Geometric variance reduction in Markov chains: application to value function and gradient estimation
From MaRDI portal
Recommendations
- Variance reduction techniques for gradient estimates in reinforcement learning
- Variance reduction for Markov chain processes using state space evaluation for control variates
- Variance reduction for Markov chains with application to MCMC
- Approximate gradient methods in policy-space optimization of Markov reward processes
- Variance reduction through smoothing and control variates for Markov chain simulations
Cited in
(7)- Coupling based estimation approaches for the average reward performance potential in Markov chains
- Approximate gradient methods in policy-space optimization of Markov reward processes
- Adaptive dimension reduction to accelerate infinite-dimensional geometric Markov chain Monte Carlo
- Generalization and Robustness of Batched Weighted Average Algorithm with V-Geometrically Ergodic Markov Data
- Variance reduction techniques for gradient estimates in reinforcement learning
- Does waste recycling really improve the multi-proposal Metropolis-Hastings algorithm? An analysis based on control variates
- Variance reduction for Markov chain processes using state space evaluation for control variates
This page was built for publication: Geometric variance reduction in Markov chains: application to value function and gradient estimation
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3093352)
