Bayesian policy gradient and actor-critic algorithms

MaRDI QIDQ2810874zbMATH OpenFDO

Authors Mohammad Ghavamzadeh, Yaakov Engel, Michal Valko

Publication date 6 June 2016

Published in Journal of Machine Learning Research (JMLR) (Search for Journal in Brave)

Full work available at URL http://jmlr.csail.mit.edu/papers/v17/10-245.html

Mathematics Subject Classification ID

Gaussian processes (60G15) Bayesian inference (62F15) Learning and adaptive systems in artificial intelligence (68T05)

Recommendations

• Bayesian reinforcement learning: a survey
• Bayesian Reinforcement Learning with Exploration
• Expected policy gradients for reinforcement learning
• A Bayesian reinforcement learning approach in Markov games for computing near-optimal policies
• Variational actor-critic algorithms,
• Bayesian exploration for approximate dynamic programming
• Actor-Critic--Type Learning Algorithms for Markov Decision Processes
• Bayesian optimization for policy search via online-offline experimentation

Cited in

(10)

• Natural actor-critic algorithms
• Reinforcement learning, sequential Monte Carlo and the EM algorithm
• Bayesian policy reuse
• Using trajectory data to improve Bayesian optimization for reinforcement learning
• Bayesian Reinforcement Learning with Exploration
• Variance reduction techniques for gradient estimates in reinforcement learning
• Expected policy gradients for reinforcement learning
• Hessian matrix distribution for Bayesian policy gradient reinforcement learning
• Policy Gradient Importance Sampling for Bayesian Inference
• Decentralized fused-learner architectures for Bayesian reinforcement learning

This page was built for publication: Bayesian policy gradient and actor-critic algorithms

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2810874)