{"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/29","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":29,"pages_in_order":59,"rows_per_page":100,"rows":[2801,2900],"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/28","next":"/task/deep-reinforcement-learning/papers/30","papers":[{"url":null,"slug":"ai-on-the-water-applying-drl-to-autonomous","title":"AI on the Water: Applying DRL to Autonomous Vessel Navigation","date":"2023-10-23","arxiv_id":"2310.14938","repositories_listed":0,"syntology":null},{"url":null,"slug":"comparison-of-path-following-in-ships-using","title":"Comparison of path following in ships using modern and traditional controllers","date":"2023-10-23","arxiv_id":"2310.14940","repositories_listed":0,"syntology":null},{"url":null,"slug":"diverse-priors-for-deep-reinforcement","title":"Diverse Priors for Deep Reinforcement Learning","date":"2023-10-23","arxiv_id":"2310.14864","repositories_listed":0,"syntology":null},{"url":null,"slug":"navigating-the-ocean-with-drl-path-following","title":"Navigating the Ocean with DRL: Path following for marine vessels","date":"2023-10-23","arxiv_id":"2310.14932","repositories_listed":0,"syntology":null},{"url":null,"slug":"one-is-more-diverse-perspectives-within-a","title":"One is More: Diverse Perspectives within a Single Network for Efficient DRL","date":"2023-10-21","arxiv_id":"2310.14009","repositories_listed":0,"syntology":null},{"url":null,"slug":"cooperative-multi-agent-deep-reinforcement-2","title":"Cooperative Multi-Agent Deep Reinforcement Learning for Adaptive Decentralized Emergency Voltage Control","date":"2023-10-20","arxiv_id":"2310.13577","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-reinforcement-learning-enabled-adaptive","title":"Deep Reinforcement Learning-Enabled Adaptive Forecasting-Aided State Estimation in Distribution Systems with Multi-Source Multi-Rate Data","date":"2023-10-20","arxiv_id":"2310.13218","repositories_listed":0,"syntology":null},{"url":null,"slug":"interpretable-deep-reinforcement-learning-for-1","title":"Interpretable Deep Reinforcement Learning for Optimizing Heterogeneous Energy Storage Systems","date":"2023-10-20","arxiv_id":"2310.14783","repositories_listed":0,"syntology":null},{"url":null,"slug":"pathrl-an-end-to-end-path-generation-method","title":"PathRL: An End-to-End Path Generation Method for Collision Avoidance via Deep Reinforcement Learning","date":"2023-10-20","arxiv_id":"2310.13295","repositories_listed":0,"syntology":null},{"url":null,"slug":"reward-shaping-for-happier-autonomous-cyber","title":"Reward Shaping for Happier Autonomous Cyber Security Agents","date":"2023-10-20","arxiv_id":"2310.13565","repositories_listed":0,"syntology":null},{"url":null,"slug":"robust-training-for-conversational-question","title":"Robust Training for Conversational Question Answering Models with Reinforced Reformulation Generation","date":"2023-10-20","arxiv_id":"2310.13505","repositories_listed":0,"syntology":null},{"url":null,"slug":"dynamic-resource-management-in-integrated","title":"Dynamic Resource Management in Integrated NOMA Terrestrial-Satellite Networks using Multi-Agent Reinforcement Learning","date":"2023-10-18","arxiv_id":"2310.11814","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-to-solve-climate-sensor-placement","title":"Learning to Optimise Climate Sensor Placement using a Transformer","date":"2023-10-18","arxiv_id":"2310.12387","repositories_listed":0,"syntology":null},{"url":null,"slug":"keep-various-trajectories-promoting","title":"Keep Various Trajectories: Promoting Exploration of Ensemble Policies in Continuous Control","date":"2023-10-17","arxiv_id":"2310.11138","repositories_listed":0,"syntology":null},{"url":null,"slug":"sim-to-real-transfer-of-adaptive-control","title":"Sim-to-Real Transfer of Adaptive Control Parameters for AUV Stabilization under Current Disturbance","date":"2023-10-17","arxiv_id":"2310.11075","repositories_listed":0,"syntology":null},{"url":null,"slug":"joint-optimization-of-traffic-signal-control","title":"Joint Optimization of Traffic Signal Control and Vehicle Routing in Signalized Road