{"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/99","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":99,"pages_in_order":132,"rows_per_page":100,"rows":[9801,9900],"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/98","next":"/task/reinforcement-learning/papers/100","papers":[{"url":null,"slug":"graph-ordering-towards-the-optimal-by","title":"Graph Ordering: Towards the Optimal by Learning","date":"2020-01-18","arxiv_id":"2001.06631","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-agent-motion-planning-for-dense-and","title":"Multi-agent Motion Planning for Dense and Dynamic Environments via Deep Reinforcement Learning","date":"2020-01-18","arxiv_id":"2001.06627","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-derivative-free-method-for-solving-elliptic","title":"A Derivative-Free Method for Solving Elliptic Partial Differential Equations with Deep Neural Networks","date":"2020-01-17","arxiv_id":"2001.06145","repositories_listed":0,"syntology":null},{"url":null,"slug":"algorithms-in-multi-agent-systems-a-holistic","title":"Algorithms in Multi-Agent Systems: A Holistic Perspective from Reinforcement Learning and Game Theory","date":"2020-01-17","arxiv_id":"2001.06487","repositories_listed":0,"syntology":null},{"url":null,"slug":"mime-mutual-information-minimisation","title":"MIME: Mutual Information Minimisation Exploration","date":"2020-01-16","arxiv_id":"2001.05636","repositories_listed":0,"syntology":null},{"url":null,"slug":"reward-shaping-for-reinforcement-learning","title":"Reward Shaping for Reinforcement Learning with Omega-Regular Objectives","date":"2020-01-16","arxiv_id":"2001.05977","repositories_listed":0,"syntology":null},{"url":null,"slug":"avgout-a-simple-output-probability-measure-to","title":"AvgOut: A Simple Output-Probability Measure to Eliminate Dull Responses","date":"2020-01-15","arxiv_id":"2001.05467","repositories_listed":0,"syntology":null},{"url":null,"slug":"inducing-cooperation-in-multi-agent-games","title":"Inducing Cooperative behaviour in Sequential-Social dilemmas through Multi-Agent Reinforcement Learning using Status-Quo Loss","date":"2020-01-15","arxiv_id":"2001.05458","repositories_listed":0,"syntology":null},{"url":null,"slug":"model-based-multi-agent-reinforcement","title":"Model-based Multi-Agent Reinforcement Learning with Cooperative Prioritized Sweeping","date":"2020-01-15","arxiv_id":"2001.07527","repositories_listed":0,"syntology":null},{"url":null,"slug":"robotic-grasp-manipulation-using-evolutionary","title":"Robotic Grasp Manipulation Using Evolutionary Computing and Deep Reinforcement Learning","date":"2020-01-15","arxiv_id":"2001.05443","repositories_listed":0,"syntology":null},{"url":null,"slug":"seerl-sample-efficient-ensemble-reinforcement-1","title":"SEERL: Sample Efficient Ensemble Reinforcement Learning","date":"2020-01-15","arxiv_id":"2001.05209","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-of-control-policy-for","title":"Reinforcement Learning of Control Policy for Linear Temporal Logic Specifications Using Limit-Deterministic Generalized Büchi Automata","date":"2020-01-14","arxiv_id":"2001.04669","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploiting-language-instructions-for","title":"Exploiting Language Instructions for Interpretable and Compositional Reinforcement Learning","date":"2020-01-13","arxiv_id":"2001.04418","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-to-locomote-with-deep-neural-network","title":"Learning to Locomote with Deep Neural-Network and CPG-based Control in a Soft Snake Robot","date":"2020-01-13","arxiv_id":"2001.04059","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-robot-formation-control-using","title":"Multi-Robot Formation Control Using Reinforcement Learning","date":"2020-01-13","arxiv_id":"2001.04527","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-reinforcement-learning-for-complex-1","title":"Deep Reinforcement Learning for Complex Manipulation Tasks with Sparse Feedback","date":"2020-01-12","arxiv_id":"2001.03877","repositories_listed":0,"syntology":null},{"url":null,"slug":"functional-error-correction-for-robust-neural","title":"Functional Error Correction for Robust Neural Networks","date":"2020-01-12","arxiv_id":"2001.03814","repositories_listed":0,"syntology":null},{"url":null,"slug":"weakly-supervised-video-summarization-by","title":"Weakly Supervised Video Summarization by Hierarchical Reinforcement Learning","date":"2020-01-12","arxiv_id":"2001.05864","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-sequential-resource-investment-planning","title":"A