Man pages for nproellochs/ReinforcementLearning
Model-Free Reinforcement Learning

epsilonGreedyActionSelectionPerforms \varepsilon-greedy action selection
experienceReplayPerforms experience replay
gridworldEnvironmentDefines an environment for a gridworld example
lookupActionSelectionConverts a name into an action selection function
lookupLearningRuleLoads reinforcement learning algorithm
policyCalculates the reinforcement learning policy
randomActionSelectionPerforms random action selection
ReinforcementLearningPerforms reinforcement learning
sampleExperienceSample state transitions from an environment function
sampleGridSequenceSample grid sequence
stateCreates a state representation for arbitrary objects
tictactoeGame states of 100,000 randomly sampled Tic-Tac-Toe games.
nproellochs/ReinforcementLearning documentation built on Oct. 29, 2018, 8:20 p.m.