Networks using Multi-Agent Deep Reinforcement Learning","date":"2023-10-16","arxiv_id":"2310.10856","repositories_listed":0,"syntology":null},{"url":null,"slug":"leveraging-topological-maps-in-deep","title":"Leveraging Topological Maps in Deep Reinforcement Learning for Multi-Object Navigation","date":"2023-10-16","arxiv_id":"2310.10250","repositories_listed":0,"syntology":null},{"url":null,"slug":"unlocking-metasurface-practicality-for-b5g","title":"Unlocking Metasurface Practicality for B5G Networks: AI-assisted RIS Planning","date":"2023-10-16","arxiv_id":"2310.10330","repositories_listed":0,"syntology":null},{"url":null,"slug":"alpha-elimination-using-deep-reinforcement","title":"Alpha Elimination: Using Deep Reinforcement Learning to Reduce Fill-In during Sparse Matrix Decomposition","date":"2023-10-15","arxiv_id":"2310.09852","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-reinforcement-learning-with-explicit","title":"Deep Reinforcement Learning with Explicit Context Representation","date":"2023-10-15","arxiv_id":"2310.09924","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-blockchain-empowered-multi-aggregator","title":"A Blockchain-empowered Multi-Aggregator Federated Learning Architecture in Edge Computing with Deep Reinforcement Learning Optimization","date":"2023-10-14","arxiv_id":"2310.09665","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-semantic-communication-protocols-for","title":"Towards Semantic Communication Protocols for 6G: From Protocol Learning to Language-Oriented Approaches","date":"2023-10-14","arxiv_id":"2310.09506","repositories_listed":0,"syntology":null},{"url":null,"slug":"community-membership-hiding-as-counterfactual","title":"Evading Community Detection via Counterfactual Neighborhood Search","date":"2023-10-13","arxiv_id":"2310.08909","repositories_listed":0,"syntology":null},{"url":null,"slug":"optimal-scheduling-of-electric-vehicle","title":"Optimal Scheduling of Electric Vehicle Charging with Deep Reinforcement Learning considering End Users Flexibility","date":"2023-10-13","arxiv_id":"2310.09040","repositories_listed":0,"syntology":null},{"url":null,"slug":"beyond-traditional-doe-deep-reinforcement","title":"Beyond Traditional DoE: Deep Reinforcement Learning for Optimizing Experiments in Model Identification of Battery Dynamics","date":"2023-10-12","arxiv_id":"2310.08198","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-of-display-transfer","title":"Reinforcement Learning of Display Transfer Robots in Glass Flow Control Systems: A Physical Simulation-Based Approach","date":"2023-10-12","arxiv_id":"2310.07981","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-reinforcement-learning-for-autonomous-5","title":"Deep Reinforcement Learning for Autonomous Cyber Defence: A Survey","date":"2023-10-11","arxiv_id":"2310.07745","repositories_listed":0,"syntology":null},{"url":null,"slug":"deepref-deep-reinforcement-learning-for-video","title":"DeePref: Deep Reinforcement Learning For Video Prefetching In Content Delivery Networks","date":"2023-10-11","arxiv_id":"2310.07881","repositories_listed":0,"syntology":null},{"url":null,"slug":"explainable-attention-for-few-shot-learning","title":"Language-Guided Reinforcement Learning for Hard Attention in Few-Shot Learning","date":"2023-10-11","arxiv_id":"2310.07800","repositories_listed":0,"syntology":null},{"url":null,"slug":"logic-guided-deep-reinforcement-learning-for","title":"Logic-Q: Improving Deep Reinforcement Learning-based Quantitative Trading via Program Sketch-based Tuning","date":"2023-10-09","arxiv_id":"2310.05551","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-double-descent-in-reinforcement-learning","title":"On Double Descent in Reinforcement Learning with LSTD and Random Features","date":"2023-10-09","arxiv_id":"2310.05518","repositories_listed":0,"syntology":null},{"url":null,"slug":"predictive-auxiliary-objectives-in-deep-rl","title":"Predictive auxiliary objectives in deep RL mimic learning in the brain","date":"2023-10-09","arxiv_id":"2310.06089","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-new-economic-and-financial-theory-of-money","title":"A