{"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/36","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":36,"pages_in_order":59,"rows_per_page":100,"rows":[3501,3600],"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/35","next":"/task/deep-reinforcement-learning/papers/37","papers":[{"url":null,"slug":"modeling-adaptive-platoon-and-reservation","title":"Modeling Adaptive Platoon and Reservation Based Autonomous Intersection Control: A Deep Reinforcement Learning Approach","date":"2022-06-24","arxiv_id":"2206.12419","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-agent-deep-reinforcement-learning-for-9","title":"Multi-Agent Deep Reinforcement Learning for Cost- and Delay-Sensitive Virtual Network Function Placement and Routing","date":"2022-06-24","arxiv_id":"2206.12146","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-federated-reinforcement-learning-method","title":"A Federated Reinforcement Learning Method with Quantization for Cooperative Edge Caching in Fog Radio Access Networks","date":"2022-06-23","arxiv_id":"2206.11556","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-reinforcement-learning-assisted-1","title":"Deep Reinforcement Learning-Assisted Federated Learning for Robust Short-term Utility Demand Forecasting in Electricity Wholesale Markets","date":"2022-06-23","arxiv_id":"2206.11715","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-optimal-treatment-strategies-for","title":"Learning Optimal Treatment Strategies for Sepsis Using Offline Reinforcement Learning in Continuous Space","date":"2022-06-22","arxiv_id":"2206.11190","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-access-point-coordination-for-next-gen","title":"Multi-Access Point Coordination for Next-Gen Wi-Fi Networks Aided by Deep Reinforcement Learning","date":"2022-06-22","arxiv_id":"2206.11378","repositories_listed":0,"syntology":null},{"url":null,"slug":"hybridization-of-evolutionary-algorithm-and","title":"Hybridization of evolutionary algorithm and deep reinforcement learning for multi-objective orienteering optimization","date":"2022-06-21","arxiv_id":"2206.10464","repositories_listed":0,"syntology":null},{"url":null,"slug":"incorporating-voice-instructions-in-model","title":"Incorporating Voice Instructions in Model-Based Reinforcement Learning for Self-Driving Cars","date":"2022-06-21","arxiv_id":"2206.10249","repositories_listed":0,"syntology":null},{"url":null,"slug":"constrained-reinforcement-learning-for-1","title":"Constrained Reinforcement Learning for Robotics via Scenario-Based Programming","date":"2022-06-20","arxiv_id":"2206.09603","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-reinforced-active-learning-for-multi","title":"Deep reinforced active learning for multi-class image classification","date":"2022-06-20","arxiv_id":"2206.13391","repositories_listed":0,"syntology":null},{"url":null,"slug":"two-hop-age-of-information-scheduling-for","title":"Two-Hop Age of Information Scheduling for Multi-UAV Assisted Mobile Edge Computing: FRL vs MADDPG","date":"2022-06-19","arxiv_id":"2206.09488","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-reinforcement-learning-for-fmri","title":"Deep reinforcement learning for fMRI prediction of Autism Spectrum Disorder","date":"2022-06-17","arxiv_id":"2206.11224","repositories_listed":0,"syntology":null},{"url":null,"slug":"backbones-review-feature-extraction-networks","title":"Backbones-Review: Feature Extraction Networks for Deep Learning and Deep Reinforcement Learning Approaches","date":"2022-06-16","arxiv_id":"2206.08016","repositories_listed":0,"syntology":null},{"url":null,"slug":"challenges-and-opportunities-in-deep","title":"Challenges and Opportunities in Deep Reinforcement Learning with Graph Neural Networks: A Comprehensive review of Algorithms and Applications","date":"2022-06-16","arxiv_id":"2206.07922","repositories_listed":0,"syntology":null},{"url":null,"slug":"automating-the-resolution-of-flight-conflicts","title":"Automating the resolution of flight conflicts: Deep reinforcement learning in service of air traffic