{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/deep-reinforcement-learning/papers/19","list_of":"/task/deep-reinforcement-learning","task":"Deep Reinforcement Learning","archive":{"snapshot":"2025-07-28"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"repositories listed in the archive (most first), then date (newest first), then slug","page":19,"pages_in_order":59,"rows_per_page":100,"rows":[1801,1900],"of":5822,"counts":{"archive_papers_tagged":5822,"with_a_code_link":1739,"where_syntology_ran_a_sample":398,"not_listed_spam_title":0,"listed":5822,"listed_where_code_ran":398,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":340,"every_run_a_failure_of_syntologys_instrument":58,"listed_with_a_run_with_no_instrument_failure":340,"listed_every_run_a_failure_of_syntologys_instrument":58,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/task/deep-reinforcement-learning","prev":"/task/deep-reinforcement-learning/papers/18","next":"/task/deep-reinforcement-learning/papers/20","papers":[{"url":null,"slug":"time-reversal-symmetry-for-efficient-robotic","title":"Time Reversal Symmetry for Efficient Robotic Manipulations in Deep Reinforcement Learning","date":"2025-05-20","arxiv_id":"2505.13925","repositories_listed":0,"syntology":null},{"url":null,"slug":"from-grunts-to-grammar-emergent-language-from","title":"From Grunts to Grammar: Emergent Language from Cooperative Foraging","date":"2025-05-19","arxiv_id":"2505.12872","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-parameter-control-for-the-1-l-l-ga-on","title":"Multi-parameter Control for the (1+($λ$,$λ$))-GA on OneMax via Deep Reinforcement Learning","date":"2025-05-19","arxiv_id":"2505.12982","repositories_listed":0,"syntology":null},{"url":null,"slug":"lameta-intent-aware-agentic-network","title":"LAMeTA: Intent-Aware Agentic Network Optimization via a Large AI Model-Empowered Two-Stage Approach","date":"2025-05-18","arxiv_id":"2505.12247","repositories_listed":0,"syntology":null},{"url":null,"slug":"2505-10988","title":"DRL-Based Injection Molding Process Parameter Optimization for Adaptive and Profitable Production","date":"2025-05-16","arxiv_id":"2505.10988","repositories_listed":0,"syntology":null},{"url":null,"slug":"2505-10992","title":"ReaCritic: Large Reasoning Transformer-based DRL Critic-model Scaling For Heterogeneous Networks","date":"2025-05-16","arxiv_id":"2505.10992","repositories_listed":0,"syntology":null},{"url":null,"slug":"2505-11478","title":"Automatic Reward Shaping from Confounded Offline Data","date":"2025-05-16","arxiv_id":"2505.11478","repositories_listed":0,"syntology":null},{"url":null,"slug":"lifelong-reinforcement-learning-for-health","title":"Lifelong reinforcement learning for health-aware fast charging of lithium-ion batteries","date":"2025-05-16","arxiv_id":"2505.11061","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-adaptation-of-reinforcement","title":"Efficient Adaptation of Reinforcement Learning Agents to Sudden Environmental Change","date":"2025-05-15","arxiv_id":"2505.10330","repositories_listed":0,"syntology":null},{"url":null,"slug":"electric-bus-charging-schedules-relying-on","title":"Electric Bus Charging Schedules Relying on Real Data-Driven Targets Based on Hierarchical Deep Reinforcement Learning","date":"2025-05-15","arxiv_id":"2505.10262","repositories_listed":0,"syntology":null},{"url":null,"slug":"optimizing-electric-bus-charging-scheduling","title":"Optimizing Electric Bus Charging Scheduling with Uncertainties Using Hierarchical Deep Reinforcement Learning","date":"2025-05-15","arxiv_id":"2505.10296","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-practical-introduction-to-deep","title":"A Practical Introduction to Deep Reinforcement Learning","date":"2025-05-13","arxiv_id":"2505.08295","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-study-of-data-driven-methods-for-inventory","title":"A Study of Data-driven Methods for Inventory Optimization","date":"2025-05-13","arxiv_id":"2505.08673","repositories_listed":0,"syntology":null},{"url":null,"slug":"adaptive-security-policy-management-in-cloud","title":"Adaptive Security Policy Management in Cloud Environments Using Reinforcement Learning","date":"2025-05-13","arxiv_id":"2505.08837","repositories_listed":0,"syntology":null},{"url":null,"slug":"continuous-world-coverage-path-planning-for","title":"Continuous