storage expansion planning framework using reinforcement learning and simulation-based optimization","date":"2020-01-10","arxiv_id":"2001.03507","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-interactive-reinforcement-learning-for","title":"Deep Interactive Reinforcement Learning for Path Following of Autonomous Underwater Vehicle","date":"2020-01-10","arxiv_id":"2001.03359","repositories_listed":0,"syntology":null},{"url":null,"slug":"debate-dynamics-for-human-comprehensible-fact","title":"Debate Dynamics for Human-comprehensible Fact-checking on Knowledge Graphs","date":"2020-01-09","arxiv_id":"2001.03436","repositories_listed":0,"syntology":null},{"url":null,"slug":"identifying-distinct-effective-treatments-for","title":"Identifying Distinct, Effective Treatments for Acute Hypotension with SODA-RL: Safely Optimized Diverse Accurate Reinforcement Learning","date":"2020-01-09","arxiv_id":"2001.03224","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-computation-and-generalization-of-1","title":"On Computation and Generalization of Generative Adversarial Imitation Learning","date":"2020-01-09","arxiv_id":"2001.02792","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-tracking-control-for","title":"Reinforcement Learning Tracking Control for Robotic Manipulator With Kernel-Based Dynamic Model","date":"2020-01-09","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"eeg-based-drowsiness-estimation-for-driving","title":"EEG-based Drowsiness Estimation for Driving Safety using Deep Q-Learning","date":"2020-01-08","arxiv_id":"2001.02399","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-agent-deep-reinforcement-learning-for-4","title":"Multi-Agent Deep Reinforcement Learning for Cooperative Connected Vehicles","date":"2020-01-08","arxiv_id":"2001.02337","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-thompson-sampling-for-smoother-than","title":"On Thompson Sampling for Smoother-than-Lipschitz Bandits","date":"2020-01-08","arxiv_id":"2001.02323","repositories_listed":0,"syntology":null},{"url":null,"slug":"perception-and-decision-making-of-autonomous","title":"Perception and Navigation in Autonomous Systems in the Era of Learning: A Survey","date":"2020-01-08","arxiv_id":"2001.02319","repositories_listed":0,"syntology":null},{"url":null,"slug":"sample-based-distributional-policy-gradient","title":"Sample-based Distributional Policy Gradient","date":"2020-01-08","arxiv_id":"2001.02652","repositories_listed":0,"syntology":null},{"url":null,"slug":"what-can-robotics-research-learn-from","title":"What can robotics research learn from computer vision research?","date":"2020-01-08","arxiv_id":"2001.02366","repositories_listed":0,"syntology":null},{"url":null,"slug":"reanalysis-of-variance-reduced-temporal-1","title":"Reanalysis of Variance Reduced Temporal Difference Learning","date":"2020-01-07","arxiv_id":"2001.01898","repositories_listed":0,"syntology":null},{"url":null,"slug":"experimental-analysis-of-reinforcement","title":"Experimental Analysis of Reinforcement Learning Techniques for Spectrum Sharing Radar","date":"2020-01-06","arxiv_id":"2001.01799","repositories_listed":0,"syntology":null},{"url":null,"slug":"high-speed-autonomous-drifting-with-deep","title":"High-speed Autonomous Drifting with Deep Reinforcement Learning","date":"2020-01-06","arxiv_id":"2001.01377","repositories_listed":0,"syntology":null},{"url":null,"slug":"incentivizing-the-emergence-of-grounded","title":"Generalizing Emergent Communication","date":"2020-01-06","arxiv_id":"2001.01772","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-reusable-options-for-multi-task-1","title":"Learning Reusable Options for Multi-Task Reinforcement Learning","date":"2020-01-06","arxiv_id":"2001.01577","repositories_listed":0,"syntology":null},{"url":null,"slug":"optimal-options-for-multi-task-reinforcement","title":"Optimal Options for Multi-Task Reinforcement Learning Under Time Constraints","date":"2020-01-06","arxiv_id":"2001.01620","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-fine-grained-search-space-pruning","title":"Learning fine-grained search space pruning and heuristics for combinatorial optimization","date":"2020-01-05","arxiv_id":"2001.01230","repositories_listed":0,"syntology":null},{"url":null,"slug":"universal-successor-features-for-transfer-1","title":"Universal Successor Features for Transfer Reinforcement Learning","date":"2020-01-05","arxiv_id":"2001.04025","repositories_listed":0,"syntology":null},{"url":null,"slug":"hierarchical-reinforcement-learning-as-a","title":"Hierarchical