{"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/106","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":106,"pages_in_order":152,"rows_per_page":100,"rows":[10501,10600],"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/105","next":"/task/reinforcement-learning-1/papers/107","papers":[{"url":null,"slug":"rule-based-reinforcement-learning-for","title":"Rule-Based Reinforcement Learning for Efficient Robot Navigation with Space Reduction","date":"2021-04-15","arxiv_id":"2104.07282","repositories_listed":0,"syntology":null},{"url":null,"slug":"gan-based-interactive-reinforcement-learning","title":"GAN-Based Interactive Reinforcement Learning from Demonstration and Human Evaluative Feedback","date":"2021-04-14","arxiv_id":"2104.06600","repositories_listed":0,"syntology":null},{"url":null,"slug":"gridtopix-training-embodied-agents-with","title":"GridToPix: Training Embodied Agents with Minimal Supervision","date":"2021-04-14","arxiv_id":"2105.00931","repositories_listed":0,"syntology":null},{"url":null,"slug":"visual-comfort-aware-reinforcement-learning","title":"Visual Comfort Aware-Reinforcement Learning for Depth Adjustment of Stereoscopic 3D Images","date":"2021-04-14","arxiv_id":"2104.06782","repositories_listed":0,"syntology":null},{"url":null,"slug":"bi-level-off-policy-reinforcement-learning","title":"Bi-level Off-policy Reinforcement Learning for Volt/VAR Control Involving Continuous and Discrete Devices","date":"2021-04-13","arxiv_id":"2104.05902","repositories_listed":0,"syntology":null},{"url":null,"slug":"data-driven-reinforcement-learning-for","title":"Data-Driven Reinforcement Learning for Virtual Character Animation Control","date":"2021-04-13","arxiv_id":"2104.06358","repositories_listed":0,"syntology":null},{"url":null,"slug":"optimizing-the-long-term-average-reward-for","title":"Optimizing the Long-Term Average Reward for Continuing MDPs: A Technical Report","date":"2021-04-13","arxiv_id":"2104.06139","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-for-admission-control","title":"Reinforcement learning for Admission Control in 5G Wireless Networks","date":"2021-04-13","arxiv_id":"2104.10761","repositories_listed":0,"syntology":null},{"url":null,"slug":"reward-shaping-with-dynamic-trajectory","title":"Reward Shaping with Dynamic Trajectory Aggregation","date":"2021-04-13","arxiv_id":"2104.06163","repositories_listed":0,"syntology":null},{"url":null,"slug":"reward-shaping-with-subgoals-for-social","title":"Reward Shaping with Subgoals for Social Navigation","date":"2021-04-13","arxiv_id":"2104.06410","repositories_listed":0,"syntology":null},{"url":null,"slug":"subgoal-based-reward-shaping-to-improve","title":"Subgoal-based Reward Shaping to Improve Efficiency in Reinforcement Learning","date":"2021-04-13","arxiv_id":"2104.06411","repositories_listed":0,"syntology":null},{"url":null,"slug":"two-stage-training-algorithm-for-ai-robot","title":"Two-stage training algorithm for AI robot soccer","date":"2021-04-13","arxiv_id":"2104.05931","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-reinforcement-learning-based-controller","title":"Deep Reinforcement Learning Based Controller for Active Heave Compensation","date":"2021-04-12","arxiv_id":"2104.05599","repositories_listed":0,"syntology":null},{"url":null,"slug":"dynamic-matching-markets-in-power-grid","title":"Dynamic Matching Markets in Power Grid: Concepts and Solution using Deep Reinforcement Learning","date":"2021-04-12","arxiv_id":"2104.05654","repositories_listed":0,"syntology":null},{"url":null,"slug":"survey-on-reinforcement-learning-for-language","title":"Survey on reinforcement learning for language processing","date":"2021-04-12","arxiv_id":"2104.05565","repositories_listed":0,"syntology":null},{"url":null,"slug":"learn-goal-conditioned-policy-with-intrinsic-1","title":"Learn Goal-Conditioned Policy with Intrinsic Motivation for Deep Reinforcement