new economic and financial theory of money","date":"2023-10-08","arxiv_id":"2310.04986","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-reinforcement-learning-based-cross-layer","title":"Deep Reinforcement Learning Based Cross-Layer Design in Terahertz Mesh Backhaul Networks","date":"2023-10-08","arxiv_id":"2310.05034","repositories_listed":0,"syntology":null},{"url":null,"slug":"fully-spiking-neural-network-for-legged","title":"Fully Spiking Neural Network for Legged Robots","date":"2023-10-08","arxiv_id":"2310.05022","repositories_listed":0,"syntology":null},{"url":null,"slug":"intelligent-drl-based-adaptive-region-of","title":"Intelligent DRL-Based Adaptive Region of Interest for Delay-sensitive Telemedicine Applications","date":"2023-10-08","arxiv_id":"2310.05099","repositories_listed":0,"syntology":null},{"url":null,"slug":"digital-twin-assisted-deep-reinforcement","title":"Digital Twin Assisted Deep Reinforcement Learning for Online Admission Control in Sliced Network","date":"2023-10-07","arxiv_id":"2310.09299","repositories_listed":0,"syntology":null},{"url":null,"slug":"adjustable-robust-reinforcement-learning-for","title":"Adjustable Robust Reinforcement Learning for Online 3D Bin Packing","date":"2023-10-06","arxiv_id":"2310.04323","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-review-of-deep-reinforcement-learning-in","title":"A Review of Deep Reinforcement Learning in Serverless Computing: Function Scheduling and Resource Auto-Scaling","date":"2023-10-05","arxiv_id":"2311.12839","repositories_listed":0,"syntology":null},{"url":null,"slug":"how-the-level-sampling-process-impacts-zero","title":"How the level sampling process impacts zero-shot generalisation in deep reinforcement learning","date":"2023-10-05","arxiv_id":"2310.03494","repositories_listed":0,"syntology":null},{"url":null,"slug":"pydcm-custom-data-center-models-with","title":"PyDCM: Custom Data Center Models with Reinforcement Learning for Sustainability","date":"2023-10-05","arxiv_id":"2310.03906","repositories_listed":0,"syntology":null},{"url":null,"slug":"small-batch-deep-reinforcement-learning","title":"Small batch deep reinforcement learning","date":"2023-10-05","arxiv_id":"2310.03882","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-reinforcement-learning-algorithms-for","title":"Deep Reinforcement Learning Algorithms for Hybrid V2X Communication: A Benchmarking Study","date":"2023-10-04","arxiv_id":"2310.03767","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-reinforcement-learning-for-machine","title":"Deep reinforcement learning for machine scheduling: Methodology, the state-of-the-art, and future directions","date":"2023-10-04","arxiv_id":"2310.03195","repositories_listed":0,"syntology":null},{"url":null,"slug":"mathcal-b-coder-value-based-deep","title":"$\\mathcal{B}$-Coder: Value-Based Deep Reinforcement Learning for Program Synthesis","date":"2023-10-04","arxiv_id":"2310.03173","repositories_listed":0,"syntology":null},{"url":null,"slug":"neural-architecture-impact-on-identifying","title":"Neural architecture impact on identifying temporally extended Reinforcement Learning tasks","date":"2023-10-04","arxiv_id":"2310.03161","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-deep-reinforcement-learning-approach-for-15","title":"A Deep Reinforcement Learning Approach for Interactive Search with Sentence-level Feedback","date":"2023-10-03","arxiv_id":"2310.03043","repositories_listed":0,"syntology":null},{"url":null,"slug":"cad-clustering-and-deep-reinforcement","title":"CAD: Clustering And Deep Reinforcement Learning Based Multi-Period Portfolio Management Strategy","date":"2023-10-02","arxiv_id":"2310.01319","repositories_listed":0,"syntology":null},{"url":null,"slug":"solving-the-quadratic-assignment-problem","title":"Solving the Quadratic Assignment Problem using Deep Reinforcement Learning","date":"2023-10-02","arxiv_id":"2310.01604","repositories_listed":0,"syntology":null},{"url":null,"slug":"controlling-neural-style-transfer-with-deep","title":"Controlling Neural Style Transfer with Deep Reinforcement