{"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/35","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":35,"pages_in_order":59,"rows_per_page":100,"rows":[3401,3500],"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/34","next":"/task/deep-reinforcement-learning/papers/36","papers":[{"url":null,"slug":"active-perception-applied-to-unmanned-aerial","title":"Active Perception Applied To Unmanned Aerial Vehicles Through Deep Reinforcement Learning","date":"2022-09-13","arxiv_id":"2209.06336","repositories_listed":0,"syntology":null},{"url":null,"slug":"deterministic-and-stochastic-analysis-of-deep","title":"Deterministic and Stochastic Analysis of Deep Reinforcement Learning for Low Dimensional Sensing-based Navigation of Mobile Robots","date":"2022-09-13","arxiv_id":"2209.06328","repositories_listed":0,"syntology":null},{"url":null,"slug":"ksg-knowledge-and-skill-graph","title":"KSG: Knowledge and Skill Graph","date":"2022-09-13","arxiv_id":"2209.05698","repositories_listed":0,"syntology":null},{"url":null,"slug":"mapless-navigation-of-a-hybrid-aerial","title":"Mapless Navigation of a Hybrid Aerial Underwater Vehicle with Deep Reinforcement Learning Through Environmental Generalization","date":"2022-09-13","arxiv_id":"2209.06332","repositories_listed":0,"syntology":null},{"url":null,"slug":"self-supervised-sequential-information","title":"Self-supervised Sequential Information Bottleneck for Robust Exploration in Deep Reinforcement Learning","date":"2022-09-12","arxiv_id":"2209.05333","repositories_listed":0,"syntology":null},{"url":null,"slug":"pathfinding-in-random-partially-observable","title":"Pathfinding in Random Partially Observable Environments with Vision-Informed Deep Reinforcement Learning","date":"2022-09-11","arxiv_id":"2209.04801","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-analysis-of-deep-reinforcement-learning","title":"An Analysis of Deep Reinforcement Learning Agents for Text-based Games","date":"2022-09-09","arxiv_id":"2209.04105","repositories_listed":0,"syntology":null},{"url":null,"slug":"optimal-mesh-generation-for-a-blade-passage","title":"Non-iterative generation of an optimal mesh for a blade passage using deep reinforcement learning","date":"2022-09-08","arxiv_id":"2209.05280","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-deep-reinforcement-learning-strategy-for","title":"A Deep Reinforcement Learning Strategy for UAV Autonomous Landing on a Platform","date":"2022-09-07","arxiv_id":"2209.02954","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-sumo-framework-for-deep-reinforcement","title":"A SUMO Framework for Deep Reinforcement Learning Experiments Solving Electric Vehicle Charging Dispatching Problem","date":"2022-09-07","arxiv_id":"2209.02921","repositories_listed":0,"syntology":null},{"url":null,"slug":"auto-transrl-autonomous-composition-of-vision","title":"Auto-TransRL: Autonomous Composition of Vision Pipelines for Robotic Perception","date":"2022-09-07","arxiv_id":"2209.02991","repositories_listed":0,"syntology":null},{"url":null,"slug":"distilling-deep-rl-models-into-interpretable","title":"Distilling Deep RL Models Into Interpretable Neuro-Fuzzy Systems","date":"2022-09-07","arxiv_id":"2209.03357","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-agent-deep-reinforcement-learning-for-10","title":"Energy Management of Multi-mode Hybrid Electric Vehicles based on Hand-shaking Multi-agent Learning","date":"2022-09-06","arxiv_id":"2209.02633","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-assistive-robotics-with-deep","title":"Improving Assistive Robotics with Deep Reinforcement Learning","date":"2022-09-05","arxiv_id":"2209.02160","repositories_listed":0,"syntology":null},{"url":null,"slug":"prediction-based-decision-making-for","title":"Prediction Based Decision Making for Autonomous Highway Driving","date":"2022-09-05","arxiv_id":"2209.02106","repositories_listed":0,"syntology":null},{"url":null,"slug":"model-free-deep-reinforcement-learning-in","title":"Model-Free Deep Reinforcement Learning in Software-Defined Networks","date":"2022-09-03","arxiv_id":"2209.01490","repositories_listed":0,"syntology":null},{"url":null,"slug":"statistical-csi-based-beamforming-for-ris","title":"Statistical