{"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/reinforcement-learning-1/papers/100","list_of":"/task/reinforcement-learning-1","task":"Reinforcement Learning (RL)","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":100,"pages_in_order":152,"rows_per_page":100,"rows":[9901,10000],"of":15113,"counts":{"archive_papers_tagged":15113,"with_a_code_link":4749,"where_syntology_ran_a_sample":1416,"not_listed_spam_title":0,"listed":15113,"listed_where_code_ran":1416,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":1186,"every_run_a_failure_of_syntologys_instrument":230,"listed_with_a_run_with_no_instrument_failure":1186,"listed_every_run_a_failure_of_syntologys_instrument":230,"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/reinforcement-learning-1","prev":"/task/reinforcement-learning-1/papers/99","next":"/task/reinforcement-learning-1/papers/101","papers":[{"url":null,"slug":"incentivizing-an-unknown-crowd","title":"Incentivizing an Unknown Crowd","date":"2021-09-09","arxiv_id":"2109.04226","repositories_listed":0,"syntology":null},{"url":null,"slug":"self-supervised-reinforcement-learning-with","title":"Self-supervised Reinforcement Learning with Independently Controllable Subgoals","date":"2021-09-09","arxiv_id":"2109.04150","repositories_listed":0,"syntology":null},{"url":null,"slug":"user-tampering-in-reinforcement-learning","title":"User Tampering in Reinforcement Learning Recommender Systems","date":"2021-09-09","arxiv_id":"2109.04083","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-deep-reinforcement-learning-approach-for-8","title":"A Deep Reinforcement Learning Approach for Online Parcel Assignment","date":"2021-09-08","arxiv_id":"2109.03467","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-survey-of-deep-reinforcement-learning-in-1","title":"A Survey of Deep Reinforcement Learning in Recommender Systems: A Systematic Review and Future Directions","date":"2021-09-08","arxiv_id":"2109.03540","repositories_listed":0,"syntology":null},{"url":null,"slug":"convergence-of-batch-asynchronous-stochastic","title":"Convergence of Batch Asynchronous Stochastic Approximation With Applications to Reinforcement Learning","date":"2021-09-08","arxiv_id":"2109.03445","repositories_listed":0,"syntology":null},{"url":null,"slug":"integrated-and-adaptive-guidance-and-control","title":"Integrated and Adaptive Guidance and Control for Endoatmospheric Missiles via Reinforcement Learning","date":"2021-09-08","arxiv_id":"2109.03880","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-zero-sum-stochastic-games-with","title":"A Bayesian Learning Algorithm for Unknown Zero-sum Stochastic Games with an Arbitrary Opponent","date":"2021-09-08","arxiv_id":"2109.03396","repositories_listed":0,"syntology":null},{"url":null,"slug":"where-did-you-learn-that-from-surprising","title":"Membership Inference Attacks Against Temporally Correlated Data in Deep Reinforcement Learning","date":"2021-09-08","arxiv_id":"2109.03975","repositories_listed":0,"syntology":null},{"url":null,"slug":"cygil-a-cyber-gym-for-training-autonomous","title":"CyGIL: A Cyber Gym for Training Autonomous Agents over Emulated Network Systems","date":"2021-09-07","arxiv_id":"2109.03331","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-the-impact-of-mdp-design-for-reinforcement","title":"On the impact of MDP design for Reinforcement Learning agents in Resource Management","date":"2021-09-07","arxiv_id":"2109.03202","repositories_listed":0,"syntology":null},{"url":null,"slug":"safe-critical-modular-deep-reinforcement","title":"Safety-Critical Learning of Robot Control with Temporal Logic Specifications","date":"2021-09-07","arxiv_id":"2109.02791","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-simbad-active-landmark-based-self","title":"Deep SIMBAD: Active Landmark-based Self-localization Using Ranking -based Scene Descriptor","date":"2021-09-06","arxiv_id":"2109.02786","repositories_listed":0,"syntology":null},{"url":null,"slug":"delving-into-macro-placement-with","title":"Delving into