Picture for Semih Cayci

Semih Cayci

Essentially Sharp Estimates on the Entropy Regularization Error in Discrete Discounted Markov Decision Processes

Add code
Jun 06, 2024
Viaarxiv icon

Recurrent Natural Policy Gradient for POMDPs

Add code
May 28, 2024
Figure 1 for Recurrent Natural Policy Gradient for POMDPs
Figure 2 for Recurrent Natural Policy Gradient for POMDPs
Figure 3 for Recurrent Natural Policy Gradient for POMDPs
Viaarxiv icon

Convergence of Gradient Descent for Recurrent Neural Networks: A Nonasymptotic Analysis

Add code
Feb 19, 2024
Viaarxiv icon

Provably Robust Temporal Difference Learning for Heavy-Tailed Rewards

Add code
Jun 20, 2023
Viaarxiv icon

Policy Mirror Ascent for Efficient and Independent Learning in Mean Field Games

Add code
Dec 29, 2022
Viaarxiv icon

Finite-Time Analysis of Entropy-Regularized Neural Natural Actor-Critic Algorithm

Add code
Jun 02, 2022
Figure 1 for Finite-Time Analysis of Entropy-Regularized Neural Natural Actor-Critic Algorithm
Viaarxiv icon

Learning to Control Partially Observed Systems with Finite Memory

Add code
Feb 22, 2022
Viaarxiv icon

A Lyapunov-Based Methodology for Constrained Optimization with Bandit Feedback

Add code
Jun 09, 2021
Figure 1 for A Lyapunov-Based Methodology for Constrained Optimization with Bandit Feedback
Figure 2 for A Lyapunov-Based Methodology for Constrained Optimization with Bandit Feedback
Viaarxiv icon

Linear Convergence of Entropy-Regularized Natural Policy Gradient with Linear Function Approximation

Add code
Jun 08, 2021
Viaarxiv icon

Sample Complexity and Overparameterization Bounds for Projection-Free Neural TD Learning

Add code
Mar 02, 2021
Figure 1 for Sample Complexity and Overparameterization Bounds for Projection-Free Neural TD Learning
Viaarxiv icon