Reinforcement Learning as a Model of Human Task Interleaving","date":"2020-01-04","arxiv_id":"2001.02122","repositories_listed":0,"syntology":null},{"url":null,"slug":"intelligent-roundabout-insertion-using-deep","title":"Intelligent Roundabout Insertion using Deep Reinforcement Learning","date":"2020-01-03","arxiv_id":"2001.00786","repositories_listed":0,"syntology":null},{"url":"/paper/making-sense-of-reinforcement-learning-and-1","slug":"making-sense-of-reinforcement-learning-and-1","title":"Making Sense of Reinforcement Learning and Probabilistic Inference","date":"2020-01-03","arxiv_id":"2001.00805","repositories_listed":0,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/making-sense-of-reinforcement-learning-and-1#ran","syntology_url":"https://syntology.ai/paper/2001.00805","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2001.00805"}},"official":null}},{"url":null,"slug":"optimizing-wireless-systems-using","title":"Optimizing Wireless Systems Using Unsupervised and Reinforced-Unsupervised Deep Learning","date":"2020-01-03","arxiv_id":"2001.00784","repositories_listed":0,"syntology":null},{"url":null,"slug":"continuous-discrete-reinforcement-learning","title":"Continuous-Discrete Reinforcement Learning for Hybrid Control in Robotics","date":"2020-01-02","arxiv_id":"2001.00449","repositories_listed":0,"syntology":null},{"url":null,"slug":"joint-goal-and-strategy-inference-across","title":"Joint Goal and Strategy Inference across Heterogeneous Demonstrators via Reward Network Distillation","date":"2020-01-02","arxiv_id":"2001.00503","repositories_listed":0,"syntology":null},{"url":null,"slug":"zero-shot-reinforcement-learning-with-deep","title":"Zero-Shot Reinforcement Learning with Deep Attention Convolutional Neural Networks","date":"2020-01-02","arxiv_id":"2001.00605","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-game-theoretic-perspective-on-model-based","title":"A Game Theoretic Perspective on Model-Based Reinforcement Learning","date":"2020-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"batch-reinforcement-learning-with","title":"Batch Reinforcement Learning with Hyperparameter Gradients","date":"2020-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-randomized-least-squares-value-iteration","title":"Deep Randomized Least Squares Value Iteration","date":"2020-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-reinforcement-learning-with-implicit","title":"Deep Reinforcement Learning with Implicit Human Feedback","date":"2020-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-reinforcement-learning-with-smooth-1","title":"Deep Reinforcement Learning with Smooth Policy","date":"2020-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"designing-optimal-dynamic-treatment-regimes-a","title":"Designing Optimal Dynamic Treatment Regimes: A Causal Reinforcement Learning Approach","date":"2020-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"discovering-motor-programs-by-recomposing","title":"Discovering Motor Programs by Recomposing Demonstrations","date":"2020-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"double-reinforcement-learning-for-efficient-1","title":"Double Reinforcement Learning for Efficient and Robust Off-Policy Evaluation","date":"2020-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-language-emergence-through-empathy","title":"Enhancing Language Emergence through Empathy","date":"2020-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-the-generalization-of-visual","title":"Improving the Generalization of Visual Navigation Policies using Invariance Regularization","date":"2020-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"insights-on-visual-representations-for","title":"Insights on Visual Representations for Embodied Navigation Tasks","date":"2020-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-general-purpose-controllers-via","title":"Learning General-Purpose Controllers via Locally Communicating Sensorimotor Modules","date":"2020-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-representations-in-reinforcement-1","title":"Learning Representations in Reinforcement Learning: an Information Bottleneck Approach","date":"2020-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"on-bonus-based-exploration-methods-in-the","title":"On Bonus Based Exploration Methods In The Arcade Learning Environment","date":"2020-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"optimizing-multiagent-cooperation-via-policy","title":"Optimizing