{"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/papers/81","list_of":"/task/reinforcement-learning","task":"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":81,"pages_in_order":132,"rows_per_page":100,"rows":[8001,8100],"of":13178,"counts":{"archive_papers_tagged":13178,"with_a_code_link":4183,"where_syntology_ran_a_sample":1175,"not_listed_spam_title":0,"listed":13178,"listed_where_code_ran":1175,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":988,"every_run_a_failure_of_syntologys_instrument":187,"listed_with_a_run_with_no_instrument_failure":988,"listed_every_run_a_failure_of_syntologys_instrument":187,"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","prev":"/task/reinforcement-learning/papers/80","next":"/task/reinforcement-learning/papers/82","papers":[{"url":null,"slug":"an-offline-deep-reinforcement-learning-for","title":"An Offline Deep Reinforcement Learning for Maintenance Decision-Making","date":"2021-09-28","arxiv_id":"2109.15050","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-reinforcement-learning-versus-evolution","title":"Deep Reinforcement Learning Versus Evolution Strategies: A Comparative Survey","date":"2021-09-28","arxiv_id":"2110.01411","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-reinforcement-learning-with-adjustments","title":"Deep Reinforcement Learning with Adjustments","date":"2021-09-28","arxiv_id":"2109.13463","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-more-when-it-needs-in-deep","title":"Exploring More When It Needs in Deep Reinforcement Learning","date":"2021-09-28","arxiv_id":"2109.13477","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-for-quantitative","title":"Reinforcement Learning for Quantitative Trading","date":"2021-09-28","arxiv_id":"2109.13851","repositories_listed":0,"syntology":null},{"url":null,"slug":"from-internal-models-toward-metacognitive-ai","title":"From internal models toward metacognitive AI","date":"2021-09-27","arxiv_id":"2109.12798","repositories_listed":0,"syntology":null},{"url":null,"slug":"model-free-reinforcement-learning-for-optimal","title":"Model-Free Reinforcement Learning for Optimal Control of MarkovDecision Processes Under Signal Temporal Logic Specifications","date":"2021-09-27","arxiv_id":"2109.13377","repositories_listed":0,"syntology":null},{"url":null,"slug":"combing-policy-evaluation-and-policy","title":"The $f$-Divergence Reinforcement Learning Framework","date":"2021-09-24","arxiv_id":"2109.11867","repositories_listed":0,"syntology":null},{"url":null,"slug":"go-blend-behavior-and-affect","title":"Go-Blend behavior and affect","date":"2021-09-24","arxiv_id":"2109.13388","repositories_listed":0,"syntology":null},{"url":null,"slug":"learnable-triangulation-for-deep-learning","title":"Learnable Triangulation for Deep Learning-based 3D Reconstruction of Objects of Arbitrary Topology from Single RGB Images","date":"2021-09-24","arxiv_id":"2109.11844","repositories_listed":0,"syntology":null},{"url":null,"slug":"neuroprospecting-with-deeprl-agents","title":"Neuroprospecting with DeepRL agents","date":"2021-09-24","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"regularization-guarantees-generalization-in","title":"Regularization Guarantees Generalization in Bayesian Reinforcement Learning through Algorithmic Stability","date":"2021-09-24","arxiv_id":"2109.11792","repositories_listed":0,"syntology":null},{"url":null,"slug":"hierarchies-of-planning-and-reinforcement","title":"Hierarchies of Planning and Reinforcement Learning for Robot Navigation","date":"2021-09-23","arxiv_id":"2109.11178","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-under-algorithmic","title":"Reinforcement Learning Under Algorithmic Triage","date":"2021-09-23","arxiv_id":"2109.11328","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-survey-on-reinforcement-learning-for-1","title":"A Survey on Reinforcement Learning for Recommender Systems","date":"2021-09-22","arxiv_id":"2109.10665","repositories_listed":0,"syntology":null},{"url":null,"slug":"adversarial-training-blocks-generalization-in","title":"Adversarial Training Blocks Generalization in Neural Policies","date":"2021-09-22","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"benchmarking-lane-changing-decision-making","title":"Benchmarking Lane-changing Decision-making for Deep Reinforcement Learning","date":"2021-09-22","arxiv_id":"2109.10490","repositories_listed":0,"syntology":null},{"url":null,"slug":"introducing-symmetries-to-black-box-meta","title":"Introducing