Is Temporal Difference Learning Optimal? An Instance-Dependent Analysis
From MaRDI portal
Recommendations
- On the worst-case analysis of temporal-difference learning algorithms
- On the worst-case analysis of temporal-difference learning algorithms
- AN ANALYSIS OF EXPERIENCE REPLAY IN TEMPORAL DIFFERENCE LEARNING
- Practical issues in temporal difference learning
- On average versus discounted reward temporal-difference learning
- An analysis of temporal-difference learning with function approximation
- A finite time analysis of temporal difference learning with linear function approximation
- Least squares temporal difference methods: An analysis under general conditions
- Differential Temporal Difference Learning
- Asymptotic analysis of temporal-difference learning algorithms with constant step-sizes
Cites work
- A finite time analysis of temporal difference learning with linear function approximation
- A Framework For Estimation Of Convex Functions
- A Stochastic Approximation Method
- Acceleration of Stochastic Approximation by Averaging
- An adaptation theory for nonparametric confidence intervals
- Approximation dans les espaces m�triques et th�orie de l'estimation
- Asymptotic Statistics
- Asymptotics in statistics. Some basic concepts.
- Dynamic programming and optimal control. Vol. 1.
- Dynamic programming and optimal control. Vol. 2
- Finite-time performance of distributed temporal-difference learning with linear function approximation
- Geometrizing rates of convergence. II
- Geometrizing rates of convergence. III
- High-dimensional statistics. A non-asymptotic viewpoint
- scientific article; zbMATH DE number 3124347 (Why is no real title available?)
- scientific article; zbMATH DE number 3487311 (Why is no real title available?)
- scientific article; zbMATH DE number 1321699 (Why is no real title available?)
- scientific article; zbMATH DE number 1350309 (Why is no real title available?)
- scientific article; zbMATH DE number 3441440 (Why is no real title available?)
- scientific article; zbMATH DE number 3426635 (Why is no real title available?)
- scientific article; zbMATH DE number 3223982 (Why is no real title available?)
- Instance-Dependent ℓ∞-Bounds for Policy Evaluation in Tabular Reinforcement Learning
- Minimax PAC bounds on the sample complexity of reinforcement learning with a generative model
- Near-optimal PAC bounds for discounted MDPs
- New method of stochastic approximation type
- On the Almost Sure Rate of Convergence of Linear Stochastic Approximation Algorithms
- On the Convergence of Stochastic Iterative Dynamic Programming Algorithms
- Policy evaluation with temporal differences: a survey and comparison
- Reinforcement learning. An introduction
- Robust Stochastic Approximation Approach to Stochastic Programming
- Stochastic approximation. A dynamical systems viewpoint.
- The O.D.E. Method for Convergence of Stochastic Approximation and Reinforcement Learning
Cited in
(6)- Can Doxastic Agents Learn? On the Temporal Structure of Learning
- Accelerated and Instance-Optimal Policy Evaluation with Linear Function Approximation
- Softmax policy gradient methods can take exponential time to converge
- Neural Temporal Difference and Q Learning Provably Converge to Global Optima
- Optimal policy evaluation using kernel-based temporal difference methods
- On Bellman equations for continuous-time policy evaluation: high-order discretization and function approximation
This page was built for publication: Is Temporal Difference Learning Optimal? An Instance-Dependent Analysis
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5162625)