World Coverage Path Planning for Fixed-Wing UAVs using Deep Reinforcement Learning","date":"2025-05-13","arxiv_id":"2505.08382","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-reinforcement-learning-based-4","title":"Deep reinforcement learning-based longitudinal control strategy for automated vehicles at signalised intersections","date":"2025-05-13","arxiv_id":"2505.08896","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-reinforcement-learning-for-power-grid","title":"Deep Reinforcement Learning for Power Grid Multi-Stage Cascading Failure Mitigation","date":"2025-05-13","arxiv_id":"2505.09012","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-aerial-combat-tactics-through","title":"Enhancing Aerial Combat Tactics through Hierarchical Multi-Agent Reinforcement Learning","date":"2025-05-13","arxiv_id":"2505.08995","repositories_listed":0,"syntology":null},{"url":null,"slug":"leveraging-reinforcement-learning-and-koopman","title":"Leveraging Reinforcement Learning and Koopman Theory for Enhanced Model Predictive Control Performance","date":"2025-05-12","arxiv_id":"2505.08122","repositories_listed":0,"syntology":null},{"url":null,"slug":"voi-driven-joint-optimization-of-control-and","title":"VoI-Driven Joint Optimization of Control and Communication in Vehicular Digital Twin Network","date":"2025-05-12","arxiv_id":"2505.07892","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-reinforcement-learning-framework-for-4","title":"A Reinforcement Learning Framework for Application-Specific TCP Congestion-Control","date":"2025-05-11","arxiv_id":"2505.07042","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-value-of-information-towards-joint","title":"Learning Value of Information towards Joint Communication and Control in 6G V2X","date":"2025-05-11","arxiv_id":"2505.06978","repositories_listed":0,"syntology":null},{"url":null,"slug":"realistic-counterfactual-explanations-for","title":"Realistic Counterfactual Explanations for Machine Learning-Controlled Mobile Robots using 2D LiDAR","date":"2025-05-11","arxiv_id":"2505.06906","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-user-beamforming-with-deep","title":"Multi-User Beamforming with Deep Reinforcement Learning in Sensing-Aided Communication","date":"2025-05-09","arxiv_id":"2505.05956","repositories_listed":0,"syntology":null},{"url":null,"slug":"adaptive-biased-user-scheduling-for","title":"Adaptive Biased User Scheduling for Heterogeneous Wireless Federate Learning Network","date":"2025-05-08","arxiv_id":"2505.05231","repositories_listed":0,"syntology":null},{"url":null,"slug":"advancing-neural-network-verification-through","title":"Advancing Neural Network Verification through Hierarchical Safety Abstract Interpretation","date":"2025-05-08","arxiv_id":"2505.05235","repositories_listed":0,"syntology":null},{"url":null,"slug":"graph-neural-network-aided-deep-reinforcement","title":"Graph Neural Network Aided Deep Reinforcement Learning for Resource Allocation in Dynamic Terahertz UAV Networks","date":"2025-05-08","arxiv_id":"2505.04981","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-heuristic-integrated-drl-approach-for-phase","title":"A Heuristic-Integrated DRL Approach for Phase Optimization in Large-Scale RISs","date":"2025-05-07","arxiv_id":"2505.04401","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-learning-innovations-for-energy","title":"Deep Learning Innovations for Energy Efficiency: Advances in Non-Intrusive Load Monitoring and EV Charging Optimization for a Sustainable Grid","date":"2025-05-07","arxiv_id":"2505.04367","repositories_listed":0,"syntology":null},{"url":null,"slug":"energy-efficient-rsma-based-leo-satellite","title":"Energy Efficient RSMA-Based LEO Satellite Communications Assisted by UAV-Mounted BD-Active RIS: A DRL Approach","date":"2025-05-07","arxiv_id":"2505.04148","repositories_listed":0,"syntology":null},{"url":null,"slug":"trajectory-entropy-reinforcement-learning-for","title":"Trajectory Entropy Reinforcement Learning for Predictable and Robust Control","date":"2025-05-07","arxiv_id":"2505.04193","repositories_listed":0,"syntology":null},{"url":null,"slug":"integrated-sensing-computing-communication","title":"Integrated