{"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/121","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":121,"pages_in_order":152,"rows_per_page":100,"rows":[12001,12100],"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/120","next":"/task/reinforcement-learning-1/papers/122","papers":[{"url":null,"slug":"variational-model-based-policy-optimization","title":"Variational Model-based Policy Optimization","date":"2020-06-09","arxiv_id":"2006.05443","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-comparison-of-self-play-algorithms-under-a","title":"A Comparison of Self-Play Algorithms Under a Generalized Framework","date":"2020-06-08","arxiv_id":"2006.04471","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-decentralized-policy-gradient-approach-to","title":"A Decentralized Policy Gradient Approach to Multi-task Reinforcement Learning","date":"2020-06-08","arxiv_id":"2006.04338","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-model-free-learning-algorithm-for-infinite","title":"A Model-free Learning Algorithm for Infinite-horizon Average-reward MDPs with Near-optimal Regret","date":"2020-06-08","arxiv_id":"2006.04354","repositories_listed":0,"syntology":null},{"url":null,"slug":"balancing-a-cartpole-system-with","title":"Balancing a CartPole System with Reinforcement Learning -- A Tutorial","date":"2020-06-08","arxiv_id":"2006.04938","repositories_listed":0,"syntology":null},{"url":null,"slug":"constrained-upper-confidence-reinforcement-1","title":"Constrained Upper Confidence Reinforcement Learning with Known Dynamics","date":"2020-06-08","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"hallucinating-value-a-pitfall-of-dyna-style","title":"Hallucinating Value: A Pitfall of Dyna-style Planning with Imperfect Environment Models","date":"2020-06-08","arxiv_id":"2006.04363","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-the-model-free-linear-quadratic","title":"Learning the model-free linear quadratic regulator via random search","date":"2020-06-08","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-to-plan-via-deep-optimistic-value","title":"Learning to Plan via Deep Optimistic Value Exploration","date":"2020-06-08","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"maximum-entropy-model-rollouts-fast-model","title":"Maximum Entropy Model Rollouts: Fast Model Based Policy Optimization without Compounding Errors","date":"2020-06-08","arxiv_id":"2006.04802","repositories_listed":0,"syntology":null},{"url":null,"slug":"online-data-poisoning-attacks","title":"Online Data Poisoning Attacks","date":"2020-06-08","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"policy-optimization-for-mathcal-h-2-linear","title":"Policy Optimization for $\\mathcal{H}_{2}$ Linear Control with $\\mathcal{H}_{\\infty}$ Robustness Guarantee: Implicit Regularization and Global Convergence","date":"2020-06-08","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"randomized-policy-learning-for-continuous","title":"Randomized Policy Learning for Continuous State and Action MDPs","date":"2020-06-08","arxiv_id":"2006.04331","repositories_listed":0,"syntology":null},{"url":null,"slug":"scalable-reinforcement-learning-of-localized-1","title":"Scalable Reinforcement Learning of Localized Policies for Multi-Agent Networked Systems","date":"2020-06-08","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"stable-reinforcement-learning-with-unbounded","title":"Stable Reinforcement Learning with Unbounded State Space","date":"2020-06-08","arxiv_id":"2006.04353","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-poverty-mapping-using-deep","title":"Efficient Poverty Mapping using Deep Reinforcement Learning","date":"2020-06-07","arxiv_id":"2006.04224","repositories_listed":0,"syntology":null},{"url":null,"slug":"implications-of-human-irrationality-for","title":"Implications of Human Irrationality for Reinforcement Learning","date":"2020-06-07","arxiv_id":"2006.04072","repositories_listed":0,"syntology":null},{"url":null,"slug":"incorporating-pragmatic-reasoning","title":"Incorporating Pragmatic Reasoning Communication into Emergent Language","date":"2020-06-07","arxiv_id":"2006.04109","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-task-reinforcement-learning-based","title":"Multi-Task Reinforcement Learning based Mobile Manipulation Control for Dynamic Object Tracking and Grasping","date":"2020-06-07","arxiv_id":"2006.04271","repositories_listed":0,"syntology":null},{"url":null,"slug":"real-time-model-calibration-with-deep","title":"Real-Time Model Calibration with Deep Reinforcement