Multiagent Cooperation via Policy Evolution and Shared Experiences","date":"2020-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-with-differential","title":"Reinforcement Learning with Differential Privacy","date":"2020-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-with-goal-distance","title":"Reinforcement Learning with Goal-Distance Gradient","date":"2020-01-01","arxiv_id":"2001.00127","repositories_listed":0,"syntology":null},{"url":null,"slug":"responsive-safety-in-reinforcement-learning-1","title":"Responsive Safety in Reinforcement Learning","date":"2020-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"svqn-sequential-variational-soft-q-learning","title":"SVQN: Sequential Variational Soft Q-Learning Networks","date":"2020-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"way-off-policy-batch-deep-reinforcement-1","title":"Way Off-Policy Batch Deep Reinforcement Learning of Human Preferences in Dialog","date":"2020-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"information-theoretic-model-predictive-q-1","title":"Information Theoretic Model Predictive Q-Learning","date":"2019-12-31","arxiv_id":"2001.02153","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-the-role-of-weight-sharing-during-deep","title":"On the Role of Weight Sharing During Deep Option Learning","date":"2019-12-31","arxiv_id":"1912.13408","repositories_listed":0,"syntology":null},{"url":null,"slug":"stochastic-recursive-variance-reduction-for","title":"Stochastic Recursive Variance Reduction for Efficient Smooth Non-Convex Compositional Optimization","date":"2019-12-31","arxiv_id":"1912.13515","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-gamblers-problem-and-beyond-1","title":"The Gambler's Problem and Beyond","date":"2019-12-31","arxiv_id":"2001.00102","repositories_listed":0,"syntology":null},{"url":null,"slug":"uncertainty-based-out-of-distribution-1","title":"Uncertainty-Based Out-of-Distribution Classification in Deep Reinforcement Learning","date":"2019-12-31","arxiv_id":"2001.00496","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-new-framework-for-query-efficient-active","title":"A New Framework for Query Efficient Active Imitation Learning","date":"2019-12-30","arxiv_id":"1912.13037","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-reinforced-self-attention-masks-for","title":"Deep Reinforced Self-Attention Masks for Abstractive Summarization (DR.SAS)","date":"2019-12-30","arxiv_id":"2001.00009","repositories_listed":0,"syntology":null},{"url":null,"slug":"world-programs-for-model-based-learning-and","title":"World Programs for Model-Based Learning and Planning in Compositional State and Action Spaces","date":"2019-12-30","arxiv_id":"1912.13007","repositories_listed":0,"syntology":null},{"url":null,"slug":"augmented-replay-memory-in-reinforcement","title":"Augmented Replay Memory in Reinforcement Learning With Continuous Control","date":"2019-12-29","arxiv_id":"1912.12719","repositories_listed":0,"syntology":null},{"url":null,"slug":"computational-model-discovery-with","title":"Computational model discovery with reinforcement learning","date":"2019-12-29","arxiv_id":"2001.00008","repositories_listed":0,"syntology":null},{"url":null,"slug":"individual-specialization-in-multi-task","title":"Individual specialization in multi-task environments with multiagent reinforcement learners","date":"2019-12-29","arxiv_id":"1912.12671","repositories_listed":0,"syntology":null},{"url":null,"slug":"loss-aversion-fosters-coordination-among","title":"Loss aversion fosters coordination among independent reinforcement learners","date":"2019-12-29","arxiv_id":"1912.12633","repositories_listed":0,"syntology":null},{"url":null,"slug":"real-time-policy-distillation-in-deep","title":"Real-time Policy Distillation in Deep Reinforcement Learning","date":"2019-12-29","arxiv_id":"1912.12630","repositories_listed":0,"syntology":null},{"url":null,"slug":"speeding-up-reinforcement-learning-by","title":"Speeding up reinforcement learning by combining attention and agency features","date":"2019-12-29","arxiv_id":"1912.12623","repositories_listed":0,"syntology":null},{"url":null,"slug":"crowdfunding-dynamics-tracking-a","title":"Crowdfunding Dynamics Tracking: A Reinforcement Learning Approach","date":"2019-12-27","arxiv_id":"1912.12016","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-reinforcement-learning-for-complex","title":"Deep reinforcement learning for complex evaluation of one-loop diagrams in quantum field