Sensing, Computing, Communication, and Control for Time-Sequence-Based Semantic Communications","date":"2025-05-06","arxiv_id":"2505.03127","repositories_listed":0,"syntology":null},{"url":null,"slug":"joint-resource-management-for-energy","title":"Joint Resource Management for Energy-efficient UAV-assisted SWIPT-MEC: A Deep Reinforcement Learning Approach","date":"2025-05-06","arxiv_id":"2505.03230","repositories_listed":0,"syntology":null},{"url":null,"slug":"sustainable-smart-farm-networks-enhancing","title":"Sustainable Smart Farm Networks: Enhancing Resilience and Efficiency with Decision Theory-Guided Deep Reinforcement Learning","date":"2025-05-06","arxiv_id":"2505.03721","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-wireless-collaborated-inference","title":"A Wireless Collaborated Inference Acceleration Framework for Plant Disease Recognition","date":"2025-05-05","arxiv_id":"2505.02877","repositories_listed":0,"syntology":null},{"url":null,"slug":"aerodynamic-and-structural-airfoil-shape","title":"Aerodynamic and structural airfoil shape optimisation via Transfer Learning-enhanced Deep Reinforcement Learning","date":"2025-05-05","arxiv_id":"2505.02634","repositories_listed":0,"syntology":null},{"url":null,"slug":"universal-approximation-theorem-of-deep-q","title":"Universal Approximation Theorem of Deep Q-Networks","date":"2025-05-04","arxiv_id":"2505.02288","repositories_listed":0,"syntology":null},{"url":null,"slug":"adaptive-drl-for-irs-mirror-orientation-in","title":"Adaptive DRL for IRS Mirror Orientation in Dynamic OWC Networks","date":"2025-05-03","arxiv_id":"2505.01818","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-reinforcement-learning-aided-frequency","title":"Deep Reinforcement Learning-Aided Frequency Control of LCC-S Resonant Converters for Wireless Power Transfer Systems","date":"2025-05-03","arxiv_id":"2505.01850","repositories_listed":0,"syntology":null},{"url":null,"slug":"integration-of-multi-mode-preference-into","title":"Integration of Multi-Mode Preference into Home Energy Management System Using Deep Reinforcement Learning","date":"2025-05-02","arxiv_id":"2505.01332","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-reinforcement-learning-for-urban-air","title":"Deep Reinforcement Learning for Urban Air Quality Management: Multi-Objective Optimization of Pollution Mitigation Booth Placement in Metropolitan Environments","date":"2025-05-01","arxiv_id":"2505.00668","repositories_listed":0,"syntology":null},{"url":null,"slug":"leveraging-partial-smiles-validation-scheme","title":"Leveraging Partial SMILES Validation Scheme for Enhanced Drug Design in Reinforcement Learning Frameworks","date":"2025-05-01","arxiv_id":"2505.00530","repositories_listed":0,"syntology":null},{"url":null,"slug":"adaptive-3d-ui-placement-in-mixed-reality","title":"Adaptive 3D UI Placement in Mixed Reality Using Deep Reinforcement Learning","date":"2025-04-30","arxiv_id":"2504.21731","repositories_listed":0,"syntology":null},{"url":null,"slug":"model-based-controller-assisted-domain","title":"Model-based controller assisted domain randomization in deep reinforcement learning: application to nonlinear powertrain control","date":"2025-04-28","arxiv_id":"2504.19715","repositories_listed":0,"syntology":null},{"url":null,"slug":"socially-aware-autonomous-driving-inferring","title":"Socially-Aware Autonomous Driving: Inferring Yielding Intentions for Safer Interactions","date":"2025-04-28","arxiv_id":"2504.20004","repositories_listed":0,"syntology":null},{"url":null,"slug":"transformation-translation-occupancy-grid","title":"Transformation & Translation Occupancy Grid Mapping: 2-Dimensional Deep Learning Refined SLAM","date":"2025-04-28","arxiv_id":"2504.19654","repositories_listed":0,"syntology":null},{"url":null,"slug":"advanced-longitudinal-control-and-collision","title":"Advanced Longitudinal Control and Collision Avoidance for High-Risk Edge Cases in Autonomous Driving","date":"2025-04-26","arxiv_id":"2504.18931","repositories_listed":0,"syntology":null},{"url":null,"slug":"two-agent-drl-for-power-allocation-and-irs","title":"Two-Agent DRL for Power Allocation and IRS Orientation in Dynamic NOMA-based OWC Networks","date":"2025-04-26","arxiv_id":"2504.18937","repositories_listed":0,"syntology":null},{"url":null,"slug":"bridging-econometrics-and-ai-var-estimation","title":"Bridging