controllers","date":"2022-06-15","arxiv_id":"2206.07403","repositories_listed":0,"syntology":null},{"url":null,"slug":"autonomous-platoon-control-with-integrated","title":"Autonomous Platoon Control with Integrated Deep Reinforcement Learning and Dynamic Programming","date":"2022-06-15","arxiv_id":"2206.07536","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-reinforcement-learning-for-exact","title":"Deep Reinforcement Learning for Exact Combinatorial Optimization: Learning to Branch","date":"2022-06-14","arxiv_id":"2206.06965","repositories_listed":0,"syntology":null},{"url":null,"slug":"computation-offloading-and-resource-1","title":"Computation Offloading and Resource Allocation in F-RANs: A Federated Deep Reinforcement Learning Approach","date":"2022-06-13","arxiv_id":"2206.05881","repositories_listed":0,"syntology":null},{"url":null,"slug":"safe-finrl-a-low-bias-and-variance-deep","title":"Safe-FinRL: A Low Bias and Variance Deep Reinforcement Learning Implementation for High-Freq Stock Trading","date":"2022-06-13","arxiv_id":"2206.05910","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-reinforcement-learning-for-optimal-2","title":"Deep Reinforcement Learning for Optimal Investment and Saving Strategy Selection in Heterogeneous Profiles: Intelligent Agents working towards retirement","date":"2022-06-12","arxiv_id":"2206.05835","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-multi-agent-reinforcement-learning-with-2","title":"Deep Multi-Agent Reinforcement Learning with Hybrid Action Spaces based on Maximum Entropy","date":"2022-06-10","arxiv_id":"2206.05108","repositories_listed":0,"syntology":null},{"url":null,"slug":"large-scale-retrieval-for-reinforcement","title":"Large-Scale Retrieval for Reinforcement Learning","date":"2022-06-10","arxiv_id":"2206.05314","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-optimization-method-assisted-ensemble-deep","title":"An Optimization Method-Assisted Ensemble Deep Reinforcement Learning Algorithm to Solve Unit Commitment Problems","date":"2022-06-09","arxiv_id":"2206.04249","repositories_listed":0,"syntology":null},{"url":null,"slug":"overcoming-the-spectral-bias-of-neural-value-1","title":"Overcoming the Spectral Bias of Neural Value Approximation","date":"2022-06-09","arxiv_id":"2206.04672","repositories_listed":0,"syntology":null},{"url":null,"slug":"action-noise-in-off-policy-deep-reinforcement","title":"Action Noise in Off-Policy Deep Reinforcement Learning: Impact on Exploration and Performance","date":"2022-06-08","arxiv_id":"2206.03787","repositories_listed":0,"syntology":null},{"url":"/paper/generalized-data-distribution-iteration","slug":"generalized-data-distribution-iteration","title":"Generalized Data Distribution Iteration","date":"2022-06-07","arxiv_id":"2206.03192","repositories_listed":0,"syntology":null},{"url":null,"slug":"adaptive-rollout-length-for-model-based-rl","title":"Adaptive Rollout Length for Model-Based RL Using Model-Free Deep RL","date":"2022-06-06","arxiv_id":"2206.02380","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-reinforcement-learning-for-cybersecurity-1","title":"Deep Reinforcement Learning for Cybersecurity Threat Detection and Protection: A Review","date":"2022-06-06","arxiv_id":"2206.02733","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-entity-based-reinforcement-learning","title":"Efficient entity-based reinforcement learning","date":"2022-06-06","arxiv_id":"2206.02855","repositories_listed":0,"syntology":null},{"url":null,"slug":"real2sim-or-sim2real-robotics-visual","title":"Real2Sim or Sim2Real: Robotics Visual Insertion using Deep Reinforcement Learning and Real2Sim Policy Adaptation","date":"2022-06-06","arxiv_id":"2206.02679","repositories_listed":0,"syntology":null},{"url":null,"slug":"robust-adversarial-attacks-detection-based-on","title":"Robust Adversarial Attacks Detection based on Explainable Deep Reinforcement Learning For UAV Guidance and Planning","date":"2022-06-06","arxiv_id":"2206.02670","repositories_listed":0,"syntology":null},{"url":null,"slug":"ddpg-based-on-multi-scale-strokes-for","title":"DDPG based on