Integrating a partial model into model free reinforcement learning

MaRDI QIDQ5405178zbMATH OpenFDO

Authors Aviv Tamar, Dotan Di Castro, Ron Meir

Publication date 1 April 2014

Full work available at URL http://www.jmlr.org/papers/v13/tamar12a.html

zbMATH Keywords

hybrid model-based model-free algorithmsMarkov decision processesreinforcement learningstochastic approximationtemporal difference

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Recommendations

• Model-based policy gradients with parameter-based exploration by least-squares conditional density estimation
• Model-free average reward multi-step reinforcement learning
• A generalized path integral control approach to reinforcement learning
• Model-based average reward reinforcement learning
• Model-Based Reinforcement Learning for Partially Observable Games with Sampling-Based State Estimation

Cited in

(2)

• scientific article; zbMATH DE number 7306889 (Why is no real title available?)
• Model-based policy gradients with parameter-based exploration by least-squares conditional density estimation

This page was built for publication: Integrating a partial model into model free reinforcement learning

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5405178)