Econometrics and AI: VaR Estimation via Reinforcement Learning and GARCH Models","date":"2025-04-23","arxiv_id":"2504.16635","repositories_listed":0,"syntology":null},{"url":null,"slug":"mining-software-repositories-for-expert","title":"Mining Software Repositories for Expert Recommendation","date":"2025-04-23","arxiv_id":"2504.16343","repositories_listed":0,"syntology":null},{"url":null,"slug":"aerial-active-star-ris-assisted-satellite","title":"Aerial Active STAR-RIS-assisted Satellite-Terrestrial Covert Communications","date":"2025-04-22","arxiv_id":"2504.16146","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-general-infrastructure-and-workflow-for","title":"A General Infrastructure and Workflow for Quadrotor Deep Reinforcement Learning and Reality Deployment","date":"2025-04-21","arxiv_id":"2504.15129","repositories_listed":0,"syntology":null},{"url":null,"slug":"symmetry-preserving-architecture-for-multi","title":"Symmetry-Preserving Architecture for Multi-NUMA Environments (SPANE): A Deep Reinforcement Learning Approach for Dynamic VM Scheduling","date":"2025-04-21","arxiv_id":"2504.14946","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-reinforcement-learning-for-investor","title":"Deep Reinforcement Learning for Investor-Specific Portfolio Optimization: A Volatility-Guided Asset Selection Approach","date":"2025-04-20","arxiv_id":"2505.03760","repositories_listed":0,"syntology":null},{"url":null,"slug":"llm-enabled-in-context-learning-for-data","title":"LLM-Enabled In-Context Learning for Data Collection Scheduling in UAV-assisted Sensor Networks","date":"2025-04-20","arxiv_id":"2504.14556","repositories_listed":0,"syntology":null},{"url":null,"slug":"coordinating-spinal-and-limb-dynamics-for","title":"Coordinating Spinal and Limb Dynamics for Enhanced Sprawling Robot Mobility","date":"2025-04-18","arxiv_id":"2504.14103","repositories_listed":0,"syntology":null},{"url":null,"slug":"factor-mcls-multi-agent-learning-system-with","title":"Factor-MCLS: Multi-agent learning system with reward factor matrix and multi-critic framework for dynamic portfolio optimization","date":"2025-04-16","arxiv_id":"2504.11874","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-rollout-based-algorithm-and-reward-function","title":"A Rollout-Based Algorithm and Reward Function for Efficient Resource Allocation in Business Processes","date":"2025-04-15","arxiv_id":"2504.11250","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-communication-and-computation-trade-off","title":"The Communication and Computation Trade-off in Wireless Semantic Communications","date":"2025-04-14","arxiv_id":"2504.10357","repositories_listed":0,"syntology":null},{"url":null,"slug":"vision-based-driving-agent-for-race-car","title":"Vision based driving agent for race car simulation environments","date":"2025-04-14","arxiv_id":"2504.10266","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-champion-level-vision-based-reinforcement","title":"A Champion-level Vision-based Reinforcement Learning Agent for Competitive Racing in Gran Turismo 7","date":"2025-04-12","arxiv_id":"2504.09021","repositories_listed":0,"syntology":null},{"url":null,"slug":"graph-based-deep-reinforcement-learning-aided","title":"Graph Based Deep Reinforcement Learning Aided by Transformers for Multi-Agent Cooperation","date":"2025-04-11","arxiv_id":"2504.08195","repositories_listed":0,"syntology":null},{"url":null,"slug":"near-driven-autonomous-rover-navigation-in","title":"Near-Driven Autonomous Rover Navigation in Complex Environments: Extensions to Urban Search-and-Rescue and Industrial Inspection","date":"2025-04-11","arxiv_id":"2504.17794","repositories_listed":0,"syntology":null},{"url":null,"slug":"neural-fidelity-calibration-for-informative","title":"Neural Fidelity Calibration for Informative Sim-to-Real Adaptation","date":"2025-04-11","arxiv_id":"2504.08604","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-driven-plant-wide","title":"Reinforcement Learning-Driven Plant-Wide Refinery Planning Using Model Decomposition","date":"2025-04-11","arxiv_id":"2504.08642","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-reinforcement-learning-for-day-to-day","title":"Deep Reinforcement Learning for Day-to-day Dynamic Tolling