Policy Gradient Methods for the Noisy Linear Quadratic Regulator over a Finite Horizon
From MaRDI portal
Publication:5157372
Recommendations
Cites work
- A note on the Hanson-Wright inequality for random vectors with dependencies
- Derivative-free methods for policy optimization: guarantees for linear quadratic systems
- Dynamic programming and optimal control. Vol. 1.
- Efficient learning of distributed linear-quadratic control policies
- Introductory lectures on convex optimization. A basic course.
- Linear Thompson sampling revisited
- On the sample complexity of the linear quadratic regulator
- Online convex optimization in the bandit setting: gradient descent without a gradient
- Optimal execution strategies in limit order books with general shape functions
- Optimal execution with nonlinear impact functions and trading-enhanced risk
- OPTIMAL TRADE EXECUTION UNDER GEOMETRIC BROWNIAN MOTION IN THE ALMGREN AND CHRISS FRAMEWORK
- Optimism-Based Adaptive Regulation of Linear-Quadratic Systems
- Recovering Low-Rank Matrices From Few Coefficients in Any Basis
Cited in
(24)- Regularized policy iteration with nonparametric function spaces
- Robust Policy Iteration for Continuous-Time Linear Quadratic Regulation
- Entropy Regularization for Mean Field Games with Learning
- A Small Gain Analysis of Single Timescale Actor Critic
- Linear Convergence of a Policy Gradient Method for Some Finite Horizon Continuous Time Control Problems
- Recent advances in reinforcement learning in finance
- Continuous‐time stochastic gradient descent for optimizing over the stationary distribution of stochastic differential equations
- Reinforcement learning with dynamic convex risk measures
- Convergence of policy gradient methods for finite-horizon exploratory linear-quadratic control problems
- Policy gradient methods for discrete time linear quadratic regulator with random parameters
- Recent developments in machine learning methods for stochastic control and games
- Scalable natural policy gradient for general-sum linear quadratic games with unknown parameters
- Model-agnostic Hessian-free meta-policy optimization via zeroth-order estimation: a linear quadratic regulator perspective
- Hierarchical dynamic graphical games for optimal leader-follower consensus control
- Fast policy learning for linear-quadratic control with entropy regularization
- Sublinear regret for a class of continuous-time linear-quadratic reinforcement learning problems
- Learning zero-sum linear quadratic games with improved sample complexity and last-iterate convergence
- Entropy annealing for policy mirror descent in continuous time and space
- Policy gradient converges to the globally optimal policy for nearly linear-quadratic regulators
- Policy optimization of finite-horizon Kalman filter with unknown noise covariance
- Policy iteration for the deterministic control problems -- a viscosity approach
- Continuous-time risk-sensitive reinforcement learning via quadratic variation penalty
- Interpretable gradient descent for the Kalman gain
- Logarithmic regret in the ergodic Avellaneda-Stoikov market making model
This page was built for publication: Policy Gradient Methods for the Noisy Linear Quadratic Regulator over a Finite Horizon
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5157372)