Learning","date":"2021-04-11","arxiv_id":"2104.05043","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-reinforcement-learning-based-energy","title":"A Reinforcement-Learning-Based Energy-Efficient Framework for Multi-Task Video Analytics Pipeline","date":"2021-04-09","arxiv_id":"2104.04443","repositories_listed":0,"syntology":null},{"url":null,"slug":"inverse-reinforcement-learning-a-control","title":"Inverse Reinforcement Learning: A Control Lyapunov Approach","date":"2021-04-09","arxiv_id":"2104.04483","repositories_listed":0,"syntology":null},{"url":null,"slug":"jamming-resilient-path-planning-for-multiple","title":"Jamming-Resilient Path Planning for Multiple UAVs via Deep Reinforcement Learning","date":"2021-04-09","arxiv_id":"2104.04477","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-sampling-policy-for-faster","title":"Learning Sampling Policy for Faster Derivative Free Optimization","date":"2021-04-09","arxiv_id":"2104.04405","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-to-reweight-imaginary-transitions","title":"Learning to Reweight Imaginary Transitions for Model-Based Reinforcement Learning","date":"2021-04-09","arxiv_id":"2104.04174","repositories_listed":0,"syntology":null},{"url":null,"slug":"symmetry-reduction-for-deep-reinforcement","title":"Symmetry reduction for deep reinforcement learning active control of chaotic spatiotemporal dynamics","date":"2021-04-09","arxiv_id":"2104.05437","repositories_listed":0,"syntology":null},{"url":null,"slug":"acerac-efficient-reinforcement-learning-in","title":"ACERAC: Efficient reinforcement learning in fine time discretization","date":"2021-04-08","arxiv_id":"2104.04004","repositories_listed":0,"syntology":null},{"url":null,"slug":"finite-sample-analysis-for-two-time-scale-non","title":"Non-Asymptotic Analysis for Two Time-scale TDC with General Smooth Function Approximation","date":"2021-04-07","arxiv_id":"2104.02836","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-with-a-disentangled","title":"Reinforcement Learning with a Disentangled Universal Value Function for Item Recommendation","date":"2021-04-07","arxiv_id":"2104.02981","repositories_listed":0,"syntology":null},{"url":null,"slug":"risk-conditioned-distributional-soft-actor","title":"Risk-Conditioned Distributional Soft Actor-Critic for Risk-Sensitive Navigation","date":"2021-04-07","arxiv_id":"2104.03111","repositories_listed":0,"syntology":null},{"url":null,"slug":"unsupervised-visual-attention-and-invariance","title":"Unsupervised Visual Attention and Invariance for Reinforcement Learning","date":"2021-04-07","arxiv_id":"2104.02921","repositories_listed":0,"syntology":null},{"url":null,"slug":"approximate-robust-nmpc-using-reinforcement","title":"Approximate Robust NMPC using Reinforcement Learning","date":"2021-04-06","arxiv_id":"2104.02743","repositories_listed":0,"syntology":null},{"url":null,"slug":"data-driven-simulation-of-ride-hailing","title":"Data-Driven Simulation of Ride-Hailing Services using Imitation and Reinforcement Learning","date":"2021-04-06","arxiv_id":"2104.02661","repositories_listed":0,"syntology":null},{"url":null,"slug":"distributed-deep-reinforcement-learning-for-3","title":"Distributed Deep Reinforcement Learning for Collaborative Spectrum Sharing","date":"2021-04-06","arxiv_id":"2104.02059","repositories_listed":0,"syntology":null},{"url":null,"slug":"mpc-based-reinforcement-learning-for-economic","title":"MPC-based Reinforcement Learning for Economic Problems with Application to Battery Storage","date":"2021-04-06","arxiv_id":"2104.02411","repositories_listed":0,"syntology":null},{"url":null,"slug":"progressive-extension-of-reinforcement","title":"Progressive extension of reinforcement learning action dimension for asymmetric assembly tasks","date":"2021-04-06","arxiv_id":"2104.04078","repositories_listed":0,"syntology":null},{"url":null,"slug":"temporal-logic-based-intermittent-optimal-and","title":"Temporal-Logic-Based Intermittent, Optimal, and Safe Continuous-Time Learning