Q Learning

Q-learning is a reinforcement learning algorithm aiming to find optimal actions in an environment by learning a Q-function that estimates the expected cumulative reward for each state-action pair. Current research focuses on improving Q-learning's robustness, efficiency, and applicability to complex scenarios, including multi-agent systems, partially observable environments (POMDPs), and those with corrupted rewards, often employing deep learning architectures like deep Q-networks (DQNs) and modifications such as double Q-learning and prioritized experience replay. These advancements are significant for addressing challenges in various fields, such as robotics, autonomous systems, and network optimization, where efficient and reliable decision-making under uncertainty is crucial.

Papers

February 12, 2024

Leveraging Digital Cousins for Ensemble Q-Learning in Large-Scale Wireless Networks
Talha Bozkus, Urbashi Mitra
Large Scale Q Learning Diverse Ensemble Wireless Network Ensemble Q Learning

February 9, 2024

February 8, 2024

Multi-Timescale Ensemble Q-learning for Markov Decision Process Policy Optimization
Talha Bozkus, Urbashi Mitra
Reinforcement Learning Q Learning Model Free Reinforcement Learning Ensemble Q Learning Frank Wolfe Policy Optimization

February 3, 2024

January 26, 2024

Regularized Q-Learning with Linear Function Approximation
Jiachen Xi, Alfredo Garcia, Petar Momcilovic
Reinforcement Learning Q Learning Linear Function Approximation Finite Time Convergence Soft Q Learning Multimodal Policy

January 25, 2024

Constant Stepsize Q-learning: Distributional Convergence, Bias and Extrapolation
Yixuan Zhang, Qiaomin Xie
Reinforcement Learning Absolute Stance Bias Q Learning Extrapolation Framework Asynchronous Q Learning

January 6, 2024

December 23, 2023

December 19, 2023

December 12, 2023

I Open at the Close: A Deep Reinforcement Learning Evaluation of Open Streets Initiatives
R. Teal Witter, Lucas Rosenblatt
Reinforcement Learning Graph Neural Network Q Learning Reinforcement Learning Problem Open Street

December 5, 2023

A Q-learning approach to the continuous control problem of robot inverted pendulum balancing
Mohammad Safeea, Pedro Neto
Robot Person Q Learning Action Space Control Problem Inverted Pendulum Action Space Reinforcement Learning

November 29, 2023

Q-learning Based Optimal False Data Injection Attack on Probabilistic Boolean Control Networks
Xianlun Peng, Yang Tang, Fangfei Li, Yang Liu
Reinforcement Learning Q Learning Optimal Attack Probabilistic Boolean Network

November 26, 2023

FRAC-Q-Learning: A Reinforcement Learning with Boredom Avoidance Processes for Social Robots
Akinari Onishi
Reinforcement Learning Q Learning Social Robot Q$ Learning Q$ Learning Algorithm

November 24, 2023

Approximation of Convex Envelope Using Reinforcement Learning
Vivek S. Borkar, Adit Akarsh
Reinforcement Learning Q Learning Average Approximation Convex Set Stochastic Control Stopping Time

Q Learning

Papers

Leveraging Digital Cousins for Ensemble Q-Learning in Large-Scale Wireless Networks

Dynamic Q-planning for Online UAV Path Planning in Unknown and Complex Environments

Value function interference and greedy action selection in value-based multi-objective reinforcement learning

Multi-Timescale Ensemble Q-learning for Markov Decision Process Policy Optimization

SQT -- std $Q$-target

Towards Optimal Adversarial Robust Q-learning with Bellman Infinity-error

Regularized Q-Learning with Linear Function Approximation

Constant Stepsize Q-learning: Distributional Convergence, Bias and Extrapolation

An Empirical Investigation of Value-Based Multi-objective Reinforcement Learning for Stochastic Environments

SPQR: Controlling Q-ensemble Independence with Spiked Random Model for Reinforcement Learning

Q-Boost: On Visual Quality Assessment Ability of Low-level Multi-Modality Foundation Models

Reinforcement Learning for Safe Occupancy Strategies in Educational Spaces during an Epidemic

Sample Efficient Reinforcement Learning with Partial Dynamics Knowledge

Cautiously-Optimistic Knowledge Sharing for Cooperative Multi-Agent Reinforcement Learning

Stability of Multi-Agent Learning in Competitive Networks: Delaying the Onset of Chaos

I Open at the Close: A Deep Reinforcement Learning Evaluation of Open Streets Initiatives

A Q-learning approach to the continuous control problem of robot inverted pendulum balancing

Q-learning Based Optimal False Data Injection Attack on Probabilistic Boolean Control Networks

FRAC-Q-Learning: A Reinforcement Learning with Boredom Avoidance Processes for Social Robots

Approximation of Convex Envelope Using Reinforcement Learning