Benchmarking for Bayesian Reinforcement Learning

09/14/2015
by   Michael Castronovo, et al.
0

In the Bayesian Reinforcement Learning (BRL) setting, agents try to maximise the collected rewards while interacting with their environment while using some prior knowledge that is accessed beforehand. Many BRL algorithms have already been proposed, but even though a few toy examples exist in the literature, there are still no extensive or rigorous benchmarks to compare them. The paper addresses this problem, and provides a new BRL comparison methodology along with the corresponding open source library. In this methodology, a comparison criterion that measures the performance of algorithms on large sets of Markov Decision Processes (MDPs) drawn from some probability distributions is defined. In order to enable the comparison of non-anytime algorithms, our methodology also includes a detailed analysis of the computation time requirement of each algorithm. Our library is released with all source code and documentation: it includes three test problems, each of which has two different prior distributions, and seven state-of-the-art RL algorithms. Finally, our library is illustrated by comparing all the available algorithms and the results are discussed.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
01/24/2022

Pearl: Parallel Evolutionary and Reinforcement Learning Library

Reinforcement learning is increasingly finding success across domains wh...
research
04/03/2023

A Tutorial Introduction to Reinforcement Learning

In this paper, we present a brief survey of Reinforcement Learning (RL),...
research
06/09/2009

Feature Reinforcement Learning: Part I: Unstructured MDPs

General-purpose, intelligent, learning agents cycle through sequences of...
research
09/24/2021

Regularization Guarantees Generalization in Bayesian Reinforcement Learning through Algorithmic Stability

In the Bayesian reinforcement learning (RL) setting, a prior distributio...
research
03/27/2013

ABC Reinforcement Learning

This paper introduces a simple, general framework for likelihood-free Ba...
research
07/18/2022

An Information-Theoretic Analysis of Bayesian Reinforcement Learning

Building on the framework introduced by Xu and Raginksy [1] for supervis...
research
11/11/2020

pymgrid: An Open-Source Python Microgrid Simulator for Applied Artificial Intelligence Research

Microgrids, self contained electrical grids that are capable of disconne...

Please sign up or login with your details

Forgot password? Click here to reset