Macro Placement with Reinforcement Learning","date":"2021-09-06","arxiv_id":"2109.02587","repositories_listed":0,"syntology":null},{"url":null,"slug":"guiding-global-placement-with-reinforcement","title":"Guiding Global Placement With Reinforcement Learning","date":"2021-09-06","arxiv_id":"2109.02631","repositories_listed":0,"syntology":null},{"url":null,"slug":"hindsight-reward-tweaking-via-conditional","title":"Hindsight Reward Tweaking via Conditional Deep Reinforcement Learning","date":"2021-09-06","arxiv_id":"2109.02332","repositories_listed":0,"syntology":null},{"url":null,"slug":"method-for-making-multi-attribute-decisions","title":"Method for making multi-attribute decisions in wargames by combining intuitionistic fuzzy numbers with reinforcement learning","date":"2021-09-06","arxiv_id":"2109.02354","repositories_listed":0,"syntology":null},{"url":null,"slug":"recommendation-fairness-from-static-to","title":"Recommendation Fairness: From Static to Dynamic","date":"2021-09-05","arxiv_id":"2109.03150","repositories_listed":0,"syntology":null},{"url":null,"slug":"eden-a-unified-environment-framework-for","title":"Eden: A Unified Environment Framework for Booming Reinforcement Learning Algorithms","date":"2021-09-04","arxiv_id":"2109.01768","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-the-complexity-of-computing-markov-perfect","title":"On the Complexity of Computing Markov Perfect Equilibrium in General-Sum Stochastic Games","date":"2021-09-04","arxiv_id":"2109.01795","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-agent-natural-actor-critic","title":"Multi-agent Natural Actor-critic Reinforcement Learning Algorithms","date":"2021-09-03","arxiv_id":"2109.01654","repositories_listed":0,"syntology":null},{"url":null,"slug":"provably-safe-model-based-meta-reinforcement","title":"Provably Safe Model-Based Meta Reinforcement Learning: An Abstraction-Based Approach","date":"2021-09-03","arxiv_id":"2109.01255","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-oracle-and-observations-for-the-openai-gym","title":"An Oracle and Observations for the OpenAI Gym / ALE Freeway Environment","date":"2021-09-02","arxiv_id":"2109.01220","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-agent-inverse-reinforcement-learning-2","title":"Multi-Agent Inverse Reinforcement Learning: Suboptimal Demonstrations and Alternative Solution Concepts","date":"2021-09-02","arxiv_id":"2109.01178","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-for-battery-energy","title":"Reinforcement Learning for Battery Energy Storage Dispatch augmented with Model-based Optimizer","date":"2021-09-02","arxiv_id":"2109.01659","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-survey-of-exploration-methods-in","title":"A Survey of Exploration Methods in Reinforcement Learning","date":"2021-09-01","arxiv_id":"2109.00157","repositories_listed":0,"syntology":null},{"url":null,"slug":"boosting-search-engines-with-interactive","title":"Boosting Search Engines with Interactive Agents","date":"2021-09-01","arxiv_id":"2109.00527","repositories_listed":0,"syntology":null},{"url":null,"slug":"variational-quantum-reinforcement-learning","title":"Variational Quantum Reinforcement Learning via Evolutionary Optimization","date":"2021-09-01","arxiv_id":"2109.00540","repositories_listed":0,"syntology":null},{"url":null,"slug":"incorporating-deception-into-cyberbattlesim","title":"Incorporating Deception into CyberBattleSim for Autonomous Defense","date":"2021-08-31","arxiv_id":"2108.13980","repositories_listed":0,"syntology":null},{"url":null,"slug":"informing-autonomous-deception-systems-with","title":"Informing Autonomous Deception Systems with Cyber Expert Performance Data","date":"2021-08-31","arxiv_id":"2109.00066","repositories_listed":0,"syntology":null},{"url":null,"slug":"adaptive-perturbation-adversarial-training","title":"Adaptive perturbation adversarial training: based on reinforcement learning","date":"2021-08-30","arxiv_id":"2108.13239","repositories_listed":0,"syntology":null},{"url":null,"slug":"integrated-decision-and-control-at-multi-lane","title":"Integrated