multi-scale strokes for financial time series trading strategy","date":"2022-06-05","arxiv_id":"2207.10071","repositories_listed":0,"syntology":null},{"url":null,"slug":"macc-cross-layer-multi-agent-congestion","title":"MACC: Cross-Layer Multi-Agent Congestion Control with Deep Reinforcement Learning","date":"2022-06-04","arxiv_id":"2206.01972","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-deep-reinforcement-learning-framework-for-6","title":"A Deep Reinforcement Learning Framework For Column Generation","date":"2022-06-03","arxiv_id":"2206.02568","repositories_listed":0,"syntology":null},{"url":null,"slug":"joint-energy-dispatch-and-unit-commitment-in","title":"Joint Energy Dispatch and Unit Commitment in Microgrids Based on Deep Reinforcement Learning","date":"2022-06-03","arxiv_id":"2206.01663","repositories_listed":0,"syntology":null},{"url":null,"slug":"hex-human-in-the-loop-explainability-via-deep","title":"HEX: Human-in-the-loop Explainability via Deep Reinforcement Learning","date":"2022-06-02","arxiv_id":"2206.01343","repositories_listed":0,"syntology":null},{"url":null,"slug":"raca-relation-aware-credit-assignment-for-ad","title":"RACA: Relation-Aware Credit Assignment for Ad-Hoc Cooperation in Multi-Agent Deep Reinforcement Learning","date":"2022-06-02","arxiv_id":"2206.01207","repositories_listed":0,"syntology":null},{"url":null,"slug":"vygotskian-autotelic-artificial-intelligence","title":"Language and Culture Internalisation for Human-Like Autotelic AI","date":"2022-06-02","arxiv_id":"2206.01134","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-scheduling-of-data-augmentation-for","title":"Efficient Scheduling of Data Augmentation for Deep Reinforcement Learning","date":"2022-06-01","arxiv_id":"2206.00518","repositories_listed":0,"syntology":null},{"url":null,"slug":"rlss-a-deep-reinforcement-learning-algorithm","title":"RLSS: A Deep Reinforcement Learning Algorithm for Sequential Scene Generation","date":"2022-06-01","arxiv_id":"2206.02544","repositories_listed":0,"syntology":null},{"url":null,"slug":"lessons-learned-from-data-driven-building","title":"Lessons Learned from Data-Driven Building Control Experiments: Contrasting Gaussian Process-based MPC, Bilevel DeePC, and Deep Reinforcement Learning","date":"2022-05-31","arxiv_id":"2205.15703","repositories_listed":0,"syntology":null},{"url":null,"slug":"robust-longitudinal-control-for-vehicular","title":"Robust Longitudinal Control for Vehicular Autonomous Platoons Using Deep Reinforcement Learning","date":"2022-05-31","arxiv_id":"2206.01175","repositories_listed":0,"syntology":null},{"url":null,"slug":"representation-gap-in-deep-reinforcement","title":"Frustratingly Easy Regularization on Representation Can Boost Deep Reinforcement Learning","date":"2022-05-29","arxiv_id":"2205.14557","repositories_listed":0,"syntology":null},{"url":null,"slug":"survival-analysis-on-structured-data-using","title":"Survival Analysis on Structured Data using Deep Reinforcement Learning","date":"2022-05-28","arxiv_id":"2205.14331","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-reinforcement-learning-for-distributed-1","title":"Deep Reinforcement Learning for Distributed and Uncoordinated Cognitive Radios Resource Allocation","date":"2022-05-27","arxiv_id":"2205.13944","repositories_listed":0,"syntology":null},{"url":null,"slug":"galois-boosting-deep-reinforcement-learning","title":"GALOIS: Boosting Deep Reinforcement Learning via Generalizable Logic Synthesis","date":"2022-05-27","arxiv_id":"2205.13728","repositories_listed":0,"syntology":null},{"url":null,"slug":"guided-exploration-of-data-summaries","title":"Guided Exploration of Data Summaries","date":"2022-05-27","arxiv_id":"2205.13956","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-reinforcement-learning-with-adaptive-1","title":"Multi-Phase Multi-Objective Dexterous Manipulation with Adaptive Hierarchical Curriculum","date":"2022-05-26","arxiv_id":"2205.13441","repositories_listed":0,"syntology":null},{"url":null,"slug":"physics-guided-hierarchical-reward-mechanism","title":"Physics-Guided Hierarchical Reward