Robust reinforcement learning for risk-sensitive linear quadratic Gaussian control
From MaRDI portal
Cited in
(4)- Model-free approximate dynamic programming for stochastic zero-sum games: algorithm design and analysis
- Direct data-driven discounted infinite horizon linear quadratic regulator with robustness guarantees
- A generalized policy-iteration algorithm for linear discrete-time two-player zero-sum games with convergence guarantees
- Decentralized strategies for finite population LQG social control: a reinforcement learning approach
This page was built for publication: Robust reinforcement learning for risk-sensitive linear quadratic Gaussian control
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6668004)
