Model-Free Reinforcement Learning

---

Documentation for package ‘ReinforcementLearning’ version 1.0.5

• DESCRIPTION file.
• User guides, package vignettes and other documentation.
• Package NEWS.

Help Pages

computePolicy	Computes the reinforcement learning policy
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	Computes the reinforcement learning policy
randomActionSelection	Performs random action selection
ReinforcementLearning	Performs reinforcement learning
replayExperience	Performs experience replay
rl	Performs reinforcement learning
sampleExperience	Sample state transitions from an environment function
sampleGridSequence	Sample grid sequence
selectEpsilonGreedyAction	Performs \varepsilon-greedy action selection
selectRandomAction	Performs random action selection
state	Creates a state representation for arbitrary objects
tictactoe	Game states of 100,000 randomly sampled Tic-Tac-Toe games.