deep reinforcement learning
PulseAugur coverage of deep reinforcement learning — every cluster mentioning deep reinforcement learning across labs, papers, and developer communities, ranked by signal.
11 day(s) with sentiment data
-
AI weather prediction framework uses reinforcement learning to coordinate specialist models
Researchers have developed a new framework called FTAE-Weather that uses deep reinforcement learning to improve weather prediction accuracy. Instead of creating a single, monolithic AI model, FTAE-Weather coordinates a …
-
New DRL approach enables robot control across diverse configurations
Researchers have developed a novel deep reinforcement learning (DRL) approach for controlling cable-driven parallel robots (CDPRs) that generalizes across different configurations. This method trains an actuator-level p…
-
Reinforcement learning agents struggle with partial observability due to critic bias
A new analysis of reinforcement learning agents under partial observability reveals that learning performance suffers more than previously attributed to policy limitations. Researchers found that even when an optimal po…
-
Deep Reinforcement Learning Optimizes Truck Routing, Cuts Costs by 10%
This paper explores the application of deep reinforcement learning (DRL) to solve the complex Vehicle Routing Problem (VRP) in the logistics industry. It presents a case study focusing on truck network design for three …
-
New AI method uses LLMs to initialize reinforcement learning agents
Researchers have introduced ProDVI, a novel framework designed to enhance the sample efficiency of deep reinforcement learning agents. ProDVI utilizes large language models to generate Python code that hypothesizes envi…
-
New framework bridges AI and power engineering education · 2 sources tracked
A new framework, Engineering-Grounded AI (EGAI), has been developed to integrate artificial intelligence into power and energy systems education. This framework, presented as a collection of open, executable Jupyter not…
-
AI framework integrates logistics routing and dispatching for efficiency
Researchers have developed a new framework to optimize last-mile pickup operations in logistics by integrating order dispatching and routing decisions. This approach uses a Dynamic-Residual Graph Attention Network for r…
-
Deep Reinforcement Learning Enhances Quantum State Preparation Accuracy
Researchers have developed a novel framework utilizing deep reinforcement learning, specifically Proximal Policy Optimization (PPO), to tackle the complex challenge of approximate quantum state preparation (QSP). This a…
-
New MAPS architecture enhances autonomous vehicle coordination at intersections
Researchers have developed the Master-Agent Proto-plan System (MAPS), a novel hierarchical deep reinforcement learning architecture designed to improve coordination among autonomous vehicles at unsignalized intersection…
-
LLM-DRL Hybrid Navigates UAVs in Complex Networks
Researchers have developed a new hierarchical control framework for Uncrewed Aerial Vehicles (UAVs) navigating complex Integrated Terrestrial and Non-Terrestrial Networks (ITNTNs). This system combines the strategic rea…
-
AI policies transformed into readable Prolog programs for enhanced explainability
Researchers have developed a novel three-stage process to transform deep reinforcement learning policies into executable Prolog programs. This method aims to make complex AI models more interpretable by converting their…
-
New algorithm synthesizes formally verified control policies for autonomous systems
Researchers have developed SMC-ES, a new algorithm that integrates Evolutionary Strategies with Statistical Model Checking to automatically synthesize control policies for autonomous systems. This method provides formal…
-
Deep Reinforcement Learning Automates Orthodontic Tooth Alignment Planning
Researchers have developed a novel deep reinforcement learning framework to automate the planning of 3D geometric tooth alignment trajectories for digital orthodontics. The system formulates the planning as a Markov Dec…
-
Deep Reinforcement Learning Tackles Time-Lag Scheduling in Module Factories
Researchers have developed a novel time-lag-aware deep reinforcement learning approach to optimize scheduling in prefabricated module factories. This method specifically addresses the significant delays caused by post-o…
-
Coding agents offer interpretable alternative to DRL for active flow control
Researchers have developed a new method for active flow control that utilizes coding agents to search for explicit feedback laws, moving away from traditional deep reinforcement learning (DRL) approaches. This heuristic…
-
New PR-MRE concept enhances AI strategy robustness in adversarial games
Researchers have introduced a new equilibrium concept called Probabilistically Robust Minimax-Regret Equilibrium (PR-MRE) to address challenges in adversarial team games with asymmetric information. This concept combine…
-
New dataset and benchmark advance UAV active object detection
Researchers have introduced ATRNet-LUDO, a new large-scale dataset and benchmark designed to advance active object detection for unmanned aerial vehicles (UAVs). The dataset comprises over 121,000 aerial images and 1.21…
-
New defense system ORAN-DEFEND targets backdoor attacks in Open RAN
Researchers have developed ORAN-DEFEND, a new system designed to protect Open Radio Access Networks (O-RAN) from backdoor attacks embedded in third-party deep reinforcement learning (DRL) xApps. This defense mechanism o…
-
New theory tackles plasticity loss in AI for video streaming
Researchers have introduced the Silent Neuron Theory to address the issue of plasticity loss in deep reinforcement learning models used for adaptive video streaming. This theory posits that existing metrics for dormant …
-
Deep Reinforcement Learning Optimizes Portfolio Risk-Return
Researchers have developed a novel deep reinforcement learning framework, MORP-DRL, designed to optimize investment portfolios by considering both expected return and downside risk. This framework integrates variance, C…