Learning","date":"2020-06-07","arxiv_id":"2006.04001","repositories_listed":0,"syntology":null},{"url":null,"slug":"skill-discovery-of-coordination-in-multi","title":"Skill Discovery of Coordination in Multi-agent Reinforcement Learning","date":"2020-06-07","arxiv_id":"2006.04021","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-evaluation-of-natural-stochastic","title":"Efficient Evaluation of Natural Stochastic Policies in Offline Reinforcement Learning","date":"2020-06-06","arxiv_id":"2006.03886","repositories_listed":0,"syntology":null},{"url":null,"slug":"model-free-reinforcement-learning-from","title":"Model-Free Reinforcement Learning: from Clipped Pseudo-Regret to Sample Complexity","date":"2020-06-06","arxiv_id":"2006.03864","repositories_listed":0,"syntology":null},{"url":null,"slug":"stable-and-efficient-policy-evaluation","title":"Stable and Efficient Policy Evaluation","date":"2020-06-06","arxiv_id":"2006.03978","repositories_listed":0,"syntology":null},{"url":null,"slug":"autohas-differentiable-hyper-parameter-and","title":"AutoHAS: Efficient Hyperparameter and Architecture Search","date":"2020-06-05","arxiv_id":"2006.03656","repositories_listed":0,"syntology":null},{"url":null,"slug":"balancing-reinforcement-learning-training","title":"Balancing Reinforcement Learning Training Experiences in Interactive Information Retrieval","date":"2020-06-05","arxiv_id":"2006.03185","repositories_listed":0,"syntology":null},{"url":null,"slug":"state-action-separable-reinforcement-learning","title":"State Action Separable Reinforcement Learning","date":"2020-06-05","arxiv_id":"2006.03713","repositories_listed":0,"syntology":null},{"url":null,"slug":"constrained-reinforcement-learning-for","title":"Constrained Reinforcement Learning for Dynamic Optimization under Uncertainty","date":"2020-06-04","arxiv_id":"2006.02750","repositories_listed":0,"syntology":null},{"url":null,"slug":"meta-model-based-meta-policy-optimization","title":"Meta-Model-Based Meta-Policy Optimization","date":"2020-06-04","arxiv_id":"2006.02608","repositories_listed":0,"syntology":null},{"url":null,"slug":"refined-continuous-control-of-ddpg-actors-via","title":"Refined Continuous Control of DDPG Actors via Parametrised Activation","date":"2020-06-04","arxiv_id":"2006.02818","repositories_listed":0,"syntology":null},{"url":null,"slug":"causality-and-batch-reinforcement-learning","title":"Causality and Batch Reinforcement Learning: Complementary Approaches To Planning In Unknown Domains","date":"2020-06-03","arxiv_id":"2006.02579","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-to-scan-a-deep-reinforcement","title":"Learning to Scan: A Deep Reinforcement Learning Approach for Personalized Scanning in CT Imaging","date":"2020-06-03","arxiv_id":"2006.02420","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-value-improvement-path-towards-better","title":"The Value-Improvement Path: Towards Better Representations for Reinforcement Learning","date":"2020-06-03","arxiv_id":"2006.02243","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-novel-approach-for-multi-agent-cooperative","title":"A novel approach for multi-agent cooperative pursuit to capture grouped evaders","date":"2020-06-01","arxiv_id":"2006.01022","repositories_listed":0,"syntology":null},{"url":null,"slug":"active-vision-for-early-recognition-of-human","title":"Active Vision for Early Recognition of Human Actions","date":"2020-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"mitigating-bias-in-face-recognition-using","title":"Mitigating Bias in Face Recognition Using Skewness-Aware Reinforcement Learning","date":"2020-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"model-based-reinforcement-learning-with-value","title":"Model-Based Reinforcement Learning with Value-Targeted Regression","date":"2020-06-01","arxiv_id":"2006.01107","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-and-bayesian-data","title":"Reinforcement learning and Bayesian data assimilation for model-informed precision dosing in oncology","date":"2020-06-01","arxiv_id":"2006.01061","repositories_listed":0,"syntology":null},{"url":null,"slug":"robust-reinforcement-learning-with-1","title":"Robust Reinforcement Learning with Wasserstein Constraint","date":"2020-06-01","arxiv_id":"2006.00945","repositories_listed":0,"syntology":null},{"url":null,"slug":"temporal-differential-learning-in-continuous","title":"Temporal-Differential Learning in Continuous Environments","date":"2020-06-01","arxiv_id":"2006.00997","repositories_listed":0,"syntology":null},{"url":null,"slug":"variational-reward-estimator-bottleneck","title":"Variational Reward Estimator Bottleneck: Learning