in Tradable Credit Schemes","date":"2025-04-10","arxiv_id":"2504.08074","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-player-enjoyment-with-a-two-tier","title":"Enhancing Player Enjoyment with a Two-Tier DRL and LLM-Based Agent System for Fighting Games","date":"2025-04-10","arxiv_id":"2504.07425","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-joint-source-channel-encoding-in-irs","title":"Learning Joint Source-Channel Encoding in IRS-assisted Multi-User Semantic Communications","date":"2025-04-10","arxiv_id":"2504.07498","repositories_listed":0,"syntology":null},{"url":null,"slug":"propel-supervised-and-reinforcement-learning","title":"PROPEL: Supervised and Reinforcement Learning for Large-Scale Supply Chain Planning","date":"2025-04-10","arxiv_id":"2504.07383","repositories_listed":0,"syntology":null},{"url":null,"slug":"neuron-level-balance-between-stability-and","title":"Neuron-level Balance between Stability and Plasticity in Deep Reinforcement Learning","date":"2025-04-09","arxiv_id":"2504.08000","repositories_listed":0,"syntology":null},{"url":null,"slug":"attention-augmented-inverse-reinforcement","title":"Attention-Augmented Inverse Reinforcement Learning with Graph Convolutions for Multi-Agent Task Allocation","date":"2025-04-07","arxiv_id":"2504.05045","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-agent-deep-reinforcement-learning-for-22","title":"Multi-Agent Deep Reinforcement Learning for Multiple Anesthetics Collaborative Control","date":"2025-04-07","arxiv_id":"2504.04765","repositories_listed":0,"syntology":null},{"url":null,"slug":"physics-informed-modularized-neural-network","title":"Physics-informed Modularized Neural Network for Advanced Building Control by Deep Reinforcement Learning","date":"2025-04-07","arxiv_id":"2504.05397","repositories_listed":0,"syntology":null},{"url":null,"slug":"deliberate-planning-of-3d-bin-packing-on","title":"Deliberate Planning of 3D Bin Packing on Packing Configuration Trees","date":"2025-04-06","arxiv_id":"2504.04421","repositories_listed":0,"syntology":null},{"url":null,"slug":"economic-battery-storage-dispatch-with-deep","title":"Economic Battery Storage Dispatch with Deep Reinforcement Learning from Rule-Based Demonstrations","date":"2025-04-06","arxiv_id":"2504.04326","repositories_listed":0,"syntology":null},{"url":null,"slug":"autonomous-state-space-segmentation-for-deep","title":"Autonomous state-space segmentation for Deep-RL sparse reward scenarios","date":"2025-04-04","arxiv_id":"2504.03420","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-dual-arm-coordination-for-grasping","title":"Learning Dual-Arm Coordination for Grasping Large Flat Objects","date":"2025-04-04","arxiv_id":"2504.03500","repositories_listed":0,"syntology":null},{"url":null,"slug":"anomaly-detection-in-time-series-data-using","title":"Anomaly Detection in Time Series Data Using Reinforcement Learning, Variational Autoencoder, and Active Learning","date":"2025-04-03","arxiv_id":"2504.02999","repositories_listed":0,"syntology":null},{"url":null,"slug":"handover-and-sinr-aware-path-optimization-in","title":"Handover and SINR-Aware Path Optimization in 5G-UAV mmWave Communication using DRL","date":"2025-04-03","arxiv_id":"2504.02688","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-log-based-anomaly-detection-through","title":"Improving log-based anomaly detection through learned adaptive filter","date":"2025-04-03","arxiv_id":"2504.02994","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-and-sustainable-task-offloading-in","title":"Efficient and Sustainable Task Offloading in UAV-Assisted MEC Systems via Meta Deep Reinforcement Learning","date":"2025-04-01","arxiv_id":"2504.00453","repositories_listed":0,"syntology":null},{"url":null,"slug":"resource-allocation-for-ris-assisted-comp","title":"Resource Allocation for RIS-Assisted CoMP-NOMA Networks using Reinforcement Learning","date":"2025-04-01","arxiv_id":"2504.00975","repositories_listed":0,"syntology":null},{"url":null,"slug":"nuclear-microreactor-control-with-deep","title":"Nuclear Microreactor Control with Deep Reinforcement Learning","date":"2025-03-31","arxiv_id":"2504.00156","repositories_listed":0,"syntology":null},{"url":null,"slug":"rack-position-optimization-in-large-scale","title":"Rack Position