replayExperience: Performs experience replay

In ReinforcementLearning: Model-Free Reinforcement Learning

Description

Performs experience replay. Experience replay allows reinforcement learning agents to remember and reuse experiences from the past. The algorithm requires input data in the form of sample sequences consisting of states, actions and rewards. The result of the learning process is a state-action table Q that allows one to infer the best possible action in each state.

Usage

replayExperience(D, Q, control, ...)

Arguments

D	A dataframe containing the input data for reinforcement learning. Each row represents a state transition tuple (s,a,r,s_new).
Q	Existing state-action table of type hash.
control	Control parameters defining the behavior of the agent.
...	Additional parameters passed to function.

Value

Returns an object of class hash that contains the learned Q-table.

References

Lin (1992). "Self-Improving Reactive Agents Based on Reinforcement Learning, Planning and Teaching", Machine Learning (8:3), pp. 293–321.

Watkins (1992). "Q-learning". Machine Learning (8:3), pp. 279–292.

See Also

ReinforcementLearning

ReinforcementLearning documentation built on March 26, 2020, 7:38 p.m.