Robust Reward Estimator for Multi-Domain Task-Oriented Dialog","date":"2020-05-31","arxiv_id":"2006.00417","repositories_listed":0,"syntology":null},{"url":null,"slug":"ai-based-resource-allocation-reinforcement","title":"AI-based Resource Allocation: Reinforcement Learning for Adaptive Auto-scaling in Serverless Environments","date":"2020-05-29","arxiv_id":"2005.14410","repositories_listed":0,"syntology":null},{"url":null,"slug":"domain-knowledge-integration-by-gradient","title":"Domain Knowledge Integration By Gradient Matching For Sample-Efficient Reinforcement Learning","date":"2020-05-28","arxiv_id":"2005.13778","repositories_listed":0,"syntology":null},{"url":null,"slug":"intelligent-residential-energy-management","title":"Intelligent Residential Energy Management System using Deep Reinforcement Learning","date":"2020-05-28","arxiv_id":"2005.14259","repositories_listed":0,"syntology":null},{"url":null,"slug":"active-measure-reinforcement-learning-for","title":"Active Measure Reinforcement Learning for Observation Cost Minimization","date":"2020-05-26","arxiv_id":"2005.12697","repositories_listed":0,"syntology":null},{"url":null,"slug":"anomaly-detection-under-controlled-sensing","title":"Anomaly Detection Under Controlled Sensing Using Actor-Critic Reinforcement Learning","date":"2020-05-26","arxiv_id":"2006.01044","repositories_listed":0,"syntology":null},{"url":null,"slug":"breaking-the-sample-size-barrier-in-model","title":"Breaking the Sample Size Barrier in Model-Based Reinforcement Learning with a Generative Model","date":"2020-05-26","arxiv_id":"2005.12900","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-use-of-heuristics-for-accelerating","title":"Efficient Use of heuristics for accelerating XCS-based Policy Learning in Markov Games","date":"2020-05-26","arxiv_id":"2005.12553","repositories_listed":0,"syntology":null},{"url":null,"slug":"integrating-leo-satellite-and-uav-relaying","title":"Integrating LEO Satellite and UAV Relaying via Reinforcement Learning for Non-Terrestrial Networks","date":"2020-05-26","arxiv_id":"2005.12521","repositories_listed":0,"syntology":null},{"url":null,"slug":"time-variant-variational-transfer-for-value","title":"Time-Variant Variational Transfer for Value Functions","date":"2020-05-26","arxiv_id":"2005.12864","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-intervention-centric-causal-reasoning","title":"Towards intervention-centric causal reasoning in learning agents","date":"2020-05-26","arxiv_id":"2005.12968","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-learning-models-for-automatic","title":"Deep Learning Models for Automatic Summarization","date":"2020-05-25","arxiv_id":"2005.11988","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-reinforcement-learning-based-power-1","title":"Deep Reinforcement Learning Based Power Allocation for D2D Network","date":"2020-05-25","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"dynamic-value-estimation-for-single-task","title":"Dynamic Value Estimation for Single-Task Multi-Scene Reinforcement Learning","date":"2020-05-25","arxiv_id":"2005.12254","repositories_listed":0,"syntology":null},{"url":null,"slug":"generator-and-critic-a-deep-reinforcement","title":"Generator and Critic: A Deep Reinforcement Learning Approach for Slate Re-ranking in E-commerce","date":"2020-05-25","arxiv_id":"2005.12206","repositories_listed":0,"syntology":null},{"url":null,"slug":"gradient-monitored-reinforcement-learning","title":"Gradient Monitored Reinforcement Learning","date":"2020-05-25","arxiv_id":"2005.12108","repositories_listed":0,"syntology":null},{"url":null,"slug":"meta-reinforcement-learning-for-trajectory","title":"Meta-Reinforcement Learning for Trajectory Design in Wireless UAV Networks","date":"2020-05-25","arxiv_id":"2005.12394","repositories_listed":0,"syntology":null},{"url":null,"slug":"optimization-driven-deep-reinforcement","title":"Optimization-driven Deep Reinforcement Learning for Robust Beamforming in IRS-assisted Wireless Communications","date":"2020-05-25","arxiv_id":"2005.11885","repositories_listed":0,"syntology":null},{"url":null,"slug":"policy-entropy-for-out-of-distribution","title":"Policy Entropy for Out-of-Distribution Classification","date":"2020-05-25","arxiv_id":"2005.12069","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-with-iterative","title":"Reinforcement Learning with Iterative Reasoning for Merging in Dense Traffic","date":"2020-05-25","arxiv_id":"2005.11895","repositories_listed":0,"syntology":null},{"url":null,"slug":"gochat-goal-oriented-chatbots-with","title":"GoChat: Goal-oriented Chatbots with