Learning","date":"2023-09-30","arxiv_id":"2310.00405","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-reinforcement-learning-for-autonomous-6","title":"Deep Reinforcement Learning for Autonomous Vehicle Intersection Navigation","date":"2023-09-30","arxiv_id":"2310.08595","repositories_listed":0,"syntology":null},{"url":null,"slug":"reliability-quantification-of-deep","title":"Reliability Quantification of Deep Reinforcement Learning-based Control","date":"2023-09-29","arxiv_id":"2309.16977","repositories_listed":0,"syntology":null},{"url":null,"slug":"trandrl-a-transformer-driven-deep","title":"TranDRL: A Transformer-Driven Deep Reinforcement Learning Enabled Prescriptive Maintenance Framework","date":"2023-09-29","arxiv_id":"2309.16935","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-learning-in-deterministic-computational","title":"Deep Learning in Deterministic Computational Mechanics","date":"2023-09-27","arxiv_id":"2309.15421","repositories_listed":0,"syntology":null},{"url":null,"slug":"residual-scheduling-a-new-reinforcement","title":"Residual Scheduling: A New Reinforcement Learning Approach to Solving Job Shop Scheduling Problem","date":"2023-09-27","arxiv_id":"2309.15517","repositories_listed":0,"syntology":null},{"url":null,"slug":"age-minimization-in-massive-iot-via-uav-swarm","title":"Age Minimization in Massive IoT via UAV Swarm: A Multi-agent Reinforcement Learning Approach","date":"2023-09-26","arxiv_id":"2309.14757","repositories_listed":0,"syntology":null},{"url":null,"slug":"gray-box-adversarial-attack-of-deep","title":"Gray-box Adversarial Attack of Deep Reinforcement Learning-based Trading Agents","date":"2023-09-26","arxiv_id":"2309.14615","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-based-latency-constrained-fronthaul","title":"Constrained Deep Reinforcement Learning for Fronthaul Compression Optimization","date":"2023-09-26","arxiv_id":"2309.15060","repositories_listed":0,"syntology":null},{"url":null,"slug":"v2x-lead-lidar-based-end-to-end-autonomous","title":"V2X-Lead: LiDAR-based End-to-End Autonomous Driving with Vehicle-to-Everything Communication Integration","date":"2023-09-26","arxiv_id":"2309.15252","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-reinforcement-learning-for-the-heat","title":"Deep Reinforcement Learning for the Heat Transfer Control of Pulsating Impinging Jets","date":"2023-09-25","arxiv_id":"2309.13955","repositories_listed":0,"syntology":null},{"url":null,"slug":"implicit-sensing-in-traffic-optimization","title":"Implicit Sensing in Traffic Optimization: Advanced Deep Reinforcement Learning Techniques","date":"2023-09-25","arxiv_id":"2309.14395","repositories_listed":0,"syntology":null},{"url":null,"slug":"collision-avoidance-and-navigation-for-a","title":"Collision Avoidance and Navigation for a Quadrotor Swarm Using End-to-end Deep Reinforcement Learning","date":"2023-09-23","arxiv_id":"2309.13285","repositories_listed":0,"syntology":null},{"url":null,"slug":"diagnosing-and-exploiting-the-computational","title":"Diagnosing and exploiting the computational demands of videos games for deep reinforcement learning","date":"2023-09-22","arxiv_id":"2309.13181","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-actions-and-control-of-focus-of","title":"Learning Actions and Control of Focus of Attention with a Log-Polar-like Sensor","date":"2023-09-22","arxiv_id":"2309.12634","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-reinforcement-learning-for-backscatter-1","title":"Deep Reinforcement Learning for Backscatter Communications: Augmenting Intelligence in Future Internet of Things","date":"2023-09-21","arxiv_id":"2309.12507","repositories_listed":0,"syntology":null},{"url":null,"slug":"improve-the-efficiency-of-deep-reinforcement","title":"Improve the efficiency of deep reinforcement learning through semantic exploration guided by natural language","date":"2023-09-21","arxiv_id":"2309.11753","repositories_listed":0,"syntology":null},{"url":null,"slug":"ai-driven-patient-monitoring-with-multi-agent","title":"Adaptive Multi-Agent Deep Reinforcement Learning for Timely Healthcare