Optimization in Large-Scale Heterogeneous Data Centers","date":"2025-03-31","arxiv_id":"2504.00277","repositories_listed":0,"syntology":null},{"url":null,"slug":"predictive-traffic-rule-compliance-using","title":"Predictive Traffic Rule Compliance using Reinforcement Learning","date":"2025-03-29","arxiv_id":"2503.22925","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-the-mistaken-assumption-of-interchangeable","title":"On the Mistaken Assumption of Interchangeable Deep Reinforcement Learning Implementations","date":"2025-03-28","arxiv_id":"2503.22575","repositories_listed":0,"syntology":null},{"url":null,"slug":"robust-deep-reinforcement-learning-in","title":"Robust Deep Reinforcement Learning in Robotics via Adaptive Gradient-Masked Adversarial Attacks","date":"2025-03-26","arxiv_id":"2503.20844","repositories_listed":0,"syntology":null},{"url":null,"slug":"state-aware-perturbation-optimization-for","title":"State-Aware Perturbation Optimization for Robust Deep Reinforcement Learning","date":"2025-03-26","arxiv_id":"2503.20613","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-agent-deep-reinforcement-learning-for-20","title":"Multi-Agent Deep Reinforcement Learning for Safe Autonomous Driving with RICS-Assisted MEC","date":"2025-03-25","arxiv_id":"2503.19418","repositories_listed":0,"syntology":null},{"url":null,"slug":"adventurer-exploration-with-bigan-for-deep","title":"Adventurer: Exploration with BiGAN for Deep Reinforcement Learning","date":"2025-03-24","arxiv_id":"2503.18612","repositories_listed":0,"syntology":null},{"url":null,"slug":"cae-repurposing-the-critic-as-an-explorer-in","title":"CAE: Repurposing the Critic as an Explorer in Deep Reinforcement Learning","date":"2025-03-23","arxiv_id":"2503.18980","repositories_listed":0,"syntology":null},{"url":null,"slug":"iterative-multi-agent-reinforcement-learning","title":"Iterative Multi-Agent Reinforcement Learning: A Novel Approach Toward Real-World Multi-Echelon Inventory Optimization","date":"2025-03-23","arxiv_id":"2503.18201","repositories_listed":0,"syntology":null},{"url":null,"slug":"optimizing-navigation-and-chemical","title":"Optimizing Navigation And Chemical Application in Precision Agriculture With Deep Reinforcement Learning And Conditional Action Tree","date":"2025-03-23","arxiv_id":"2503.17985","repositories_listed":0,"syntology":null},{"url":null,"slug":"bandwidth-reservation-for-time-critical","title":"Bandwidth Reservation for Time-Critical Vehicular Applications: A Multi-Operator Environment","date":"2025-03-22","arxiv_id":"2503.17756","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-new-segment-routing-method-with-swap-node","title":"A New Segment Routing method with Swap Node Selection Strategy Based on Deep Reinforcement Learning for Software Defined Network","date":"2025-03-21","arxiv_id":"2503.16914","repositories_listed":0,"syntology":null},{"url":null,"slug":"lamour-leveraging-language-models-for-out-of","title":"LaMOuR: Leveraging Language Models for Out-of-Distribution Recovery in Reinforcement Learning","date":"2025-03-21","arxiv_id":"2503.17125","repositories_listed":0,"syntology":null},{"url":null,"slug":"optimizing-2d-1-packing-in-constrained","title":"Optimizing 2D+1 Packing in Constrained Environments Using Deep Reinforcement Learning","date":"2025-03-21","arxiv_id":"2503.17573","repositories_listed":0,"syntology":null},{"url":null,"slug":"active-management-of-battery-degradation-in","title":"Active management of battery degradation in wireless sensor network using deep reinforcement learning for group battery replacement","date":"2025-03-20","arxiv_id":"2503.15865","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-agent-actor-critic-with-harmonic","title":"Multi-Agent Actor-Critic with Harmonic Annealing Pruning for Dynamic Spectrum Access Systems","date":"2025-03-19","arxiv_id":"2503.15172","repositories_listed":0,"syntology":null},{"url":null,"slug":"colson-controllable-learning-based-social","title":"COLSON: Controllable Learning-Based Social Navigation via Diffusion-Based Reinforcement Learning","date":"2025-03-18","arxiv_id":"2503.13934","repositories_listed":0,"syntology":null}],"record_sha256":"7f988fc4cbcc8b69bea106369153f8f69aa17906e9005f01f75754323a7123f7","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}