Hierarchical Reinforcement Learning","date":"2020-05-24","arxiv_id":"2005.11729","repositories_listed":0,"syntology":null},{"url":null,"slug":"model-free-reinforcement-learning-for-1","title":"Model-free Reinforcement Learning for Stochastic Stackelberg Security Games","date":"2020-05-24","arxiv_id":"2005.11853","repositories_listed":0,"syntology":null},{"url":null,"slug":"adaptive-reinforcement-learning-through","title":"Adaptive Reinforcement Learning through Evolving Self-Modifying Neural Networks","date":"2020-05-22","arxiv_id":"2006.05832","repositories_listed":0,"syntology":null},{"url":null,"slug":"evaluating-generalisation-in-general-video","title":"Evaluating Generalisation in General Video Game Playing","date":"2020-05-22","arxiv_id":"2005.11247","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-with-human-advice-a","title":"Reinforcement learning with human advice: a survey","date":"2020-05-22","arxiv_id":"2005.11016","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-automated-safety-coverage-and-testing","title":"Towards Automated Safety Coverage and Testing for Autonomous Vehicles with Reinforcement Learning","date":"2020-05-22","arxiv_id":"2005.13976","repositories_listed":0,"syntology":null},{"url":null,"slug":"provably-efficient-reinforcement-learning-2","title":"Reinforcement Learning with General Value Function Approximation: Provably Efficient Approach via Bounded Eluder Dimension","date":"2020-05-21","arxiv_id":"2005.10804","repositories_listed":0,"syntology":null},{"url":null,"slug":"q-nav-nav-setting-method-based-on","title":"Q-NAV: NAV Setting Method based on Reinforcement Learning in Underwater Wireless Networks","date":"2020-05-21","arxiv_id":"2005.13521","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-reinforcement-learning-based-decision","title":"A reinforcement learning based decision support system in textile manufacturing process","date":"2020-05-20","arxiv_id":"2005.09867","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-reinforcement-learning-for-high-level","title":"Deep Reinforcement Learning for High Level Character Control","date":"2020-05-20","arxiv_id":"2005.10391","repositories_listed":0,"syntology":null},{"url":null,"slug":"finite-sample-analysis-of-greedy-gq-with","title":"Finite-sample Analysis of Greedy-GQ with Linear Function Approximation under Markovian Noise","date":"2020-05-20","arxiv_id":"2005.10175","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-and-reasoning-for-robot-dialog-and","title":"Learning and Reasoning for Robot Dialog and Navigation Tasks","date":"2020-05-20","arxiv_id":"2005.09833","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-for-variable-selection","title":"Reinforcement Learning for Variable Selection in a Branch and Bound Algorithm","date":"2020-05-20","arxiv_id":"2005.10026","repositories_listed":0,"syntology":null},{"url":null,"slug":"two-stage-deep-reinforcement-learning-for","title":"Two-stage Deep Reinforcement Learning for Inverter-based Volt-VAR Control in Active Distribution Networks","date":"2020-05-20","arxiv_id":"2005.11142","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-survey-of-reinforcement-learning-algorithms","title":"A Survey of Reinforcement Learning Algorithms for Dynamically Varying Environments","date":"2020-05-19","arxiv_id":"2005.10619","repositories_listed":0,"syntology":null},{"url":null,"slug":"batch-augmented-multi-agent-reinforcement","title":"Batch-Augmented Multi-Agent Reinforcement Learning for Efficient Traffic Signal Optimization","date":"2020-05-19","arxiv_id":"2005.09624","repositories_listed":0,"syntology":null},{"url":null,"slug":"experience-augmentation-boosting-and","title":"Experience Augmentation: Boosting and Accelerating Off-Policy Multi-Agent Reinforcement Learning","date":"2020-05-19","arxiv_id":"2005.09453","repositories_listed":0,"syntology":null},{"url":null,"slug":"human-instruction-following-with-deep","title":"Human Instruction-Following with Deep Reinforcement Learning via Transfer-Learning from Text","date":"2020-05-19","arxiv_id":"2005.09382","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-to-herd-agents-amongst-obstacles","title":"Learning to Herd Agents Amongst Obstacles: Training Robust Shepherding Behaviors using Deep Reinforcement Learning","date":"2020-05-19","arxiv_id":"2005.09476","repositories_listed":0,"syntology":null},{"url":null,"slug":"privileged-information-dropout-in","title":"Privileged Information Dropout in Reinforcement Learning","date":"2020-05-19","arxiv_id":"2005.09220","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-for-caching-with-space","title":"Reinforcement