for Trajectory Tracking","date":"2021-04-06","arxiv_id":"2104.02547","repositories_listed":0,"syntology":null},{"url":null,"slug":"zeus-efficiently-localizing-actions-in-videos","title":"Zeus: Efficiently Localizing Actions in Videos using Reinforcement Learning","date":"2021-04-06","arxiv_id":"2104.06142","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-dual-critic-reinforcement-learning","title":"A Dual-Critic Reinforcement Learning Framework for Frame-level Bit Allocation in HEVC/H.265","date":"2021-04-05","arxiv_id":"2104.01735","repositories_listed":0,"syntology":null},{"url":null,"slug":"machine-learning-applications-in-the-routing","title":"Machine Learning Applications in the Routing in Computer Networks","date":"2021-04-05","arxiv_id":"2104.01946","repositories_listed":0,"syntology":null},{"url":null,"slug":"non-monotonic-value-function-factorization","title":"NQMIX: Non-monotonic Value Function Factorization for Deep Multi-Agent Reinforcement Learning","date":"2021-04-05","arxiv_id":"2104.01939","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-transformers-in-reinforcement-1","title":"Efficient Transformers in Reinforcement Learning using Actor-Learner Distillation","date":"2021-04-04","arxiv_id":"2104.01655","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-for-minimizing-age-of","title":"Distributed Reinforcement Learning for Age of Information Minimization in Real-Time IoT Systems","date":"2021-04-04","arxiv_id":"2104.01527","repositories_listed":0,"syntology":null},{"url":null,"slug":"solo-search-online-learn-offline-for","title":"SOLO: Search Online, Learn Offline for Combinatorial Optimization Problems","date":"2021-04-04","arxiv_id":"2104.01646","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-dynamics-perspective-of-pursuit-evasion","title":"A Dynamics Perspective of Pursuit-Evasion Games of Intelligent Agents with the Ability to Learn","date":"2021-04-03","arxiv_id":"2104.01445","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-reinforcement-learning-powered-irs","title":"Deep Reinforcement Learning Powered IRS-Assisted Downlink NOMA","date":"2021-04-03","arxiv_id":"2104.01414","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-for-emotional-text-to","title":"Reinforcement Learning for Emotional Text-to-Speech Synthesis with Improved Emotion Discriminability","date":"2021-04-03","arxiv_id":"2104.01408","repositories_listed":0,"syntology":null},{"url":null,"slug":"federated-double-deep-q-learning-for-joint","title":"Federated Double Deep Q-learning for Joint Delay and Energy Minimization in IoT networks","date":"2021-04-02","arxiv_id":"2104.11320","repositories_listed":0,"syntology":null},{"url":null,"slug":"low-dose-helical-cbct-denoising-by-using","title":"Low Dose Helical CBCT denoising by using domain filtering with deep reinforcement learning","date":"2021-04-02","arxiv_id":"2104.00889","repositories_listed":0,"syntology":null},{"url":null,"slug":"adapool-a-diurnal-adaptive-fleet-management","title":"AdaPool: A Diurnal-Adaptive Fleet Management Framework using Model-Free Deep Reinforcement Learning and Change Point Detection","date":"2021-04-01","arxiv_id":"2104.00203","repositories_listed":0,"syntology":null},{"url":null,"slug":"multiple-tasks-integration-tagging-syntactic","title":"Multiple Tasks Integration: Tagging, Syntactic and Semantic Parsing as a Single Task","date":"2021-04-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"optimization-algorithm-for-feedback-and","title":"Optimization Algorithm for Feedback and Feedforward Policies towards Robot Control Robust to Sensing Failures","date":"2021-04-01","arxiv_id":"2104.00385","repositories_listed":0,"syntology":null},{"url":null,"slug":"trajectory-tracking-of-underactuated-sea","title":"Trajectory Tracking of Underactuated Sea Vessels With Uncertain Dynamics: An Integral Reinforcement Learning Approach","date":"2021-04-01","arxiv_id":"2104.00190","repositories_listed":0,"syntology":null},{"url":null,"slug":"dealio-data-efficient-adversarial-learning","title":"DEALIO: