Year: 1999
Type: other
Abstract: This thesis describes reinforcement learning (RL) methods which can solve sequential decision \nmaking problems by learning from trial and error. Sequential decision making problems are \nproblems in which an artificial agent interacts with a specific environment through its sensors \n(to get inputs) and effectors (to make actions). To measure the goodness of some agent's \nbehavior, a reward function is used which determines how much an agent is rewarded or \npenalized for performing particular actions in particular environmental states. The goal is to \nfind an action selection policy for the agent which maximizes the cumulative reward collected \nin the future. \nIn RL, an agent's policy maps sensorbased inputs to actions. To evaluate a policy, a value function is learned which returns for each possible state the future cumulative reward collected by following the current policy. Given a value function, we can simply select the action with the largest value. In order to learn a value function for a specific problem, reinforcement learning methods simulate a policy and use the resulting agent's experiences consisting of <state,action,reward,next-state> quadruples. There are different RL problems and different RL methods for solving them. We describe different categories of problems and introduce new methods for solving them.
Author: Marco Wiering
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W2136719210