Decision and Control at Multi-Lane Intersections with Mixed Traffic Flow","date":"2021-08-30","arxiv_id":"2108.13038","repositories_listed":0,"syntology":null},{"url":null,"slug":"investigating-vulnerabilities-of-deep-neural","title":"Investigating Vulnerabilities of Deep Neural Policies","date":"2021-08-30","arxiv_id":"2108.13093","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-meta-representations-for-agents-in","title":"Learning Meta Representations for Agents in Multi-Agent Reinforcement Learning","date":"2021-08-30","arxiv_id":"2108.12988","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-policy-efficient-reduction-approach-to","title":"A Policy Efficient Reduction Approach to Convex Constrained Deep Reinforcement Learning","date":"2021-08-29","arxiv_id":"2108.12916","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-based-sparse-black-box","title":"Reinforcement Learning Based Sparse Black-box Adversarial Attack on Video Recognition Models","date":"2021-08-29","arxiv_id":"2108.13872","repositories_listed":0,"syntology":null},{"url":null,"slug":"influence-based-reinforcement-learning-for","title":"Influence-Based Reinforcement Learning for Intrinsically-Motivated Agents","date":"2021-08-28","arxiv_id":"2108.12581","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-reinforcement-learning-for-wireless-2","title":"Deep Reinforcement Learning for Wireless Resource Allocation Using Buffer State Information","date":"2021-08-27","arxiv_id":"2108.12198","repositories_listed":0,"syntology":null},{"url":null,"slug":"wad-a-deep-reinforcement-learning-agent-for","title":"WAD: A Deep Reinforcement Learning Agent for Urban Autonomous Driving","date":"2021-08-27","arxiv_id":"2108.12134","repositories_listed":0,"syntology":null},{"url":null,"slug":"adaptive-control-of-differentially-private","title":"Adaptive Control of Differentially Private Linear Quadratic Systems","date":"2021-08-26","arxiv_id":"2108.11563","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-reinforcement-learning-for-dynamic-band","title":"Deep Reinforcement Learning for Dynamic Band Switch in Cellular-Connected UAV","date":"2021-08-26","arxiv_id":"2108.12054","repositories_listed":0,"syntology":null},{"url":null,"slug":"federated-reinforcement-learning-techniques","title":"Federated Reinforcement Learning: Techniques, Applications, and Open Challenges","date":"2021-08-26","arxiv_id":"2108.11887","repositories_listed":0,"syntology":null},{"url":null,"slug":"model-based-chance-constrained-reinforcement","title":"Model-based Chance-Constrained Reinforcement Learning via Separated Proportional-Integral Lagrangian","date":"2021-08-26","arxiv_id":"2108.11623","repositories_listed":0,"syntology":null},{"url":null,"slug":"robust-model-based-reinforcement-learning-for","title":"Robust Model-based Reinforcement Learning for Autonomous Greenhouse Control","date":"2021-08-26","arxiv_id":"2108.11645","repositories_listed":0,"syntology":null},{"url":null,"slug":"when-should-agents-explore","title":"When should agents explore?","date":"2021-08-26","arxiv_id":"2108.11811","repositories_listed":0,"syntology":null},{"url":null,"slug":"adversary-agent-reinforcement-learning-for","title":"Adversary agent reinforcement learning for pursuit-evasion","date":"2021-08-25","arxiv_id":"2108.11010","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-reinforcement-learning-in-computer","title":"Deep Reinforcement Learning in Computer Vision: A Comprehensive Survey","date":"2021-08-25","arxiv_id":"2108.11510","repositories_listed":0,"syntology":null},{"url":null,"slug":"entropy-aware-model-initialization-for","title":"Entropy-Aware Model Initialization for Effective Exploration in Deep Reinforcement Learning","date":"2021-08-24","arxiv_id":"2108.10533","repositories_listed":0,"syntology":null},{"url":null,"slug":"self-optimizing-adaptive-optics-control-with-1","title":"Self-optimizing adaptive optics control with Reinforcement Learning for