Interventions","date":"2023-09-20","arxiv_id":"2309.10980","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-reinforcement-learning-for-infinite","title":"Deep Reinforcement Learning for Infinite Horizon Mean Field Problems in Continuous Spaces","date":"2023-09-19","arxiv_id":"2309.10953","repositories_listed":0,"syntology":null},{"url":null,"slug":"pdrl-multi-agent-based-reinforcement-learning","title":"PDRL: Multi-Agent based Reinforcement Learning for Predictive Monitoring","date":"2023-09-19","arxiv_id":"2309.10576","repositories_listed":0,"syntology":null},{"url":null,"slug":"task-graph-offloading-via-deep-reinforcement","title":"Task Graph offloading via Deep Reinforcement Learning in Mobile Edge Computing","date":"2023-09-19","arxiv_id":"2309.10569","repositories_listed":0,"syntology":null},{"url":null,"slug":"adaptive-liquidity-provision-in-uniswap-v3","title":"Adaptive Liquidity Provision in Uniswap V3 with Deep Reinforcement Learning","date":"2023-09-18","arxiv_id":"2309.10129","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-reinforcement-learning-for-the-joint","title":"Deep Reinforcement Learning for the Joint Control of Traffic Light Signaling and Vehicle Speed Advice","date":"2023-09-18","arxiv_id":"2309.09881","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-agent-deep-reinforcement-learning-for-14","title":"Multi-Agent Deep Reinforcement Learning for Cooperative and Competitive Autonomous Vehicles using AutoDRIVE Ecosystem","date":"2023-09-18","arxiv_id":"2309.10007","repositories_listed":0,"syntology":null},{"url":null,"slug":"self-sustaining-multiple-access-with-1","title":"Self-Sustaining Multiple Access with Continual Deep Reinforcement Learning for Dynamic Metaverse Applications","date":"2023-09-18","arxiv_id":"2309.10177","repositories_listed":0,"syntology":null},{"url":null,"slug":"sim-to-real-deep-reinforcement-learning-with","title":"Sim-to-Real Deep Reinforcement Learning with Manipulators for Pick-and-place","date":"2023-09-17","arxiv_id":"2309.09247","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-reinforcement-learning-for-efficient-and","title":"Deep Reinforcement Learning for Efficient and Fair Allocation of Health Care Resources","date":"2023-09-15","arxiv_id":"2309.08560","repositories_listed":0,"syntology":null},{"url":null,"slug":"attention-loss-adjusted-prioritized","title":"Attention Loss Adjusted Prioritized Experience Replay","date":"2023-09-13","arxiv_id":"2309.06684","repositories_listed":0,"syntology":null},{"url":null,"slug":"fidelity-induced-interpretable-policy","title":"Fidelity-Induced Interpretable Policy Extraction for Reinforcement Learning","date":"2023-09-12","arxiv_id":"2309.06097","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-drl-based-reflection-enhancement-method-for","title":"A DRL-based Reflection Enhancement Method for RIS-assisted Multi-receiver Communications","date":"2023-09-11","arxiv_id":"2309.05343","repositories_listed":0,"syntology":null},{"url":null,"slug":"finding-influencers-in-complex-networks-an","title":"Finding Influencers in Complex Networks: An Effective Deep Reinforcement Learning Approach","date":"2023-09-09","arxiv_id":"2309.07153","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-reinforcement-learning-enabled-joint","title":"Deep Reinforcement Learning Enabled Joint Deployment and Beamforming in STAR-RIS Assisted Networks","date":"2023-09-07","arxiv_id":"2309.03520","repositories_listed":0,"syntology":null},{"url":null,"slug":"marketing-budget-allocation-with-offline","title":"Marketing Budget Allocation with Offline Constrained Deep Reinforcement Learning","date":"2023-09-06","arxiv_id":"2309.02669","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-reducing-undesirable-behavior-in-deep","title":"On Reducing Undesirable Behavior in Deep Reinforcement Learning Models","date":"2023-09-06","arxiv_id":"2309.02869","repositories_listed":0,"syntology":null},{"url":null,"slug":"personalized-federated-deep-reinforcement","title":"Personalized Federated Deep Reinforcement Learning-based Trajectory Optimization for Multi-UAV Assisted Edge