Data-Efficient Adversarial Learning for Imitation from Observation","date":"2021-03-31","arxiv_id":"2104.00163","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-reinforcement-learning-for-constrained","title":"Deep Reinforcement Learning for Constrained Field Development Optimization in Subsurface Two-phase Flow","date":"2021-03-31","arxiv_id":"2104.00527","repositories_listed":0,"syntology":null},{"url":null,"slug":"energy-efficient-edge-computing-when-lyapunov","title":"Energy Efficient Edge Computing: When Lyapunov Meets Distributed Reinforcement Learning","date":"2021-03-31","arxiv_id":"2103.16985","repositories_listed":0,"syntology":null},{"url":null,"slug":"generalized-reinforcement-learning-for","title":"Generalized Reinforcement Learning for Building Control using Behavioral Cloning","date":"2021-03-31","arxiv_id":"2104.00123","repositories_listed":0,"syntology":null},{"url":null,"slug":"rlad-time-series-anomaly-detection-through","title":"RLAD: Time Series Anomaly Detection through Reinforcement Learning and Active Learning","date":"2021-03-31","arxiv_id":"2104.00543","repositories_listed":0,"syntology":null},{"url":null,"slug":"solving-heterogeneous-general-equilibrium","title":"Solving Heterogeneous General Equilibrium Economic Models with Deep Reinforcement Learning","date":"2021-03-31","arxiv_id":"2103.16977","repositories_listed":0,"syntology":null},{"url":null,"slug":"fair-iot-fairness-aware-human-in-the-loop","title":"FaiR-IoT: Fairness-aware Human-in-the-Loop Reinforcement Learning for Harnessing Human Variability in Personalized IoT","date":"2021-03-30","arxiv_id":"2103.16033","repositories_listed":0,"syntology":null},{"url":null,"slug":"greedy-gq-with-variance-reduction-finite-time-1","title":"Greedy-GQ with Variance Reduction: Finite-time Analysis and Improved Complexity","date":"2021-03-30","arxiv_id":"2103.16377","repositories_listed":0,"syntology":null},{"url":null,"slug":"online-policies-for-real-time-control-using","title":"Online Policies for Real-Time Control Using MRAC-RL","date":"2021-03-30","arxiv_id":"2103.16551","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-for-optimization-of-1","title":"Reinforcement learning for optimization of variational quantum circuit architectures","date":"2021-03-30","arxiv_id":"2103.16089","repositories_listed":0,"syntology":null},{"url":null,"slug":"augmenting-automated-game-testing-with-deep","title":"Augmenting Automated Game Testing with Deep Reinforcement Learning","date":"2021-03-29","arxiv_id":"2103.15819","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-hedging-of-derivatives-using","title":"Deep Hedging of Derivatives Using Reinforcement Learning","date":"2021-03-29","arxiv_id":"2103.16409","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-reinforcement-learning-of-event","title":"Deep reinforcement learning of event-triggered communication and control for multi-agent cooperative transport","date":"2021-03-29","arxiv_id":"2103.15260","repositories_listed":0,"syntology":null},{"url":null,"slug":"joint-resource-management-for-mc-noma-a-deep","title":"Joint Resource Management for MC-NOMA: A Deep Reinforcement Learning Approach","date":"2021-03-29","arxiv_id":"2103.15371","repositories_listed":0,"syntology":null},{"url":null,"slug":"laser-learning-a-latent-action-space-for","title":"LASER: Learning a Latent Action Space for Efficient Reinforcement Learning","date":"2021-03-29","arxiv_id":"2103.15793","repositories_listed":0,"syntology":null},{"url":null,"slug":"measuring-sample-efficiency-and","title":"Measuring Sample Efficiency and Generalization in Reinforcement Learning Benchmarks: NeurIPS 2020 Procgen Benchmark","date":"2021-03-29","arxiv_id":"2103.15332","repositories_listed":0,"syntology":null},{"url":null,"slug":"ph-rl-a-personalization-architecture-to","title":"pH-RL: A personalization architecture to bring