Learning for Caching with Space-Time Popularity Dynamics","date":"2020-05-19","arxiv_id":"2005.09155","repositories_listed":0,"syntology":null},{"url":null,"slug":"automating-turbulence-modeling-by-multi-agent","title":"Automating Turbulence Modeling by Multi-Agent Reinforcement Learning","date":"2020-05-18","arxiv_id":"2005.09023","repositories_listed":0,"syntology":null},{"url":null,"slug":"basal-glucose-control-in-type-1-diabetes","title":"Basal Glucose Control in Type 1 Diabetes using Deep Reinforcement Learning: An In Silico Validation","date":"2020-05-18","arxiv_id":"2005.09059","repositories_listed":0,"syntology":null},{"url":null,"slug":"optimal-charging-method-for-effective-li-ion","title":"Optimal Charging Method for Effective Li-ion Battery Life Extension Based on Reinforcement Learning","date":"2020-05-18","arxiv_id":"2005.08770","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-simple-imitation-learning-method-via","title":"A Simple Imitation Learning Method via Contrastive Regularization","date":"2020-05-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"concept-learning-in-deep-reinforcement","title":"Learning Transferable Concepts in Deep Reinforcement Learning","date":"2020-05-16","arxiv_id":"2005.07870","repositories_listed":0,"syntology":null},{"url":null,"slug":"data-driven-dynamic-multi-objective-optimal","title":"Data-driven Dynamic Multi-objective Optimal Control: An Aspiration-satisfying Reinforcement Learning Approach","date":"2020-05-14","arxiv_id":"2005.07118","repositories_listed":0,"syntology":null},{"url":null,"slug":"probabilistic-guarantees-for-safe-deep","title":"Probabilistic Guarantees for Safe Deep Reinforcement Learning","date":"2020-05-14","arxiv_id":"2005.07073","repositories_listed":0,"syntology":null},{"url":null,"slug":"solve-traveling-salesman-problem-by-monte","title":"Solve Traveling Salesman Problem by Monte Carlo Tree Search and Deep Neural Network","date":"2020-05-14","arxiv_id":"2005.06879","repositories_listed":0,"syntology":null},{"url":null,"slug":"stealthy-and-efficient-adversarial-attacks","title":"Stealthy and Efficient Adversarial Attacks against Deep Reinforcement Learning","date":"2020-05-14","arxiv_id":"2005.07099","repositories_listed":0,"syntology":null},{"url":null,"slug":"dream-architecture-a-developmental-approach","title":"DREAM Architecture: a Developmental Approach to Open-Ended Learning in Robotics","date":"2020-05-13","arxiv_id":"2005.06223","repositories_listed":0,"syntology":null},{"url":null,"slug":"explainable-reinforcement-learning-a-survey","title":"Explainable Reinforcement Learning: A Survey","date":"2020-05-13","arxiv_id":"2005.06247","repositories_listed":0,"syntology":null},{"url":null,"slug":"from-simulation-to-real-world-maneuver","title":"From Simulation to Real World Maneuver Execution using Deep Reinforcement Learning","date":"2020-05-13","arxiv_id":"2005.07023","repositories_listed":0,"syntology":null},{"url":null,"slug":"proxy-experience-replay-federated","title":"Proxy Experience Replay: Federated Distillation for Distributed Reinforcement Learning","date":"2020-05-13","arxiv_id":"2005.06105","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-new-deep-neural-architecture-search","title":"A New Deep Neural Architecture Search Pipeline for Face Recognition","date":"2020-05-12","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"unbiased-deep-reinforcement-learning-a","title":"Unbiased Deep Reinforcement Learning: A General Training Framework for Existing and Future Algorithms","date":"2020-05-12","arxiv_id":"2005.07782","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-deep-reinforcement-learning-approach-to-2","title":"A Deep Reinforcement Learning Approach to Efficient Drone Mobility Support","date":"2020-05-11","arxiv_id":"2005.05229","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-reinforcement-learning-for-organ","title":"Deep Reinforcement Learning for Organ Localization in CT","date":"2020-05-11","arxiv_id":"2005.04974","repositories_listed":0,"syntology":null},{"url":null,"slug":"maximizing-information-gain-in-partially","title":"Maximizing Information Gain in Partially Observable Environments via Prediction Reward","date":"2020-05-11","arxiv_id":"2005.04912","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-based-on-real-time","title":"Reinforcement Learning Based on Real-Time Iteration NMPC","date":"2020-05-11","arxiv_id":"2005.05225","repositories_listed":0,"syntology":null}],"record_sha256":"cb10d4113f33eeece59813b6a349763da16a2e96e531bca9cdf28947f24df267","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}