Mechanism for Learning-Based Robotic Grasping","date":"2022-05-26","arxiv_id":"2205.13561","repositories_listed":0,"syntology":null},{"url":null,"slug":"temporl-temporal-priors-for-exploration-in-1","title":"SFP: State-free Priors for Exploration in Off-Policy Reinforcement Learning","date":"2022-05-26","arxiv_id":"2205.13528","repositories_listed":0,"syntology":null},{"url":null,"slug":"verifying-learning-based-robotic-navigation","title":"Verifying Learning-Based Robotic Navigation Systems","date":"2022-05-26","arxiv_id":"2205.13536","repositories_listed":0,"syntology":null},{"url":null,"slug":"drl-based-resource-allocation-in-remote-state","title":"DRL-based Resource Allocation in Remote State Estimation","date":"2022-05-24","arxiv_id":"2205.12267","repositories_listed":0,"syntology":null},{"url":null,"slug":"generalization-mayhems-and-limits-in","title":"Generalization, Mayhems and Limits in Recurrent Proximal Policy Optimization","date":"2022-05-23","arxiv_id":"2205.11104","repositories_listed":0,"syntology":null},{"url":null,"slug":"spreading-factor-and-rssi-for-localization-in","title":"Spreading Factor assisted LoRa Localization with Deep Reinforcement Learning","date":"2022-05-23","arxiv_id":"2205.11428","repositories_listed":0,"syntology":null},{"url":null,"slug":"co-design-of-embodied-neural-intelligence-via","title":"Co-design of Embodied Neural Intelligence via Constrained Evolution","date":"2022-05-21","arxiv_id":"2205.10688","repositories_listed":0,"syntology":null},{"url":null,"slug":"adversarial-body-shape-search-for-legged","title":"Adversarial Body Shape Search for Legged Robots","date":"2022-05-20","arxiv_id":"2205.10187","repositories_listed":0,"syntology":null},{"url":null,"slug":"adversarial-joint-attacks-on-legged-robots","title":"Adversarial joint attacks on legged robots","date":"2022-05-20","arxiv_id":"2205.10098","repositories_listed":0,"syntology":null},{"url":null,"slug":"long-run-incremental-cost-lric-distribution","title":"Long Run Incremental Cost (LRIC) Distribution Network Pricing in UK, advising China's Distribution Network","date":"2022-05-20","arxiv_id":"2205.09946","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-jointly-optimizing-partial-offloading-and","title":"On Jointly Optimizing Partial Offloading and SFC Mapping: A Cooperative Dual-agent Deep Reinforcement Learning Approach","date":"2022-05-20","arxiv_id":"2205.09925","repositories_listed":0,"syntology":null},{"url":null,"slug":"data-valuation-for-offline-reinforcement","title":"Data Valuation for Offline Reinforcement Learning","date":"2022-05-19","arxiv_id":"2205.09550","repositories_listed":0,"syntology":null},{"url":null,"slug":"distributed-multi-agent-deep-reinforcement-1","title":"Distributed Multi-Agent Deep Reinforcement Learning for Robust Coordination against Noise","date":"2022-05-19","arxiv_id":"2205.09705","repositories_listed":0,"syntology":null},{"url":null,"slug":"routing-and-placement-of-macros-using-deep","title":"Routing and Placement of Macros using Deep Reinforcement Learning","date":"2022-05-19","arxiv_id":"2205.09289","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-reinforcement-learning-based-on-location","title":"Deep Reinforcement Learning Based on Location-Aware Imitation Environment for RIS-Aided mmWave MIMO Systems","date":"2022-05-18","arxiv_id":"2205.08788","repositories_listed":0,"syntology":null},{"url":null,"slug":"generating-explanations-from-deep","title":"Generating Explanations from Deep Reinforcement Learning Using Episodic Memory","date":"2022-05-18","arxiv_id":"2205.08926","repositories_listed":0,"syntology":null},{"url":null,"slug":"policy-distillation-with-selective-input","title":"Policy Distillation with Selective Input Gradient Regularization for Efficient Interpretability","date":"2022-05-18","arxiv_id":"2205.08685","repositories_listed":0,"syntology":null},{"url":null,"slug":"multibit-tries-packet-classification-with","title":"Multibit Tries Packet Classification with Deep Reinforcement Learning","date":"2022-05-17","arxiv_id":"2205.08606","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-deep-reinforcement-learning-blind-ai-in","title":"A