Parametric Approximation Policy Iteration Algorithm Based on Gaussian Process
From MaRDI portal
Recommendations
- Using Gaussian processes for variance reduction in policy gradient algorithms
- Approximate gradient methods in policy-space optimization of Markov reward processes
- Approximate policy iteration: a survey and some new methods
- Policy iteration reinforcement learning based on geodesic Gaussian basis defined on a state-action graph
- scientific article; zbMATH DE number 6276239
- Approximate maximum a posteriori with Gaussian process priors
Cited in
(4)- Using Gaussian processes for variance reduction in policy gradient algorithms
- Non-parametric value function approximation in robotics
- Policy iteration reinforcement learning based on geodesic Gaussian basis defined on a state-action graph
- Nonparametric approximation generalized policy iteration reinforcement learning algorithm based on states clustering
This page was built for publication: Parametric Approximation Policy Iteration Algorithm Based on Gaussian Process
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5165995)