CSI-based Beamforming for RIS-Aided Multiuser MISO Systems using Deep Reinforcement Learning","date":"2022-09-03","arxiv_id":"2209.09856","repositories_listed":0,"syntology":null},{"url":null,"slug":"inference-and-dynamic-decision-making-for","title":"Inference and dynamic decision-making for deteriorating systems with probabilistic dependencies through Bayesian networks and deep reinforcement learning","date":"2022-09-02","arxiv_id":"2209.01092","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-reinforcement-learning-for-quantum-1","title":"Deep reinforcement learning for quantum multiparameter estimation","date":"2022-09-01","arxiv_id":"2209.00671","repositories_listed":0,"syntology":null},{"url":null,"slug":"metatrader-an-reinforcement-learning-approach","title":"MetaTrader: An Reinforcement Learning Approach Integrating Diverse Policies for Portfolio Optimization","date":"2022-09-01","arxiv_id":"2210.01774","repositories_listed":0,"syntology":null},{"url":null,"slug":"systems-theoretic-process-analysis-of-a-run","title":"Systems Theoretic Process Analysis of a Run Time Assured Neural Network Control System","date":"2022-09-01","arxiv_id":"2209.00552","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-reinforcement-learning-for-uplink-multi","title":"Deep Reinforcement Learning for Uplink Multi-Carrier Non-Orthogonal Multiple Access Resource Allocation Using Buffer State Information","date":"2022-08-31","arxiv_id":"2208.14689","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-further-exploration-of-deep-multi-agent","title":"A further exploration of deep Multi-Agent Reinforcement Learning with Hybrid Action Space","date":"2022-08-30","arxiv_id":"2208.14447","repositories_listed":0,"syntology":null},{"url":null,"slug":"boosting-5g-on-smart-grid-communication-a","title":"Boosting 5G on Smart Grid Communication: A Smart RAN Slicing Approach","date":"2022-08-30","arxiv_id":"2208.14538","repositories_listed":0,"syntology":null},{"url":null,"slug":"digital-twin-assisted-risk-aware-sleep-mode","title":"Digital Twin Assisted Risk-Aware Sleep Mode Management Using Deep Q-Networks","date":"2022-08-30","arxiv_id":"2208.14380","repositories_listed":0,"syntology":null},{"url":null,"slug":"distributed-ensembles-of-reinforcement","title":"Distributed Ensembles of Reinforcement Learning Agents for Electricity Control","date":"2022-08-30","arxiv_id":"2208.14338","repositories_listed":0,"syntology":null},{"url":null,"slug":"evolutionary-deep-reinforcement-learning-for","title":"Evolutionary Deep Reinforcement Learning for Dynamic Slice Management in O-RAN","date":"2022-08-30","arxiv_id":"2208.14394","repositories_listed":0,"syntology":null},{"url":null,"slug":"object-goal-navigation-using-data-regularized","title":"Object Goal Navigation using Data Regularized Q-Learning","date":"2022-08-27","arxiv_id":"2208.13009","repositories_listed":0,"syntology":null},{"url":null,"slug":"supervisorbot-nlp-annotated-real-time","title":"SupervisorBot: NLP-Annotated Real-Time Recommendations of Psychotherapy Treatment Strategies with Deep Reinforcement Learning","date":"2022-08-27","arxiv_id":"2208.13077","repositories_listed":0,"syntology":null},{"url":null,"slug":"battery-and-hydrogen-energy-storage-control","title":"Battery and Hydrogen Energy Storage Control in a Smart Energy Network with Flexible Energy Demand using Deep Reinforcement Learning","date":"2022-08-26","arxiv_id":"2208.12779","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploiting-deep-reinforcement-learning-for","title":"Exploiting Deep Reinforcement Learning for Edge Caching in Cell-Free Massive MIMO Systems","date":"2022-08-26","arxiv_id":"2208.12453","repositories_listed":0,"syntology":null},{"url":null,"slug":"visual-processing-in-context-of-reinforcement","title":"Visual processing in context of reinforcement learning","date":"2022-08-26","arxiv_id":"2208.12525","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-intelligent-algorithmic-trading-based-on-a","title":"An intelligent algorithmic trading based on a risk-return reinforcement learning