Q-learning
PulseAugur coverage of Q-learning — every cluster mentioning Q-learning across labs, papers, and developer communities, ranked by signal.
4 day(s) with sentiment data
-
New QEMScore metric challenges learned quantum error mitigation claims
A new scoring metric called QEMScore has been proposed to better evaluate learned quantum error mitigation techniques. This metric compares a learned mitigator against a capacity-matched control model that uses the same…
-
New technique analyzes Q-learning convergence and bias in stochastic approximation
Researchers have developed a new technique for analyzing nonsmooth contractive stochastic approximation (SA) dynamics, particularly relevant to Q-learning. The study establishes weak convergence of iterates to a station…
-
New HQARRF system improves sensor survival in wireless networks
A new research paper introduces HQARRF, a two-level scheduling system designed for wireless rechargeable sensor networks. This system aims to optimize multi-charger scheduling by considering factors like sensor death ri…
-
New framework models multi-agent Q-learning with environmental feedback
Researchers have developed a new framework using evolutionary computation to model multi-agent Q-learning within complex environmental feedback loops. This model simulates how individual agent learning, local interactio…
-
New Q-SVMPC method enhances trajectory optimization with RL and SVGD
Researchers have developed Q-SVMPC, a novel approach to model predictive control (MPC) that leverages Q-learning and Stein Variational Gradient Descent (SVGD) to enhance trajectory optimization. This method aims to over…
-
New risk-averse Q-learning method for robot navigation
Researchers have developed a novel approach to risk-averse reinforcement learning for complex decision-making tasks. This method, termed Mini-Batch Risk-Averse Deep Q-Learning, addresses the challenge of estimating tran…
-
Alice system integrates Qwen model with router, memory, and learning
The document outlines 'Alice,' a local intelligence system that integrates multiple components beyond its core language model, Qwen. Alice operates on a 'KNOW → DO → LEARN IF NECESSARY → RETAIN → REUSE' principle, empha…
-
New AI method optimizes satellite scheduling for maritime targets
Researchers have developed a new method called Implicit Q-learning-bootstrapped Ant Colony Optimization (IQACO) to improve scheduling for maritime moving-target observation using agile Earth Observation Satellites. This…
-
New Q-learning framework offers stable infinite-dimensional linear approximation
Researchers have developed a novel framework for stable Q-learning using infinite-dimensional linear function approximation. This approach addresses instability issues in traditional Q-learning by preserving the Bellman…
-
New QWM Framework Enhances Reinforcement Learning with World Models
Researchers have introduced QWM, a novel framework that integrates world models with Q-learning to enhance sample efficiency in reinforcement learning. This approach uses world models for test-time search over imagined …
-
Pointer Networks with Q-Learning for Combinatorial Optimization
A research paper introduces the Pointer Q-Network (PQN), a novel neural architecture designed to improve sequence generation for combinatorial optimization tasks. The PQN integrates model-free Q-value approximation with…
-
New Q-learning method tackles overestimation bias in large action spaces
This paper addresses the overestimation bias in Q-learning, particularly within large discrete action spaces. The authors propose an "action intersection" strategy that semi-decouples Q-value estimation by allowing shar…
-
New algorithms tackle decentralized multi-player reinforcement learning
Researchers have developed new algorithms for decentralized multi-player reinforcement learning in episodic Markov Decision Processes (MDPs) with information asymmetry. The proposed methods, mQ-learning, mQ-learning-int…
-
Withdrawn paper proposed Q-learning routing for IoMT WBANs
This paper, now withdrawn, proposed QQMR, a Q-learning-based routing protocol for the Internet of Medical Things (IoMT) in wireless body area networks (WBANs). QQMR aims to address challenges like dynamic topology and e…
-
New RL algorithm optimizes laser cutting parameters, reducing time and waste
A new research paper introduces the Reinforcement Learning for Laser Cutting (RL^2C) algorithm, designed to optimize parameters for laser-based cutting of optical films. This Q-learning based approach significantly redu…
-
New framework enables online statistical inference for complex AI algorithms
Researchers have developed a novel online statistical inference framework for nonlinear stochastic approximation algorithms that utilize Markovian data. This framework establishes a functional central limit theorem for …
-
New LUQ-Learning method optimizes patient-specific treatment regimes
Researchers have developed Latent Utility Q-Learning (LUQ-Learning), a novel method for optimizing dynamic treatment regimes (DTRs) that accounts for patients' differing preferences across multiple outcomes. This approa…
-
New adaptive training controller enhances risk-aware Q-learning for financial tasks
Researchers have developed an adaptive training controller for Conditional Value-at-Risk (CVaR) risk-aware Q-learning (RaQL) to improve its stability and sample efficiency in financial applications. This controller intr…
-
New SADQ method enhances Q-learning stability in Deep Q-Networks
Researchers have introduced the Successor Rollout Aggregation Deep Q-Network (SADQ), a novel modification to Q-learning designed to improve training stability in Deep Q-Networks (DQNs). SADQ addresses the issue of DQNs …
-
Gated Q-learning offers new approach to reinforcement learning bias
Researchers have introduced Gated Q-learning, a new framework designed to address the long-standing challenge of balancing off-policy bias and sample efficiency in reinforcement learning. Unlike previous methods that fo…