Unknown

Dataset Information

0

Benchmarking for Bayesian Reinforcement Learning.

ABSTRACT: 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 the benchmarks used to compare them are only relevant for specific cases. 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.

SUBMITTER: Castronovo M 

PROVIDER: S-EPMC4909278 | biostudies-literature | 2016

REPOSITORIES: biostudies-literature

Json Xml
altmetric image

Publications

Benchmarking for Bayesian Reinforcement Learning.

Castronovo Michael M   Ernst Damien D   Couëtoux Adrien A   Fonteneau Raphael R  

PloS one 20160615 6

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 the benchmarks used to compare them are only relevant for specific cases. The paper addresses this problem, and provides a new BRL comparison methodology along with the corresponding open source library. In this methodology, a comparison criterio  ...[more]

Similar Datasets

Unknown Reinforcement Learning Trees.
| S-EPMC4760114 | biostudies-literature
Unknown Reinforcement learning and Bayesian inference provide complementary models for the unique advantage of adolescents in stochastic reversal.
| S-EPMC9108470 | biostudies-literature
Unknown Reinforcement learning in professional basketball players.
| S-EPMC3247813 | biostudies-other
Unknown Coordinated crawling via reinforcement learning.
| S-EPMC7482564 | biostudies-literature
Unknown Optimal Hierarchical Learning Path Design With Reinforcement Learning.
| S-EPMC7711250 | biostudies-literature
Unknown Reinforcement learning: Computational theory and biological mechanisms.
| S-EPMC2645553 | biostudies-other
Unknown Multitask learning and benchmarking with clinical time series data.
| S-EPMC6572845 | biostudies-other
Unknown How much of reinforcement learning is working memory, not reinforcement learning? A behavioral, computational, and neurogenetic analysis.
| S-EPMC3390186 | biostudies-literature
Unknown Developing PFC representations using reinforcement learning.
| S-EPMC2783795 | biostudies-literature
Unknown Evolution with reinforcement learning in negotiation.
| S-EPMC4105407 | biostudies-literature