Policy Gradient Importance Sampling for Bayesian Inference

DOI10.1109/TSP.2021.3093792MaRDI QIDQ5868678zbMATH OpenOpenAlexFDO

Authors Yousef El-Laham, Mónica F. Bugallo

Publication date 23 September 2022

Published in IEEE Transactions on Signal Processing (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1109/tsp.2021.3093792

Mathematics Subject Classification ID

Signal theory (characterization, reconstruction, filtering, etc.) (94A12)

Recommendations

• Importance sampling techniques for policy optimization
• Importance sampling in reinforcement learning with an estimated behavior policy
• Bayesian policy gradient and actor-critic algorithms
• Gradient-based adaptive importance samplers
• Importance sampling as a variational approximation
• Implicitly adaptive importance sampling
• Variational approximation for importance sampling
• Efficient Bayes inference in neural networks through adaptive importance sampling
• MCMC-driven importance samplers
• Adaptive importance sampling for value function approximation in off-policy reinforcement learning

Cited in

(1)

• Global convergence of optimized adaptive importance samplers

This page was built for publication: Policy Gradient Importance Sampling for Bayesian Inference

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5868678)