Symmetries to Black Box Meta Reinforcement Learning","date":"2021-09-22","arxiv_id":"2109.10781","repositories_listed":0,"syntology":null},{"url":null,"slug":"return-dispersion-as-an-estimator-of-learning","title":"Return Dispersion as an Estimator of Learning Potential for Prioritized Level Replay","date":"2021-09-22","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-multi-agent-reinforcement-learning-1","title":"Towards Multi-Agent Reinforcement Learning using Quantum Boltzmann Machines","date":"2021-09-22","arxiv_id":"2109.10900","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-simple-unified-framework-for-anomaly","title":"A Distance-based Anomaly Detection Framework for Deep Reinforcement Learning","date":"2021-09-21","arxiv_id":"2109.09889","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-offline-memory-replay-in-biological","title":"Learning offline: memory replay in biological and artificial reinforcement learning","date":"2021-09-21","arxiv_id":"2109.10034","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-reinforcement-learning-approach-to-the-1","title":"A Reinforcement Learning Approach to the Stochastic Cutting Stock Problem","date":"2021-09-20","arxiv_id":"2109.09592","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-survey-of-text-games-for-reinforcement","title":"A Survey of Text Games for Reinforcement Learning informed by Natural Language","date":"2021-09-20","arxiv_id":"2109.09478","repositories_listed":0,"syntology":null},{"url":null,"slug":"carl-conditional-value-at-risk-adversarial","title":"ACReL: Adversarial Conditional value-at-risk Reinforcement Learning","date":"2021-09-20","arxiv_id":"2109.09470","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-natural-language-generation-from","title":"Learning Natural Language Generation from Scratch","date":"2021-09-20","arxiv_id":"2109.09371","repositories_listed":0,"syntology":null},{"url":null,"slug":"two-approaches-to-building-collaborative-task","title":"Two Approaches to Building Collaborative, Task-Oriented Dialog Agents through Self-Play","date":"2021-09-20","arxiv_id":"2109.09597","repositories_listed":0,"syntology":null},{"url":null,"slug":"dual-behavior-regularized-reinforcement","title":"Dual Behavior Regularized Reinforcement Learning","date":"2021-09-19","arxiv_id":"2109.09037","repositories_listed":0,"syntology":null},{"url":null,"slug":"greedy-unmixing-for-q-learning-in-multi-agent","title":"Greedy UnMixing for Q-Learning in Multi-Agent Reinforcement Learning","date":"2021-09-19","arxiv_id":"2109.09034","repositories_listed":0,"syntology":null},{"url":null,"slug":"lifelong-robotic-reinforcement-learning-by","title":"Lifelong Robotic Reinforcement Learning by Retaining Experiences","date":"2021-09-19","arxiv_id":"2109.09180","repositories_listed":0,"syntology":null},{"url":null,"slug":"soft-actor-critic-with-integer-actions","title":"Soft Actor-Critic With Integer Actions","date":"2021-09-17","arxiv_id":"2109.08512","repositories_listed":0,"syntology":null},{"url":null,"slug":"adaptive-control-of-quadratic-costs-in-linear","title":"Reinforcement Learning Policies in Continuous-Time Linear Systems","date":"2021-09-16","arxiv_id":"2109.07630","repositories_listed":0,"syntology":null},{"url":null,"slug":"conservative-data-sharing-for-multi-task","title":"Conservative Data Sharing for Multi-Task Offline Reinforcement Learning","date":"2021-09-16","arxiv_id":"2109.08128","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-from-peers-transfer-reinforcement","title":"Learning from Peers: Deep Transfer Reinforcement Learning for Joint Radio and Cache Resource Allocation in 5G RAN Slicing","date":"2021-09-16","arxiv_id":"2109.07999","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-on-encrypted-data","title":"Reinforcement Learning on Encrypted Data","date":"2021-09-16","arxiv_id":"2109.08236","repositories_listed":0,"syntology":null},{"url":null,"slug":"convergence-of-a-human-in-the-loop-policy","title":"Convergence of a Human-in-the-Loop Policy-Gradient Algorithm With Eligibility Trace Under Reward, Policy, and Advantage Feedback","date":"2021-09-15","arxiv_id":"2109.07054","repositories_listed":0,"syntology":null},{"url":null,"slug":"optimal-cycling-of-a-heterogenous-battery","title":"Optimal Cycling of a Heterogenous Battery Bank via Reinforcement Learning","date":"2021-09-15","arxiv_id":"2109.07137","repositories_listed":0,"syntology":null},{"url":null,"slug":"short-quantum-circuits-in-reinforcement","title":"Short