Icon

Tic-Tac-Toe Learn

Training a Reinforcment Learning Model to play Tic-Tac-Toe with the Keras Deep Learning Integration.

Reinforcment Learning Process Define Network Architecture Play of Set of Games Play of Single Game InitialEmpty Board27 input represetningboard state1 output for Score54 tanh54 tanhPlay Set ofGamesPlay GameEnd of GameTransfer to JavaExecution for LoopScoreStatesEnd of SetTrain Model on 25sets of 100 gamesUpdateModelScore fortrackingr = 0.1r = 0.1Table Creator Convert to List Playable Moves Active LearningLoop Start Keras Input Layer Keras Dense Layer Keras Dense Layer Keras Dense Layer Counting Loop Start RecursiveLoop Start Game Over? Recursive Loop End Keras to TensorFlowNetwork Converter Math Formula Loop End Column Filter Select Move Active LearningLoop End Keras NetworkLearner Keras NetworkExecutor Numeric Scorer Transpose Keras Dropout Layer Keras Dropout Layer Reinforcment Learning Process Define Network Architecture Play of Set of Games Play of Single Game InitialEmpty Board27 input represetningboard state1 output for Score54 tanh54 tanhPlay Set ofGamesPlay GameEnd of GameTransfer to JavaExecution for LoopScoreStatesEnd of SetTrain Model on 25sets of 100 gamesUpdateModelScore fortrackingr = 0.1r = 0.1Table Creator Convert to List Playable Moves Active LearningLoop Start Keras Input Layer Keras Dense Layer Keras Dense Layer Keras Dense Layer Counting Loop Start RecursiveLoop Start Game Over? Recursive Loop End Keras to TensorFlowNetwork Converter Math Formula Loop End Column Filter Select Move Active LearningLoop End Keras NetworkLearner Keras NetworkExecutor Numeric Scorer Transpose Keras Dropout Layer Keras Dropout Layer

Nodes

Extensions

Links