Model-Free Reinforcement Learning
Computes the reinforcement learning policy
Performs -greedy action selection
Performs experience replay
Defines an environment for a gridworld example
Converts a name into an action selection function
Loads reinforcement learning algorithm
Computes the reinforcement learning policy
Performs random action selection
Performs reinforcement learning
Performs experience replay
Sample state transitions from an environment function
Sample grid sequence
Performs -greedy action selection
Performs random action selection
Creates a state representation for arbitrary objects
Performs model-free reinforcement learning in R. This implementation enables the learning of an optimal policy based on sample sequences consisting of states, actions and rewards. In addition, it supplies multiple predefined reinforcement learning algorithms, such as experience replay. Methodological details can be found in Sutton and Barto (1998) <ISBN:0262039249>.