algorithm","date":"2022-08-23","arxiv_id":"2208.10707","repositories_listed":0,"syntology":null},{"url":null,"slug":"what-deep-reinforcement-learning-tells-us","title":"What deep reinforcement learning tells us about human motor learning and vice-versa","date":"2022-08-23","arxiv_id":"2208.10892","repositories_listed":0,"syntology":null},{"url":null,"slug":"development-of-a-cav-based-intersection","title":"Development of a CAV-based Intersection Control System and Corridor Level Impact Assessment","date":"2022-08-21","arxiv_id":"2208.09973","repositories_listed":0,"syntology":null},{"url":null,"slug":"entropy-augmented-reinforcement-learning","title":"Entropy Augmented Reinforcement Learning","date":"2022-08-19","arxiv_id":"2208.09322","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-review-of-uncertainty-for-deep","title":"A Review of Uncertainty for Deep Reinforcement Learning","date":"2022-08-18","arxiv_id":"2208.09052","repositories_listed":0,"syntology":null},{"url":null,"slug":"explainable-reinforcement-learning-on","title":"Explainable Reinforcement Learning on Financial Stock Trading using SHAP","date":"2022-08-18","arxiv_id":"2208.08790","repositories_listed":0,"syntology":null},{"url":null,"slug":"artificial-intelligence-empowered-multiple","title":"Artificial Intelligence Empowered Multiple Access for Ultra Reliable and Low Latency THz Wireless Networks","date":"2022-08-17","arxiv_id":"2208.08039","repositories_listed":0,"syntology":null},{"url":null,"slug":"autonomous-resource-management-in","title":"Autonomous Resource Management in Construction Companies Using Deep Reinforcement Learning Based on IoT","date":"2022-08-17","arxiv_id":"2208.08087","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-deep-reinforcement-learning-based-adaptive","title":"A Deep Reinforcement Learning-based Adaptive Charging Policy for Wireless Rechargeable Sensor Networks","date":"2022-08-16","arxiv_id":"2208.07824","repositories_listed":0,"syntology":null},{"url":null,"slug":"generative-thermal-design-through-boundary","title":"Generative Thermal Design Through Boundary Representation and Multi-Agent Cooperative Environment","date":"2022-08-16","arxiv_id":"2208.07952","repositories_listed":0,"syntology":null},{"url":null,"slug":"hybrid-uav-enabled-secure-offloading-via-deep","title":"Hybrid UAV-enabled Secure Offloading via Deep Reinforcement Learning","date":"2022-08-16","arxiv_id":"2208.07550","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-reinforcement-learning-for-ris-assisted","title":"Deep Reinforcement Learning for RIS-Assisted FD Systems: Single or Distributed RIS?","date":"2022-08-15","arxiv_id":"2208.07424","repositories_listed":0,"syntology":null},{"url":null,"slug":"trustworthy-federated-learning-via-blockchain","title":"Trustworthy Federated Learning via Blockchain","date":"2022-08-13","arxiv_id":"2209.04418","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-agent-reinforcement-learning-with-graph-1","title":"Multi-Agent Reinforcement Learning with Graph Convolutional Neural Networks for optimal Bidding Strategies of Generation Units in Electricity Markets","date":"2022-08-11","arxiv_id":"2208.06242","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-reinforcement-learning-for-dynamic-4","title":"Plug-and-Play Model-Agnostic Counterfactual Policy Synthesis for Deep Reinforcement Learning based Recommendation","date":"2022-08-10","arxiv_id":"2208.05142","repositories_listed":0,"syntology":null},{"url":null,"slug":"fairness-based-energy-efficient-3d-path","title":"Fairness Based Energy-Efficient 3D Path Planning of a Portable Access Point: A Deep Reinforcement Learning Approach","date":"2022-08-10","arxiv_id":"2208.05265","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-based-client-selection-for-federated","title":"Learning-Based Client Selection for Federated Learning Services Over Wireless Networks with Constrained Monetary Budgets","date":"2022-08-08","arxiv_id":"2208.04322","repositories_listed":0,"syntology":null},{"url":null,"slug":"maximum-correntropy-value-decomposition-for","title":"Maximum Correntropy Value Decomposition for Multi-agent Deep