Quantum Circuits in Reinforcement Learning Policies for the Vehicle Routing Problem","date":"2021-09-15","arxiv_id":"2109.07498","repositories_listed":0,"syntology":null},{"url":null,"slug":"continuous-homeostatic-reinforcement-learning","title":"Continuous Homeostatic Reinforcement Learning for Self-Regulated Autonomous Agents","date":"2021-09-14","arxiv_id":"2109.06580","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploration-in-deep-reinforcement-learning-a","title":"Exploration in Deep Reinforcement Learning: From Single-Agent to Multiagent Domain","date":"2021-09-14","arxiv_id":"2109.06668","repositories_listed":0,"syntology":null},{"url":null,"slug":"romax-certifiably-robust-deep-multiagent","title":"ROMAX: Certifiably Robust Deep Multiagent Reinforcement Learning via Convex Relaxation","date":"2021-09-14","arxiv_id":"2109.06795","repositories_listed":0,"syntology":null},{"url":null,"slug":"radars-memory-efficient-reinforcement","title":"RADARS: Memory Efficient Reinforcement Learning Aided Differentiable Neural Architecture Search","date":"2021-09-13","arxiv_id":"2109.05691","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-for-load-balanced","title":"Reinforcement Learning for Load-balanced Parallel Particle Tracing","date":"2021-09-13","arxiv_id":"2109.05679","repositories_listed":0,"syntology":null},{"url":null,"slug":"theoretical-guarantees-of-fictitious-discount","title":"Theoretical Guarantees of Fictitious Discount Algorithms for Episodic Reinforcement Learning and Global Convergence of Policy Gradient Methods","date":"2021-09-13","arxiv_id":"2109.06362","repositories_listed":0,"syntology":null},{"url":null,"slug":"concave-utility-reinforcement-learning-with","title":"Concave Utility Reinforcement Learning with Zero-Constraint Violations","date":"2021-09-12","arxiv_id":"2109.05439","repositories_listed":0,"syntology":null},{"url":null,"slug":"federated-ensemble-model-based-reinforcement","title":"Federated Ensemble Model-based Reinforcement Learning in Edge Computing","date":"2021-09-12","arxiv_id":"2109.05549","repositories_listed":0,"syntology":null},{"url":null,"slug":"financial-trading-with-feature-preprocessing","title":"Financial Trading with Feature Preprocessing and Recurrent Reinforcement Learning","date":"2021-09-11","arxiv_id":"2109.05283","repositories_listed":0,"syntology":null},{"url":null,"slug":"data-generation-method-for-learning-a-low","title":"Data Generation Method for Learning a Low-dimensional Safe Region in Safe Reinforcement Learning","date":"2021-09-10","arxiv_id":"2109.05077","repositories_listed":0,"syntology":null},{"url":null,"slug":"projected-state-action-balancing-weights-for","title":"Projected State-action Balancing Weights for Offline Reinforcement Learning","date":"2021-09-10","arxiv_id":"2109.04640","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":"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":"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":"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":"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":"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":"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":"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":"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":"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":"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":"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":"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":"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":"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":"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":"improving-human-decision-making-with-machine","title":"Improving Human Sequential Decision-Making with Reinforcement Learning","date":"2021-08-19","arxiv_id":"2108.08454","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":"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":"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":"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":"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":"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":"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":"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":"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}],"record_sha256":"57665bd05228c4a81a6d9168972d4f8ae98caca054a564a49b5d9b36b0d32415","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}