Deep Reinforcement Learning Blind AI in DareFightingICE","date":"2022-05-16","arxiv_id":"2205.07444","repositories_listed":0,"syntology":null},{"url":null,"slug":"attacking-and-defending-deep-reinforcement","title":"Attacking and Defending Deep Reinforcement Learning Policies","date":"2022-05-16","arxiv_id":"2205.07626","repositories_listed":0,"syntology":null},{"url":null,"slug":"many-field-packet-classification-with","title":"Many Field Packet Classification with Decomposition and Reinforcement Learning","date":"2022-05-16","arxiv_id":"2205.07973","repositories_listed":0,"syntology":null},{"url":null,"slug":"romfac-a-robust-mean-field-actor-critic","title":"RoMFAC: A robust mean-field actor-critic reinforcement learning against adversarial perturbations on states","date":"2022-05-15","arxiv_id":"2205.07229","repositories_listed":0,"syntology":null},{"url":null,"slug":"prefixrl-optimization-of-parallel-prefix","title":"PrefixRL: Optimization of Parallel Prefix Circuits using Deep Reinforcement Learning","date":"2022-05-14","arxiv_id":"2205.07000","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-reinforcement-learning-in-mmw-noma-joint","title":"Deep Reinforcement Learning in mmW-NOMA: Joint Power Allocation and Hybrid Beamforming","date":"2022-05-13","arxiv_id":"2205.06814","repositories_listed":0,"syntology":null},{"url":null,"slug":"joint-power-allocation-and-beamformer-for-mmw","title":"Joint Power Allocation and Beamformer for mmW-NOMA Downlink Systems by Deep Reinforcement Learning","date":"2022-05-13","arxiv_id":"2205.06489","repositories_listed":0,"syntology":null},{"url":null,"slug":"provably-safe-deep-reinforcement-learning-for","title":"Provably Safe Deep Reinforcement Learning for Robotic Manipulation in Human Environments","date":"2022-05-12","arxiv_id":"2205.06311","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-to-guide-multiple-heterogeneous","title":"Learning to Guide Multiple Heterogeneous Actors from a Single Human Demonstration via Automatic Curriculum Learning in StarCraft II","date":"2022-05-11","arxiv_id":"2205.05784","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-the-verge-of-solving-rocket-league-using","title":"On the Verge of Solving Rocket League using Deep Reinforcement Learning and Sim-to-sim Transfer","date":"2022-05-10","arxiv_id":"2205.05061","repositories_listed":0,"syntology":null},{"url":null,"slug":"personalized-qoe-enhancement-for-adaptive","title":"Personalized QoE Enhancement for Adaptive Video Streaming: A Digital Twin-Assisted Scheme","date":"2022-05-09","arxiv_id":"2205.04014","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-reinforcement-learning-based-adaptive-1","title":"Deep Reinforcement Learning-Based Adaptive IRS Control with Limited Feedback Codebooks","date":"2022-05-07","arxiv_id":"2205.03636","repositories_listed":0,"syntology":null},{"url":null,"slug":"search-based-testing-of-reinforcement","title":"Search-Based Testing of Reinforcement Learning","date":"2022-05-07","arxiv_id":"2205.04887","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-deep-reinforcement-learning-based-sliding","title":"A Deep Reinforcement Learning-based Sliding Mode Control Design for Partially-known Nonlinear Systems","date":"2022-05-06","arxiv_id":"2205.02975","repositories_listed":0,"syntology":null},{"url":null,"slug":"vehicle-management-in-a-modular-production","title":"Vehicle management in a modular production context using Deep Q-Learning","date":"2022-05-06","arxiv_id":"2205.03294","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-deep-reinforcement-learning-framework-for-5","title":"A Deep Reinforcement Learning Framework for Rapid Diagnosis of Whole Slide Pathological Images","date":"2022-05-05","arxiv_id":"2205.02850","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-temporal-pattern-backdoor-attack-to-deep","title":"A Temporal-Pattern Backdoor Attack to Deep Reinforcement Learning","date":"2022-05-05","arxiv_id":"2205.02589","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-agent-deep-reinforcement-learning-in","title":"Multi-Agent