high-contrast imaging","date":"2021-08-24","arxiv_id":"2108.11332","repositories_listed":0,"syntology":null},{"url":null,"slug":"collect-infer-a-fresh-look-at-data-efficient","title":"Collect & Infer -- a fresh look at data-efficient Reinforcement Learning","date":"2021-08-23","arxiv_id":"2108.10273","repositories_listed":0,"syntology":null},{"url":null,"slug":"no-dba-no-regret-multi-armed-bandits-for","title":"No DBA? No regret! Multi-armed bandits for index tuning of analytical and HTAP workloads with provable guarantees","date":"2021-08-23","arxiv_id":"2108.10130","repositories_listed":0,"syntology":null},{"url":null,"slug":"power-grid-cascading-failure-mitigation-by","title":"Power Grid Cascading Failure Mitigation by Reinforcement Learning","date":"2021-08-23","arxiv_id":"2108.10424","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-boosting-approach-to-reinforcement-learning","title":"A Boosting Approach to Reinforcement Learning","date":"2021-08-22","arxiv_id":"2108.09767","repositories_listed":0,"syntology":null},{"url":null,"slug":"mimicbot-combining-imitation-and","title":"MimicBot: Combining Imitation and Reinforcement Learning to win in Bot Bowl","date":"2021-08-21","arxiv_id":"2108.09478","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-independent-study-of-reinforcement","title":"An Independent Study of Reinforcement Learning and Autonomous Driving","date":"2021-08-20","arxiv_id":"2110.07729","repositories_listed":0,"syntology":null},{"url":null,"slug":"crown-jewels-analysis-using-reinforcement","title":"Crown Jewels Analysis using Reinforcement Learning with Attack Graphs","date":"2021-08-20","arxiv_id":"2108.09358","repositories_listed":0,"syntology":null},{"url":null,"slug":"explainable-reinforcement-learning-for-broad","title":"Explainable Reinforcement Learning for Broad-XAI: A Conceptual Framework and Survey","date":"2021-08-20","arxiv_id":"2108.09003","repositories_listed":0,"syntology":null},{"url":null,"slug":"plug-and-play-model-based-reinforcement","title":"Plug and Play, Model-Based Reinforcement Learning","date":"2021-08-20","arxiv_id":"2108.08960","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-to-optimize-lifetime","title":"Reinforcement Learning to Optimize Lifetime Value in Cold-Start Recommendation","date":"2021-08-20","arxiv_id":"2108.09141","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-reinforcement-learning-approach-for-gnss","title":"A Reinforcement Learning Approach for GNSS Spoofing Attack Detection of Autonomous Vehicles","date":"2021-08-19","arxiv_id":"2108.08628","repositories_listed":0,"syntology":null},{"url":null,"slug":"cooperative-localization-utilizing","title":"Cooperative Localization Utilizing Reinforcement Learning for 5G Networks","date":"2021-08-19","arxiv_id":"2108.10222","repositories_listed":0,"syntology":null},{"url":null,"slug":"global-convergence-of-the-ode-limit-for","title":"Global Convergence of the ODE Limit for Online Actor-Critic Algorithms in Reinforcement Learning","date":"2021-08-19","arxiv_id":"2108.08655","repositories_listed":0,"syntology":null},{"url":null,"slug":"provable-benefits-of-actor-critic-methods-for","title":"Provable Benefits of Actor-Critic Methods for Offline Reinforcement Learning","date":"2021-08-19","arxiv_id":"2108.08812","repositories_listed":0,"syntology":null},{"url":null,"slug":"trends-in-neural-architecture-search-towards","title":"Trends in Neural Architecture Search: Towards the Acceleration of Search","date":"2021-08-19","arxiv_id":"2108.08474","repositories_listed":0,"syntology":null},{"url":null,"slug":"explainable-deep-reinforcement-learning-using","title":"Explainable Deep Reinforcement Learning Using Introspection in a Non-episodic Task","date":"2021-08-18","arxiv_id":"2108.08911","repositories_listed":0,"syntology":null},{"url":null,"slug":"optimal-placement-of-public-electric-vehicle","title":"Optimal Placement of Public Electric Vehicle Charging Stations Using Deep Reinforcement