Posts

This is my summary of the lecture on Reinforcement Learning by Vien Ngo, Hung Ngo and Marc Toussaint from Machine Learning & Robotics Lab, IPVS, University of Stuttgart. This is based on the summer semester 2017. https://ipvs.informatik.uni-stuttgart.de/mlr/reinforcement-learning-ss-17/

Reinforcement learning (RL) is an area of machine learning inspired by behaviorist psychology, concerned with how software agents ought to take actions in an environment so as to maximize some notion of cumulative reward. The problem, due to its generality, is studied in many other disciplines, such as game theory, control theory, operations research, information theory, simulation-based optimization, multi-agent systems, swarm intelligence, statistics, and genetic algorithms. In the operations research and control literature, the field where reinforcement learning methods are studied is called approximate dynamic programming. The problem has been studied in the theory of optimal control, though most studies are concerned with the existence of optimal solutions and their characterization, and not with the learning or approximation aspects. In economics and game theory, reinforcement learning may be used to explain how equilibrium may arise under bounded rationality. (Wikipedia)

Content

1 Introduction

2 MDP, Bellman Equations, DP

3 Temporal Difference

4 Value Function Approximation

6 Hierarchical RL

7 Inverse RL

8 Model Based RL

References

subscribe via RSS