reinforcement learning to health practice","date":"2021-03-29","arxiv_id":"2103.15908","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-beyond-expectation","title":"Reinforcement Learning Beyond Expectation","date":"2021-03-29","arxiv_id":"2104.00540","repositories_listed":0,"syntology":null},{"url":null,"slug":"knowru-knowledge-reusing-via-knowledge","title":"KnowRU: Knowledge Reusing via Knowledge Distillation in Multi-agent Reinforcement Learning","date":"2021-03-27","arxiv_id":"2103.14891","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-convex-programming-approach-to-data-driven","title":"A Convex Programming Approach to Data-Driven Risk-Averse Reinforcement Learning","date":"2021-03-26","arxiv_id":"2103.14606","repositories_listed":0,"syntology":null},{"url":null,"slug":"autonomous-overtaking-in-gran-turismo-sport","title":"Autonomous Overtaking in Gran Turismo Sport Using Curriculum Reinforcement Learning","date":"2021-03-26","arxiv_id":"2103.14666","repositories_listed":0,"syntology":null},{"url":null,"slug":"barrier-function-based-safe-reinforcement","title":"Barrier Function-based Safe Reinforcement Learning for Emergency Control of Power Systems","date":"2021-03-26","arxiv_id":"2103.14186","repositories_listed":0,"syntology":null},{"url":null,"slug":"increasing-the-efficiency-of-policy-learning","title":"Increasing the Efficiency of Policy Learning for Autonomous Vehicles by Multi-Task Representation Learning","date":"2021-03-26","arxiv_id":"2103.14718","repositories_listed":0,"syntology":null},{"url":null,"slug":"model-free-learning-of-safe-yet-effective","title":"Model-Free Learning of Safe yet Effective Controllers","date":"2021-03-26","arxiv_id":"2103.14600","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-for-robust","title":"Reinforcement Learning for Robust Parameterized Locomotion Control of Bipedal Robots","date":"2021-03-26","arxiv_id":"2103.14295","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-meta-reinforcement-learning-approach-to","title":"A Meta-Reinforcement Learning Approach to Process Control","date":"2021-03-25","arxiv_id":"2103.14060","repositories_listed":0,"syntology":null},{"url":null,"slug":"aoa-based-pilot-assignment-in-massive-mimo","title":"AoA-Based Pilot Assignment in Massive MIMO Systems Using Deep Reinforcement Learning","date":"2021-03-25","arxiv_id":"2103.13791","repositories_listed":0,"syntology":null},{"url":null,"slug":"hierarchical-program-triggered-reinforcement","title":"Hierarchical Program-Triggered Reinforcement Learning Agents For Automated Driving","date":"2021-03-25","arxiv_id":"2103.13861","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-playtesting-coverage-via-curiosity","title":"Improving Playtesting Coverage via Curiosity Driven Reinforcement Learning Agents","date":"2021-03-25","arxiv_id":"2103.13798","repositories_listed":0,"syntology":null},{"url":null,"slug":"nearly-horizon-free-offline-reinforcement","title":"Nearly Horizon-Free Offline Reinforcement Learning","date":"2021-03-25","arxiv_id":"2103.14077","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-for-deceiving-reactive","title":"Reinforcement Learning for Deceiving Reactive Jammers in Wireless Networks","date":"2021-03-25","arxiv_id":"2103.14056","repositories_listed":0,"syntology":null},{"url":null,"slug":"risk-bounds-and-rademacher-complexity-in","title":"Risk Bounds and Rademacher Complexity in Batch Reinforcement Learning","date":"2021-03-25","arxiv_id":"2103.13883","repositories_listed":0,"syntology":null},{"url":null,"slug":"self-imitation-learning-by-planning","title":"Self-Imitation Learning by Planning","date":"2021-03-25","arxiv_id":"2103.13834","repositories_listed":0,"syntology":null},{"url":null,"slug":"cautiously-optimistic-policy-optimization-and","title":"Cautiously Optimistic Policy Optimization and Exploration with Linear Function Approximation","date":"2021-03-24","arxiv_id":"2103.12923","repositories_listed":0,"syntology":null},{"url":null,"slug":"clamgen-closed-loop-arm-motion-generation-via","title":"CLAMGen: