A finite-time analysis of Q-learning with neural network function approximation
Q-learning with neural network function approximation (neural Q-learning for short) is
among the most prevalent deep reinforcement learning algorithms. Despite its empirical …
among the most prevalent deep reinforcement learning algorithms. Despite its empirical …
Smart cities using machine learning and intelligent applications
AG Prawiyogi, S Purnama… - … Transactions on Artificial …, 2022 - journal.pandawan.id
The goal of smart cities is to properly manage to expand urbanization, Reduce energy
usage, Enhance the economic and quality of life of the locals while also preserving the …
usage, Enhance the economic and quality of life of the locals while also preserving the …
Characterizing the exact behaviors of temporal difference learning algorithms using Markov jump linear system theory
In this paper, we provide a unified analysis of temporal difference learning algorithms with
linear function approximators by exploiting their connections to Markov jump linear systems …
linear function approximators by exploiting their connections to Markov jump linear systems …
Finite-time analysis of decentralized temporal-difference learning with linear function approximation
Motivated by the emerging use of multi-agent reinforcement learning (MARL) in engineering
applications such as networked robotics, swarming drones, and sensor networks, we …
applications such as networked robotics, swarming drones, and sensor networks, we …
Single-timescale stochastic nonconvex-concave optimization for smooth nonlinear td learning
Temporal-Difference (TD) learning with nonlinear smooth function approximation for policy
evaluation has achieved great success in modern reinforcement learning. It is shown that …
evaluation has achieved great success in modern reinforcement learning. It is shown that …
Reanalysis of variance reduced temporal difference learning
Temporal difference (TD) learning is a popular algorithm for policy evaluation in
reinforcement learning, but the vanilla TD can substantially suffer from the inherent …
reinforcement learning, but the vanilla TD can substantially suffer from the inherent …
Decentralized TD tracking with linear function approximation and its finite-time analysis
The present contribution deals with decentralized policy evaluation in multi-agent Markov
decision processes using temporal-difference (TD) methods with linear function …
decision processes using temporal-difference (TD) methods with linear function …
A single-timescale analysis for stochastic approximation with multiple coupled sequences
Stochastic approximation (SA) with multiple coupled sequences has found broad
applications in machine learning such as bilevel learning and reinforcement learning (RL) …
applications in machine learning such as bilevel learning and reinforcement learning (RL) …
Concentration of contractive stochastic approximation and reinforcement learning
Using a martingale concentration inequality, concentration bounds “from time n 0 on” are
derived for stochastic approximation algorithms with contractive maps and both martingale …
derived for stochastic approximation algorithms with contractive maps and both martingale …
On rademacher complexity-based generalization bounds for deep learning
LV Truong - arXiv preprint arXiv:2208.04284, 2022 - arxiv.org
In this paper, we develop some novel bounds for the Rademacher complexity and the
generalization error in deep learning with iid and Markov datasets. The new Rademacher …
generalization error in deep learning with iid and Markov datasets. The new Rademacher …