Deep Q-Network
PulseAugur coverage of Deep Q-Network — every cluster mentioning Deep Q-Network across labs, papers, and developer communities, ranked by signal.
6 day(s) with sentiment data
-
New research revisits action factorization for complex RL spaces · 2 sources tracked
A new research paper explores methods for handling complex action spaces in reinforcement learning, particularly those that combine discrete and continuous actions. The study analyzes various factorization techniques ac…
-
New AI method optimizes additive manufacturing with attention-based RL
Researchers have developed a novel approach to optimize additive manufacturing processes by integrating a multi-head attention mechanism with the Soft Actor-Critic (SAC) algorithm. This method addresses limitations in t…
-
New theory advances Q-learning in continuous stochastic control
Researchers have published a paper on arXiv detailing a theoretical advancement in Q-learning, a fundamental algorithm in reinforcement learning. The study focuses on the mathematical underpinnings of Q-learning within …
-
Active Inference Controller Optimizes Traffic Signals in Challenging Environments
Researchers have developed an active inference controller for traffic signal management in noisy and unpredictable IoT environments. This controller dynamically selects signal phases by minimizing expected free energy, …
-
New betting strategy enhances anytime-valid statistical testing
Researchers have developed a new method for anytime-valid testing that accounts for deadlines and the amount of data available. This approach, framed as a horizon-aware betting problem, uses a Deep Reinforcement Learnin…
-
Deep RL algorithms learn distinct representational invariances
Researchers have analyzed deep reinforcement learning representations using MDP reduction theory, finding that different algorithms learn distinct types of invariances. Specifically, DQN learns representations invariant…
-
New O-RAN framework uses AI to combat jamming for low-latency networks
This paper introduces a new framework for managing radio resource allocation in Open RAN environments, specifically addressing the challenge of adversarial jamming that can disrupt latency-critical network slices. The p…
-
DRL algorithms struggle to outperform calibrated baselines in resource control benchmarks
A new benchmark study, RLScale-Bench, has been developed to evaluate deep reinforcement learning (DRL) algorithms for adaptive resource control. The research found that a properly calibrated rule-based autoscaler often …
-
New ASTRO framework uses RL and GNNs for cyber-physical anomaly detection
Researchers have developed ASTRO, a new anomaly detection framework for cyber-physical systems that utilizes reinforcement learning and Graph Neural Networks. ASTRO dynamically optimizes decision boundaries by integrati…
-
Quantum Frog game shows cooperation improves agent success
Researchers have developed a new cooperative game called Quantum Frog, inspired by Frogger, which uses a quantized-time mechanic where the environment only advances when a player acts. Using reinforcement learning, they…
-
Meta-learning framework accelerates control system adaptation with limited data
Researchers have developed a novel meta-learning framework for designing optimal controllers for uncertain nonlinear systems, particularly when target system data is scarce. This approach leverages offline data from sim…
-
New research challenges independence assumption in Deep Q-Learning algorithms
Researchers have developed a new statistical analysis for Deep Q-Networks (DQN) that accounts for temporal dependence in training data. This approach models minibatches as $\tau$-mixing, moving beyond the typical assump…
-
NaviGNN AI framework optimizes sustainable mobility in futuristic smart cities
Researchers have developed NaviGNN, a novel AI system designed to optimize mobility in futuristic smart cities with complex vertical and linear structures. This system integrates multi-agent reinforcement learning and g…
-
Reinforcement learning enhances autonomous target tracking accuracy and robustness
Researchers have developed a deep reinforcement learning approach for autonomous bearings-only tracking of moving targets. The system formulates the observer maneuver problem as a belief Markov decision process, using a…
-
AI routing framework boosts LEO satellite network performance and efficiency
Researchers have developed a novel spatial-temporal learning-based distributed routing framework designed for dynamic Low Earth Orbit (LEO) satellite networks. This framework integrates Graph Attention Networks (GAT) an…
-
DRL framework optimizes NR-U/Wi-Fi coexistence for fairness and throughput
Researchers have developed a policy-driven deep reinforcement learning framework to manage resource allocation between NR-U and Wi-Fi networks operating in unlicensed spectrum. This framework uses a deep Q-network to le…
-
New C++ engine HASE achieves 33M steps/sec for multi-agent RL training
Researchers have developed a new C++ engine called Hide-And-Seek-Engine (HASE) designed to significantly improve the efficiency of training reinforcement learning agents in decentralized, partially observable environmen…
-
LLMs fine-tuned for traffic control with critic-guided reinforcement learning
Researchers have developed DGLight, a novel framework that fine-tunes large language models for traffic signal control. This approach utilizes a Deep Q-Network critic to guide the optimization process, enabling the mode…
-
OpenAI and researchers reveal AI vulnerabilities to adversarial attacks
OpenAI researchers are exploring the transferability of adversarial robustness across different types of perturbations in neural networks. Their findings indicate that robustness against one perturbation type does not a…