Reinforcemen Learning","date":"2022-08-07","arxiv_id":"2208.03663","repositories_listed":0,"syntology":null},{"url":null,"slug":"dl-drl-a-double-layer-deep-reinforcement","title":"DL-DRL: A double-level deep reinforcement learning approach for large-scale task scheduling of multi-UAV","date":"2022-08-04","arxiv_id":"2208.02447","repositories_listed":0,"syntology":null},{"url":null,"slug":"feddrl-deep-reinforcement-learning-based","title":"FedDRL: Deep Reinforcement Learning-based Adaptive Aggregation for Non-IID Data in Federated Learning","date":"2022-08-04","arxiv_id":"2208.02442","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-vulman-a-deep-reinforcement-learning","title":"Deep VULMAN: A Deep Reinforcement Learning-Enabled Cyber Vulnerability Management Framework","date":"2022-08-03","arxiv_id":"2208.02369","repositories_listed":0,"syntology":null},{"url":null,"slug":"joint-sensing-and-communications-for-deep","title":"Joint Sensing and Communications for Deep Reinforcement Learning-based Beam Management in 6G","date":"2022-08-03","arxiv_id":"2208.01880","repositories_listed":0,"syntology":null},{"url":null,"slug":"chemotaxis-of-sea-urchin-sperm-cells-through","title":"Chemotaxis of sea urchin sperm cells through deep reinforcement learning","date":"2022-08-02","arxiv_id":"2209.07407","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-maintenance-planning-framework-using-online","title":"A Maintenance Planning Framework using Online and Offline Deep Reinforcement Learning","date":"2022-08-01","arxiv_id":"2208.00808","repositories_listed":0,"syntology":null},{"url":null,"slug":"gandse-generative-adversarial-network-based","title":"GANDSE: Generative Adversarial Network based Design Space Exploration for Neural Network Accelerator Design","date":"2022-08-01","arxiv_id":"2208.00800","repositories_listed":0,"syntology":null},{"url":null,"slug":"hierarchical-reinforcement-learning-for-6","title":"Hierarchical Reinforcement Learning for Precise Soccer Shooting Skills using a Quadrupedal Robot","date":"2022-08-01","arxiv_id":"2208.01160","repositories_listed":0,"syntology":null},{"url":null,"slug":"sampling-communication-and-prediction-co","title":"Sampling, Communication, and Prediction Co-Design for Synchronizing the Real-World Device and Digital Model in Metaverse","date":"2022-07-31","arxiv_id":"2208.04233","repositories_listed":0,"syntology":null},{"url":null,"slug":"solving-the-vehicle-routing-problem-with-deep","title":"Solving the vehicle routing problem with deep reinforcement learning","date":"2022-07-30","arxiv_id":"2208.00202","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-reinforcement-learning-for-system-on","title":"Deep Reinforcement Learning for System-on-Chip: Myths and Realities","date":"2022-07-29","arxiv_id":"2207.14595","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-objective-provisioning-of-network","title":"Multi-Objective Provisioning of Network Slices using Deep Reinforcement Learning","date":"2022-07-27","arxiv_id":"2207.13821","repositories_listed":0,"syntology":null},{"url":null,"slug":"vision-aided-blockage-avoidance-in-uav","title":"Vision-Aided Blockage Avoidance in UAV-assisted V2X Communications","date":"2022-07-26","arxiv_id":"2207.12991","repositories_listed":0,"syntology":null},{"url":null,"slug":"repnp-plug-and-play-with-deep-reinforcement","title":"REPNP: Plug-and-Play with Deep Reinforcement Learning Prior for Robust Image Restoration","date":"2022-07-25","arxiv_id":"2207.12056","repositories_listed":0,"syntology":null},{"url":null,"slug":"epersist-a-self-balancing-robot-using-pid","title":"Epersist: A Self Balancing Robot Using PID Controller And Deep Reinforcement Learning","date":"2022-07-23","arxiv_id":"2207.11431","repositories_listed":0,"syntology":null},{"url":null,"slug":"halftoning-with-multi-agent-deep","title":"Halftoning with Multi-Agent Deep Reinforcement Learning","date":"2022-07-23","arxiv_id":"2207.11408","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-to-route-in-mobile-wireless-networks","title":"Learning an Adaptive Forwarding Strategy for Mobile Wireless Networks: Resource Usage