Learning","date":"2021-08-17","arxiv_id":"2108.07772","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforce-attack-adversarial-attack-against","title":"Reinforce Attack: Adversarial Attack against BERT with Reinforcement Learning","date":"2021-08-17","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"the-ecosystem-path-to-general-ai","title":"The Ecosystem Path to General AI","date":"2021-08-17","arxiv_id":"2108.07578","repositories_listed":0,"syntology":null},{"url":null,"slug":"heterotic-string-model-building-with-monad","title":"Heterotic String Model Building with Monad Bundles and Reinforcement Learning","date":"2021-08-16","arxiv_id":"2108.07316","repositories_listed":0,"syntology":null},{"url":null,"slug":"implicitly-regularized-rl-with-implicit-q","title":"Implicitly Regularized RL with Implicit Q-Values","date":"2021-08-16","arxiv_id":"2108.07041","repositories_listed":0,"syntology":null},{"url":null,"slug":"introduction-to-quantum-reinforcement","title":"Introduction to Quantum Reinforcement Learning: Theory and PennyLane-based Implementation","date":"2021-08-16","arxiv_id":"2108.06849","repositories_listed":0,"syntology":null},{"url":null,"slug":"neural-to-tree-policy-distillation-with","title":"Neural-to-Tree Policy Distillation with Policy Improvement Criterion","date":"2021-08-16","arxiv_id":"2108.06898","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-emergence-of-wireless-mac-protocols-with","title":"The Emergence of Wireless MAC Protocols with Multi-Agent Reinforcement Learning","date":"2021-08-16","arxiv_id":"2108.07144","repositories_listed":0,"syntology":null},{"url":null,"slug":"using-cyber-terrain-in-reinforcement-learning","title":"Using Cyber Terrain in Reinforcement Learning for Penetration Testing","date":"2021-08-16","arxiv_id":"2108.07124","repositories_listed":0,"syntology":null},{"url":null,"slug":"optimal-scheduling-of-isolated-microgrids","title":"Optimal Scheduling of Isolated Microgrids Using Automated Reinforcement Learning-based Multi-period Forecasting","date":"2021-08-15","arxiv_id":"2108.06764","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-microscopic-pandemic-simulator-for-pandemic","title":"A Microscopic Pandemic Simulator for Pandemic Prediction Using Scalable Million-Agent Reinforcement Learning","date":"2021-08-14","arxiv_id":"2108.06589","repositories_listed":0,"syntology":null},{"url":null,"slug":"adaptive-selection-of-informative-path","title":"Adaptive Selection of Informative Path Planning Strategies via Reinforcement Learning","date":"2021-08-14","arxiv_id":"2108.06618","repositories_listed":0,"syntology":null},{"url":null,"slug":"fractional-transfer-learning-for-deep-model","title":"Fractional Transfer Learning for Deep Model-Based Reinforcement Learning","date":"2021-08-14","arxiv_id":"2108.06526","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-to-assign-towards-fair-task","title":"Learning to Assign: Towards Fair Task Assignment in Large-Scale Ride Hailing","date":"2021-08-14","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"offline-online-reinforcement-learning-for","title":"Offline-Online Reinforcement Learning for Energy Pricing in Office Demand Response: Lowering Energy and Data Costs","date":"2021-08-14","arxiv_id":"2108.06594","repositories_listed":0,"syntology":null},{"url":null,"slug":"hac-explore-accelerating-exploration-with","title":"HAC Explore: Accelerating Exploration with Hierarchical Reinforcement Learning","date":"2021-08-12","arxiv_id":"2108.05872","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-approach-to-active","title":"Reinforcement Learning Approach to Active Learning for Image Classification","date":"2021-08-12","arxiv_id":"2108.05595","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-approach-to-partial-observability-in-games","title":"An Approach to Partial Observability in Games: Learning to Both Act and Observe","date":"2021-08-11","arxiv_id":"2108.05701","repositories_listed":0,"syntology":null},{"url":null,"slug":"does-explicit-prediction-matter-in-energy","title":"Does Explicit Prediction Matter in Deep