Padawan to Jedi: Using Reinforcement Learning to Train an Agent to Play Mancala

This paper discusses the results of using reinforcement learning to train an agent to play Mancala. I trained the agent by having it play a certain number of games against itself, and at the end of each game, I rewarded each move depending on whether it won or lost. Each move was rewarded by varying amounts based on how close to the end of the game it occurred. See game code at github.com/trb15a/mancala