vs. Latency","date":"2022-07-23","arxiv_id":"2207.11386","repositories_listed":0,"syntology":null},{"url":null,"slug":"knowledge-enhanced-black-box-attacks-for","title":"Knowledge-enhanced Black-box Attacks for Recommendations","date":"2022-07-21","arxiv_id":"2207.10307","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-asset-closed-loop-reservoir-management","title":"Multi-Asset Closed-Loop Reservoir Management Using Deep Reinforcement Learning","date":"2022-07-21","arxiv_id":"2207.10376","repositories_listed":0,"syntology":null},{"url":null,"slug":"inspector-pixel-based-automated-game-testing","title":"Inspector: Pixel-Based Automated Game Testing via Exploration, Detection, and Investigation","date":"2022-07-18","arxiv_id":"2207.08379","repositories_listed":0,"syntology":null},{"url":null,"slug":"romanus-robust-task-offloading-in-modular","title":"Romanus: Robust Task Offloading in Modular Multi-Sensor Autonomous Driving Systems","date":"2022-07-18","arxiv_id":"2207.08865","repositories_listed":0,"syntology":null},{"url":null,"slug":"associative-memory-based-experience-replay","title":"Associative Memory Based Experience Replay for Deep Reinforcement Learning","date":"2022-07-16","arxiv_id":"2207.07791","repositories_listed":0,"syntology":null},{"url":null,"slug":"optimizing-data-collection-in-deep","title":"Optimizing Data Collection in Deep Reinforcement Learning","date":"2022-07-15","arxiv_id":"2207.07736","repositories_listed":0,"syntology":null},{"url":null,"slug":"covy-an-ai-powered-robot-for-detection-of","title":"Covy: An AI-powered Robot with a Compound Vision System for Detecting Breaches in Social Distancing","date":"2022-07-14","arxiv_id":"2207.06847","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-agent-deep-reinforcement-learning-2","title":"Multi-Agent Deep Reinforcement Learning-Driven Mitigation of Adverse Effects of Cyber-Attacks on Electric Vehicle Charging Station","date":"2022-07-14","arxiv_id":"2207.07041","repositories_listed":0,"syntology":null},{"url":null,"slug":"self-play-psro-toward-optimal-populations-in","title":"Self-Play PSRO: Toward Optimal Populations in Two-Player Zero-Sum Games","date":"2022-07-13","arxiv_id":"2207.06541","repositories_listed":0,"syntology":null},{"url":null,"slug":"state-dropout-based-curriculum-reinforcement","title":"State Dropout-Based Curriculum Reinforcement Learning for Self-Driving at Unsignalized Intersections","date":"2022-07-10","arxiv_id":"2207.04361","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-reinforcement-learning-for-long-term-1","title":"Deep Reinforcement Learning for Long-Term Voltage Stability Control","date":"2022-07-09","arxiv_id":"2207.04240","repositories_listed":0,"syntology":null},{"url":null,"slug":"domain-adapting-speech-emotion-recognition","title":"Domain Adapting Deep Reinforcement Learning for Real-world Speech Emotion Recognition","date":"2022-07-07","arxiv_id":"2207.12248","repositories_listed":0,"syntology":null},{"url":null,"slug":"drl-isp-multi-objective-camera-isp-with-deep","title":"DRL-ISP: Multi-Objective Camera ISP with Deep Reinforcement Learning","date":"2022-07-07","arxiv_id":"2207.03081","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-based-autonomous-channel-access-in","title":"Learning-based Autonomous Channel Access in the Presence of Hidden Terminals","date":"2022-07-07","arxiv_id":"2207.03605","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-the-quality-of-machine-permutations","title":"Learning the Quality of Machine Permutations in Job Shop Scheduling","date":"2022-07-07","arxiv_id":"2207.03244","repositories_listed":0,"syntology":null},{"url":null,"slug":"vessel-following-model-for-inland-waterways","title":"Vessel-following model for inland waterways based on deep reinforcement learning","date":"2022-07-07","arxiv_id":"2207.03257","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-reinforcement-learning-approach-for","title":"Deep Reinforcement Learning Approach for Trading Automation in The Stock Market","date":"2022-07-05","arxiv_id":"2208.07165","repositories_listed":0,"syntology":null},{"url":null,"slug":"explainability-in-deep-reinforcement-learning-1","title":"Explainability