Reinforcement Learning-Based Energy Management?","date":"2021-08-11","arxiv_id":"2108.05099","repositories_listed":0,"syntology":null},{"url":null,"slug":"integrating-process-design-and-control-using","title":"Integrating process design and control using reinforcement learning","date":"2021-08-11","arxiv_id":"2108.05242","repositories_listed":0,"syntology":null},{"url":null,"slug":"low-level-pose-control-of-tilting-multirotor","title":"Low-level Pose Control of Tilting Multirotor for Wall Perching Tasks Using Reinforcement Learning","date":"2021-08-11","arxiv_id":"2108.05457","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-survey-on-deep-reinforcement-learning-for-1","title":"A Survey on Deep Reinforcement Learning for Data Processing and Analytics","date":"2021-08-10","arxiv_id":"2108.04526","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-reinforcement-learning-for-demand-driven","title":"Deep Reinforcement Learning for Demand Driven Services in Logistics and Transportation Systems: A Survey","date":"2021-08-10","arxiv_id":"2108.04462","repositories_listed":0,"syntology":null},{"url":null,"slug":"high-quality-related-search-query-suggestions","title":"High Quality Related Search Query Suggestions using Deep Reinforcement Learning","date":"2021-08-10","arxiv_id":"2108.04452","repositories_listed":0,"syntology":null},{"url":null,"slug":"bob-and-alice-go-to-a-bar-reasoning-about","title":"Bob and Alice Go to a Bar: Reasoning About Future With Probabilistic Programs","date":"2021-08-09","arxiv_id":"2108.03834","repositories_listed":0,"syntology":null},{"url":null,"slug":"knowledge-accumulating-the-general-pattern-of","title":"Knowledge accumulating: The general pattern of learning","date":"2021-08-09","arxiv_id":"2108.03988","repositories_listed":0,"syntology":null},{"url":null,"slug":"mis-spoke-or-mis-lead-achieving-robustness-in","title":"Mis-spoke or mis-lead: Achieving Robustness in Multi-Agent Communicative Reinforcement Learning","date":"2021-08-09","arxiv_id":"2108.03803","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-proxemic-behavior-using","title":"Learning Proxemic Behavior Using Reinforcement Learning with Cognitive Agents","date":"2021-08-08","arxiv_id":"2108.03730","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-the-difficulty-of-generalizing","title":"On the Difficulty of Generalizing Reinforcement Learning Framework for Combinatorial Optimization","date":"2021-08-08","arxiv_id":"2108.03713","repositories_listed":0,"syntology":null},{"url":null,"slug":"online-bootstrap-inference-for-policy","title":"Online Bootstrap Inference For Policy Evaluation in Reinforcement Learning","date":"2021-08-08","arxiv_id":"2108.03706","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-representation-for-electric-vehicle","title":"Efficient Representation for Electric Vehicle Charging Station Operations using Reinforcement Learning","date":"2021-08-07","arxiv_id":"2108.03236","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-study-on-dense-and-sparse-visual-rewards-in","title":"A Study on Dense and Sparse (Visual) Rewards in Robot Policy Learning","date":"2021-08-06","arxiv_id":"2108.03222","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-reinforcement-learning-for-intelligent-3","title":"Deep Reinforcement Learning for Intelligent Reflecting Surface-assisted D2D Communications","date":"2021-08-06","arxiv_id":"2108.02892","repositories_listed":0,"syntology":null},{"url":null,"slug":"semantic-tracklets-an-object-centric","title":"Semantic Tracklets: An Object-Centric Representation for Visual Multi-Agent Reinforcement Learning","date":"2021-08-06","arxiv_id":"2108.03319","repositories_listed":0,"syntology":null},{"url":null,"slug":"active-reinforcement-learning-over-mdps","title":"Active Reinforcement Learning over MDPs","date":"2021-08-05","arxiv_id":"2108.02323","repositories_listed":0,"syntology":null}],"record_sha256":"0d5183855be2606350b14a4777fe60cd4cb25d42f123c602c31527808571e493","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}