Closed-Loop Arm Motion Generation via Multi-view Vision-Based RL","date":"2021-03-24","arxiv_id":"2103.13267","repositories_listed":0,"syntology":null},{"url":null,"slug":"discriminator-augmented-model-based","title":"Discriminator Augmented Model-Based Reinforcement Learning","date":"2021-03-24","arxiv_id":"2103.12999","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-gradient-convergence-bound-of-federated","title":"The Gradient Convergence Bound of Federated Multi-Agent Reinforcement Learning with Efficient Communication","date":"2021-03-24","arxiv_id":"2103.13026","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-exponential-lower-bound-for-linearly","title":"An Exponential Lower Bound for Linearly-Realizable MDPs with Constant Suboptimality Gap","date":"2021-03-23","arxiv_id":"2103.12690","repositories_listed":0,"syntology":null},{"url":null,"slug":"assured-learning-enabled-autonomy-a","title":"Assured Learning-enabled Autonomy: A Metacognitive Reinforcement Learning Framework","date":"2021-03-23","arxiv_id":"2103.12558","repositories_listed":0,"syntology":null},{"url":null,"slug":"hamiltonian-policy-optimization-in","title":"Hamiltonian Policy Optimization in Reinforcement Learning","date":"2021-03-23","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-6dof-grasping-using-reward","title":"Learning 6DoF Grasping Using Reward-Consistent Demonstration","date":"2021-03-23","arxiv_id":"2103.12321","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-adaptable-policy-via-meta","title":"Meta-Adversarial Inverse Reinforcement Learning for Decision-making Tasks","date":"2021-03-23","arxiv_id":"2103.12694","repositories_listed":0,"syntology":null},{"url":null,"slug":"unsupervised-contextual-paraphrase-generation","title":"Unsupervised Contextual Paraphrase Generation using Lexical Control and Reinforcement Learning","date":"2021-03-23","arxiv_id":"2103.12777","repositories_listed":0,"syntology":null},{"url":null,"slug":"bridging-offline-reinforcement-learning-and","title":"Bridging Offline Reinforcement Learning and Imitation Learning: A Tale of Pessimism","date":"2021-03-22","arxiv_id":"2103.12021","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-the-generalization-performance-and","title":"IPAPRec: A promising tool for learning high-performance mapless navigation skills with deep reinforcement learning","date":"2021-03-22","arxiv_id":"2103.11686","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-actor-critic-reinforcement-learning","title":"Improving Actor-Critic Reinforcement Learning via Hamiltonian Monte Carlo Method","date":"2021-03-22","arxiv_id":"2103.12020","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-based-on-mpc-mhe-for","title":"Reinforcement Learning based on MPC/MHE for Unmodeled and Partially Observable Dynamics","date":"2021-03-22","arxiv_id":"2103.11871","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-based-on-scenario-tree","title":"Reinforcement Learning based on Scenario-tree MPC for ASVs","date":"2021-03-22","arxiv_id":"2103.11949","repositories_listed":0,"syntology":null},{"url":null,"slug":"smart-scheduling-based-on-deep-reinforcement","title":"Smart Scheduling based on Deep Reinforcement Learning for Cellular Networks","date":"2021-03-22","arxiv_id":"2103.11542","repositories_listed":0,"syntology":null},{"url":null,"slug":"softmax-with-regularization-better-value","title":"Regularized Softmax Deep Multi-Agent $Q$-Learning","date":"2021-03-22","arxiv_id":"2103.11883","repositories_listed":0,"syntology":null},{"url":null,"slug":"variational-quantum-compiling-with-double-q","title":"Variational quantum compiling with double Q-learning","date":"2021-03-22","arxiv_id":"2103.11611","repositories_listed":0,"syntology":null}],"record_sha256":"7832f41d5e5eeffbd07d9cc33ef262e413fa62702aab274a7f020de5ea8222b5","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}