An active exploration method for data efficient reinforcement learning

DOI10.2478/AMCS-2019-0026zbMATH Open1430.93072OpenAlexW2957466728WikidataQ127540608 ScholiaQ127540608MaRDI QIDQ2299097FDOQ2299097

Authors: Dongfang Zhao, Jiafeng Liu, Rui Wu, Dansong Cheng, Xianglong Tang 

Publication date: 20 February 2020

Published in: International Journal of Applied Mathematics and Computer Science (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.2478/amcs-2019-0026

Recommendations

• Efficient exploration through active learning for value function approximation in reinforcement learning
• A generalized path integral control approach to reinforcement learning
• Dual control for approximate Bayesian reinforcement learning
• Efficient sample reuse in policy gradients with parameter-based exploration
• Safe Exploration of State and Action Spaces in Reinforcement Learning

zbMATH Keywords

reinforcement learninginformation entropydata efficiencyPILCO

Mathematics Subject Classification ID

Measures of information, entropy (94A17) Iterative learning control (93B47)

Cites Work

• Entropy expressions and their estimators for multivariate distributions
• Title not available (Why is that?)
• Active contextual policy search
• End-to-end training of deep visuomotor policies

Cited In (4)

• Data-driven online modelling for a UGI gasification process using modified lazy learning with a relevance vector machine
• An information based approach to stochastic control problems
• Efficient exploration through active learning for value function approximation in reinforcement learning
• A linear programming methodology for approximate dynamic programming

Uses Software

• PILCO

This page was built for publication: An active exploration method for data efficient reinforcement learning

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2299097)