ReinforcementLearning   Performs reinforcement learning
epsilonGreedyActionSelection
                        Performs \varepsilon-greedy action selection
experienceReplay        Performs experience replay
gridworldEnvironment    Defines an environment for a gridworld example
lookupActionSelection   Converts a name into an action selection
                        function
lookupLearningRule      Loads reinforcement learning algorithm
policy                  Calculates the reinforcement learning policy
randomActionSelection   Performs random action selection
sampleExperience        Sample state transitions from an environment
                        function
sampleGridSequence      Sample grid sequence
state                   Creates a state representation for arbitrary
                        objects
tictactoe               Game states of 100,000 randomly sampled
                        Tic-Tac-Toe games.
