Closing the Gap: Achieving Global Convergence (Last Iterate) of Actor-Critic under Markovian Sampling with Neural Network Parametrization

Mudit Gaur; Amrit Bedi; Di Wang; Vaneet Aggarwal

2024 ICML ICML 2024

Closing the Gap: Achieving Global Convergence (Last Iterate) of Actor-Critic under Markovian Sampling with Neural Network Parametrization

Abstract

No abstract available. No abstract was captured for this paper when its proceedings were scraped - most often an older edition published without one online. How the corpus is built.

🌉 Interdisciplinary Bridge - Artificial Intelligence and Reinforcement Learning

Authors

Mudit Gaur, Amrit Bedi, Di Wang, Vaneet Aggarwal

Topics

Machine Learning > Optimization & Theory > Optimization Reinforcement Learning > Methods > Deep RL Reinforcement Learning > Applications > Value Iteration

Keywords

global convergence markovian sampling neural network parametrization actor critic last iterate critic estimation

Download PDF