in Deep Reinforcement Learning, a Review into Current Methods and Applications","date":"2022-07-05","arxiv_id":"2207.01911","repositories_listed":0,"syntology":null},{"url":null,"slug":"resource-allocation-in-multicore-elastic","title":"Resource Allocation in Multicore Elastic Optical Networks: A Deep Reinforcement Learning Approach","date":"2022-07-05","arxiv_id":"2207.02074","repositories_listed":0,"syntology":null},{"url":null,"slug":"tackling-real-world-autonomous-driving-using","title":"Tackling Real-World Autonomous Driving using Deep Reinforcement Learning","date":"2022-07-05","arxiv_id":"2207.02162","repositories_listed":0,"syntology":null},{"url":null,"slug":"asynchronous-curriculum-experience-replay-a","title":"Asynchronous Curriculum Experience Replay: A Deep Reinforcement Learning Approach for UAV Autonomous Motion Control in Unknown Dynamic Environments","date":"2022-07-04","arxiv_id":"2207.01251","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-versatile-adaptive-curriculum-learning","title":"A Versatile Adaptive Curriculum Learning Framework for Task-oriented Dialogue Policy Learning","date":"2022-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"coor-plt-a-hierarchical-control-model-for","title":"COOR-PLT: A hierarchical control model for coordinating adaptive platoons of connected and autonomous vehicles at signal-free intersections based on deep reinforcement learning","date":"2022-07-01","arxiv_id":"2207.07195","repositories_listed":0,"syntology":null},{"url":null,"slug":"dynamictoc-persona-based-table-of-contents","title":"DynamicTOC: Persona-based Table of Contents for Consumption of Long Documents","date":"2022-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-reinforcement-learning-for-small-bowel","title":"Deep Reinforcement Learning for Small Bowel Path Tracking using Different Types of Annotations","date":"2022-06-29","arxiv_id":"2206.14847","repositories_listed":0,"syntology":null},{"url":null,"slug":"dependency-parsing-with-backtracking-using","title":"Dependency Parsing with Backtracking using Deep Reinforcement Learning","date":"2022-06-28","arxiv_id":"2206.13914","repositories_listed":0,"syntology":null},{"url":null,"slug":"left-heavy-tails-and-the-effectiveness-of-the","title":"Left Heavy Tails and the Effectiveness of the Policy and Value Networks in DNN-based best-first search for Sokoban Planning","date":"2022-06-28","arxiv_id":"2206.14298","repositories_listed":0,"syntology":null},{"url":null,"slug":"position-agnostic-autonomous-navigation-in","title":"Position-Agnostic Autonomous Navigation in Vineyards with Deep Reinforcement Learning","date":"2022-06-28","arxiv_id":"2206.14155","repositories_listed":0,"syntology":null},{"url":null,"slug":"traffic-management-of-autonomous-vehicles","title":"Traffic Management of Autonomous Vehicles using Policy Based Deep Reinforcement Learning and Intelligent Routing","date":"2022-06-28","arxiv_id":"2206.14608","repositories_listed":0,"syntology":null},{"url":null,"slug":"interpretable-hidden-markov-model-based-deep","title":"Interpretable Hidden Markov Model-Based Deep Reinforcement Learning Hierarchical Framework for Predictive Maintenance of Turbofan Engines","date":"2022-06-27","arxiv_id":"2206.13433","repositories_listed":0,"syntology":null},{"url":null,"slug":"hierarchical-reinforcement-learning-with-4","title":"Hierarchical Reinforcement Learning with Opponent Modeling for Distributed Multi-agent Cooperation","date":"2022-06-25","arxiv_id":"2206.12718","repositories_listed":0,"syntology":null},{"url":null,"slug":"value-consistent-representation-learning-for","title":"Value-Consistent Representation Learning for Data-Efficient Reinforcement Learning","date":"2022-06-25","arxiv_id":"2206.12542","repositories_listed":0,"syntology":null},{"url":null,"slug":"dynamic-network-congestion-pricing-based-on","title":"Dynamic network congestion pricing based on deep reinforcement learning","date":"2022-06-24","arxiv_id":"2206.12188","repositories_listed":0,"syntology":null}],"record_sha256":"92660302954af27ac7be4682d1e0f20acf1a5d27b659879cbb30187edcd00e25","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}