAI #MachineLearning #Qlearning #SARSA #GameAI #IntelligentAgent #OptimalStrategies #AIvsHuman #RLAlgorithms #GameDevelopment #LearningFromRewards #AIChallenge #StrategyGames #AIPlayer #CompetitiveGaming #SimpleGames #ComplexEnvironments