theory","date":"2019-12-27","arxiv_id":"1912.12322","repositories_listed":0,"syntology":null},{"url":null,"slug":"evolution-strategies-converges-to-finite","title":"Evolution Strategies Converges to Finite Differences","date":"2019-12-27","arxiv_id":"2001.01684","repositories_listed":0,"syntology":null},{"url":null,"slug":"quantum-logic-gate-synthesis-as-a-markov","title":"Quantum Logic Gate Synthesis as a Markov Decision Process","date":"2019-12-27","arxiv_id":"1912.12002","repositories_listed":0,"syntology":null},{"url":null,"slug":"convergence-and-sample-complexity-of-gradient","title":"Convergence and sample complexity of gradient methods for the model-free linear quadratic regulator problem","date":"2019-12-26","arxiv_id":"1912.11899","repositories_listed":0,"syntology":null},{"url":null,"slug":"quasi-newton-trust-region-policy-optimization","title":"Quasi-Newton Trust Region Policy Optimization","date":"2019-12-26","arxiv_id":"1912.11912","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-to-combat-compounding-error-in-model-1","title":"Learning to Combat Compounding-Error in Model-Based Reinforcement Learning","date":"2019-12-24","arxiv_id":"1912.11206","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-survey-of-deep-reinforcement-learning-in","title":"A Survey of Deep Reinforcement Learning in Video Games","date":"2019-12-23","arxiv_id":"1912.10944","repositories_listed":0,"syntology":null},{"url":null,"slug":"direct-and-indirect-reinforcement-learning","title":"Direct and indirect reinforcement learning","date":"2019-12-23","arxiv_id":"1912.10600","repositories_listed":0,"syntology":null},{"url":null,"slug":"finite-time-analysis-and-restarting-scheme","title":"Finite-Time Analysis and Restarting Scheme for Linear Two-Time-Scale Stochastic Approximation","date":"2019-12-23","arxiv_id":"1912.10583","repositories_listed":0,"syntology":null},{"url":null,"slug":"hamilton-jacobi-bellman-equations-for-q","title":"Hamilton-Jacobi-Bellman Equations for Q-Learning in Continuous Time","date":"2019-12-23","arxiv_id":"1912.10697","repositories_listed":0,"syntology":null},{"url":null,"slug":"monte-carlo-tree-search-for-policy","title":"Monte-Carlo Tree Search for Policy Optimization","date":"2019-12-23","arxiv_id":"1912.10648","repositories_listed":0,"syntology":null},{"url":null,"slug":"energy-aware-multi-server-mobile-edge","title":"Energy-Aware Multi-Server Mobile Edge Computing: A Deep Reinforcement Learning Approach","date":"2019-12-22","arxiv_id":"1912.10485","repositories_listed":0,"syntology":null},{"url":null,"slug":"online-reinforcement-learning-of-optimal","title":"Online Reinforcement Learning of Optimal Threshold Policies for Markov Decision Processes","date":"2019-12-21","arxiv_id":"1912.10325","repositories_listed":0,"syntology":null},{"url":null,"slug":"predictive-coding-for-boosting-deep-1","title":"Predictive Coding for Boosting Deep Reinforcement Learning with Sparse Rewards","date":"2019-12-21","arxiv_id":"1912.13414","repositories_listed":0,"syntology":null},{"url":null,"slug":"dependable-neural-networks-for-safety","title":"Dependable Neural Networks for Safety Critical Tasks","date":"2019-12-20","arxiv_id":"1912.09902","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploiting-the-potential-of-deep","title":"Exploiting the potential of deep reinforcement learning for classification tasks in high-dimensional and unstructured data","date":"2019-12-20","arxiv_id":"1912.09595","repositories_listed":0,"syntology":null},{"url":null,"slug":"mastering-complex-control-in-moba-games-with","title":"Mastering Complex Control in MOBA Games with Deep Reinforcement Learning","date":"2019-12-20","arxiv_id":"1912.09729","repositories_listed":0,"syntology":null},{"url":null,"slug":"optimizing-collision-avoidance-in-dense","title":"Optimizing Collision Avoidance in Dense Airspace using Deep Reinforcement Learning","date":"2019-12-20","arxiv_id":"1912.10146","repositories_listed":0,"syntology":null},{"url":null,"slug":"teaching-robots-to-perceive-time-a","title":"Teaching robots to perceive time -- A reinforcement learning approach (Extended version)","date":"2019-12-20","arxiv_id":"1912.10113","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-reinforcement-learning-designed-rf-pulse","title":"Deep Reinforcement Learning Designed Shinnar-Le Roux RF Pulse using Root-Flipping: DeepRF_SLR","date":"2019-12-19","arxiv_id":"1912.09015","repositories_listed":0,"syntology":null}],"record_sha256":"d86f0fa5e2806861414f813dea8271faacff8f14e6e1db4f4dfff0a1f55b3232","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}