Computing","date":"2023-09-05","arxiv_id":"2309.02193","repositories_listed":0,"syntology":null},{"url":null,"slug":"active-flow-control-for-three-dimensional","title":"Active flow control for three-dimensional cylinders through deep reinforcement learning","date":"2023-09-04","arxiv_id":"2309.02462","repositories_listed":0,"syntology":null},{"url":null,"slug":"hawkeye-change-targeted-testing-for-android","title":"Hawkeye: Change-targeted Testing for Android Apps based on Deep Reinforcement Learning","date":"2023-09-04","arxiv_id":"2309.01519","repositories_listed":0,"syntology":null},{"url":null,"slug":"looptune-optimizing-tensor-computations-with","title":"LoopTune: Optimizing Tensor Computations with Reinforcement Learning","date":"2023-09-04","arxiv_id":"2309.01825","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-survey-on-service-route-and-time-prediction","title":"A Survey on Service Route and Time Prediction in Instant Delivery: Taxonomy, Progress, and Prospects","date":"2023-09-03","arxiv_id":"2309.01194","repositories_listed":0,"syntology":null},{"url":null,"slug":"how-does-forecasting-affect-the-convergence","title":"How Does Forecasting Affect the Convergence of DRL Techniques in O-RAN Slicing?","date":"2023-09-01","arxiv_id":"2309.00489","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-agent-deeprl-based-joint-power-and","title":"Multi Agent DeepRL based Joint Power and Subchannel Allocation in IAB networks","date":"2023-08-31","arxiv_id":"2309.00144","repositories_listed":0,"syntology":null},{"url":null,"slug":"physics-based-trajectory-design-for-cellular","title":"Physics-Based Trajectory Design for Cellular-Connected UAV in Rainy Environments Based on Deep Reinforcement Learning","date":"2023-08-31","arxiv_id":"2309.00017","repositories_listed":0,"syntology":null},{"url":null,"slug":"adversarial-style-transfer-for-robust-policy-1","title":"Adversarial Style Transfer for Robust Policy Optimization in Deep Reinforcement Learning","date":"2023-08-29","arxiv_id":"2308.15550","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-reinforcement-learning-based-framework","title":"Deep Reinforcement Learning Based Framework for Mobile Energy Disseminator Dispatching to Charge On-the-Road Electric Vehicles","date":"2023-08-29","arxiv_id":"2308.15656","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-reinforcement-learning-for-uplink","title":"Deep Reinforcement Learning for Uplink Scheduling in NOMA-URLLC Networks","date":"2023-08-28","arxiv_id":"2308.14523","repositories_listed":0,"syntology":null},{"url":null,"slug":"optimal-economic-gas-turbine-dispatch-with","title":"Optimal Economic Gas Turbine Dispatch with Deep Reinforcement Learning","date":"2023-08-28","arxiv_id":"2308.14924","repositories_listed":0,"syntology":null},{"url":null,"slug":"target-independent-xla-optimization-using","title":"Target-independent XLA optimization using Reinforcement Learning","date":"2023-08-28","arxiv_id":"2308.14364","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-based-optimal-control-2","title":"Reinforcement Learning-based Optimal Control and Software Rejuvenation for Safe and Efficient UAV Navigation","date":"2023-08-27","arxiv_id":"2308.14139","repositories_listed":0,"syntology":null},{"url":null,"slug":"packet-header-recognition-utilizing-an-all","title":"Packet Header Recognition Utilizing an All-Optical Reservoir Based on Reinforcement-Learning-Optimized Double-Ring Resonator","date":"2023-08-26","arxiv_id":"2308.13818","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-reinforcement-learning-driven-cross","title":"Deep Reinforcement Learning-driven Cross-Community Energy Interaction Optimal Scheduling","date":"2023-08-24","arxiv_id":"2308.12554","repositories_listed":0,"syntology":null},{"url":null,"slug":"racing-towards-reinforcement-learning-based","title":"Racing Towards Reinforcement Learning based control of an Autonomous Formula SAE Car","date":"2023-08-24","arxiv_id":"2308.13088","repositories_listed":0,"syntology":null}],"record_sha256":"f8ceb17e9688f5cab20c523eb394ea1d68f1909dce4c580c6c779fb700b650f8","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}