Deep Reinforcement Learning in Vehicular OCC","date":"2022-05-05","arxiv_id":"2205.02672","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-subgoal-robot-navigation-in-crowds-with","title":"Multi-subgoal Robot Navigation in Crowds with History Information and Interactions","date":"2022-05-04","arxiv_id":"2205.02003","repositories_listed":0,"syntology":null},{"url":null,"slug":"using-deep-reinforcement-learning-to-solve","title":"Using Deep Reinforcement Learning to solve Optimal Power Flow problem with generator failures","date":"2022-05-04","arxiv_id":"2205.02108","repositories_listed":0,"syntology":null},{"url":null,"slug":"real-time-cooperative-vehicle-coordination-at","title":"Real-time Cooperative Vehicle Coordination at Unsignalized Road Intersections","date":"2022-05-03","arxiv_id":"2205.01278","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-attack-over-the-deep-reinforcement","title":"Deep-Attack over the Deep Reinforcement Learning","date":"2022-05-02","arxiv_id":"2205.00807","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploration-in-deep-reinforcement-learning-a-1","title":"Exploration in Deep Reinforcement Learning: A Survey","date":"2022-05-02","arxiv_id":"2205.00824","repositories_listed":0,"syntology":null},{"url":null,"slug":"data-driven-control-of-spatiotemporal-chaos","title":"Data-driven control of spatiotemporal chaos with reduced-order neural ODE-based models and reinforcement learning","date":"2022-05-01","arxiv_id":"2205.00579","repositories_listed":0,"syntology":null},{"url":null,"slug":"processing-network-controls-via-deep","title":"Processing Network Controls via Deep Reinforcement Learning","date":"2022-05-01","arxiv_id":"2205.02119","repositories_listed":0,"syntology":null},{"url":null,"slug":"tinylight-adaptive-traffic-signal-control-on","title":"TinyLight: Adaptive Traffic Signal Control on Devices with Extremely Limited Resources","date":"2022-05-01","arxiv_id":"2205.00427","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-reinforcement-learning-for-online-3","title":"Deep Reinforcement Learning for Online Routing of Unmanned Aerial Vehicles with Wireless Power Transfer","date":"2022-04-25","arxiv_id":"2204.11477","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-reinforcement-learning-for-orienteering","title":"Deep Reinforcement Learning for Orienteering Problems Based on Decomposition","date":"2022-04-25","arxiv_id":"2204.11575","repositories_listed":0,"syntology":null},{"url":null,"slug":"skill-based-meta-reinforcement-learning-1","title":"Skill-based Meta-Reinforcement Learning","date":"2022-04-25","arxiv_id":"2204.11828","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-reinforcement-learning-using-a-low","title":"Deep Reinforcement Learning Using a Low-Dimensional Observation Filter for Visual Complex Video Game Playing","date":"2022-04-24","arxiv_id":"2204.11370","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-reinforcement-learning-based-radio","title":"Deep Reinforcement Learning-based Radio Resource Allocation and Beam Management under Location Uncertainty in 5G mmWave Networks","date":"2022-04-23","arxiv_id":"2204.10984","repositories_listed":0,"syntology":null},{"url":null,"slug":"gfcl-a-gru-based-federated-continual-learning","title":"GFCL: A GRU-based Federated Continual Learning Framework against Data Poisoning Attacks in IoV","date":"2022-04-23","arxiv_id":"2204.11010","repositories_listed":0,"syntology":null},{"url":null,"slug":"transferring-convnet-features-from-passive-to","title":"Active Domain-Invariant Self-Localization Using Ego-Centric and World-Centric Maps","date":"2022-04-22","arxiv_id":"2204.10497","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-how-to-interact-with-a-complex","title":"Learning how to Interact with a Complex Interface using Hierarchical Reinforcement Learning","date":"2022-04-21","arxiv_id":"2204.10374","repositories_listed":0,"syntology":null}],"record_sha256":"615a4fa83e2c953b2c1eb8e9a7718f8aa8e6f32b95d2cd6a79a21caef028431c","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}