{"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-2/papers/127","list_of":"/task/reinforcement-learning-2","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":127,"pages_in_order":135,"rows_per_page":100,"rows":[12601,12700],"of":13427,"counts":{"archive_papers_tagged":13427,"with_a_code_link":4119,"where_syntology_ran_a_sample":1165,"not_listed_spam_title":0,"listed":13427,"listed_where_code_ran":1165,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":973,"every_run_a_failure_of_syntologys_instrument":192,"listed_with_a_run_with_no_instrument_failure":973,"listed_every_run_a_failure_of_syntologys_instrument":192,"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-2","prev":"/task/reinforcement-learning-2/papers/126","next":"/task/reinforcement-learning-2/papers/128","papers":[{"url":null,"slug":"truncated-horizon-policy-search-combining","title":"Truncated Horizon Policy Search: Combining Reinforcement Learning & Imitation Learning","date":"2018-05-29","arxiv_id":"1805.11240","repositories_listed":0,"syntology":null},{"url":null,"slug":"variational-inverse-control-with-events-a","title":"Variational Inverse Control with Events: A General Framework for Data-Driven Reward Definition","date":"2018-05-29","arxiv_id":"1805.11686","repositories_listed":0,"syntology":null},{"url":null,"slug":"virtuously-safe-reinforcement-learning","title":"Virtuously Safe Reinforcement Learning","date":"2018-05-29","arxiv_id":"1805.11447","repositories_listed":0,"syntology":null},{"url":null,"slug":"hierarchical-clustering-with-deep-q-learning","title":"Hierarchical clustering with deep Q-learning","date":"2018-05-28","arxiv_id":"1805.10900","repositories_listed":0,"syntology":null},{"url":null,"slug":"importance-weighted-transfer-of-samples-in","title":"Importance Weighted Transfer of Samples in Reinforcement Learning","date":"2018-05-28","arxiv_id":"1805.10886","repositories_listed":0,"syntology":null},{"url":null,"slug":"value-propagation-networks","title":"Value Propagation Networks","date":"2018-05-28","arxiv_id":"1805.11199","repositories_listed":0,"syntology":null},{"url":null,"slug":"fingerprint-policy-optimisation-for-robust","title":"Fingerprint Policy Optimisation for Robust Reinforcement Learning","date":"2018-05-27","arxiv_id":"1805.10662","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-reinforcement-learning-in-ice-hockey-for","title":"Deep Reinforcement Learning in Ice Hockey for Context-Aware Player Evaluation","date":"2018-05-26","arxiv_id":"1805.11088","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-sliding-window-algorithm-for-markov","title":"A Sliding-Window Algorithm for Markov Decision Processes with Arbitrarily Changing Rewards and Transitions","date":"2018-05-25","arxiv_id":"1805.10066","repositories_listed":0,"syntology":null},{"url":null,"slug":"finite-sample-analysis-of-lstd-with-random","title":"Finite Sample Analysis of LSTD with Random Projections and Eligibility Traces","date":"2018-05-25","arxiv_id":"1805.10005","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforced-extractive-summarization-with","title":"Reinforced Extractive Summarization with Question-Focused Rewards","date":"2018-05-25","arxiv_id":"1805.10392","repositories_listed":0,"syntology":null},{"url":null,"slug":"resource-allocation-for-a-wireless","title":"Resource Allocation for a Wireless Coexistence Management System Based on Reinforcement Learning","date":"2018-05-24","arxiv_id":"1806.04702","repositories_listed":0,"syntology":null},{"url":null,"slug":"discovering-blind-spots-in-reinforcement","title":"Discovering Blind Spots in Reinforcement Learning","date":"2018-05-23","arxiv_id":"1805.08966","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-for-heterogeneous","title":"Reinforcement Learning for Heterogeneous Teams with PALO Bounds","date":"2018-05-23","arxiv_id":"1805.09267","repositories_listed":0,"syntology":null},{"url":null,"slug":"scalable-centralized-deep-multi-agent","title":"Scalable Centralized Deep Multi-Agent Reinforcement Learning via Policy Gradients","date":"2018-05-22","arxiv_id":"1805.08776","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-framework-and-method-for-online-inverse","title":"A Framework and Method for Online Inverse Reinforcement Learning","date":"2018-05-21","arxiv_id":"1805.07871","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-general-family-of-robust-stochastic","title":"A General Family of Robust Stochastic Operators for Reinforcement Learning","date":"2018-05-21","arxiv_id":"1805.08122","repositories_listed":0,"syntology":null},{"url":null,"slug":"hierarchical-reinforcement-learning-with-1","title":"Hierarchical Reinforcement Learning with Hindsight","date":"2018-05-21","arxiv_id":"1805.08180","repositories_listed":0,"syntology":null},{"url":"/paper/hierarchically-structured-reinforcement","slug":"hierarchically-structured-reinforcement","title":"Hierarchically Structured Reinforcement Learning for Topically Coherent Visual Story Generation","date":"2018-05-21","arxiv_id":"1805.08191","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-safe-policies-with-expert-guidance","title":"Learning Safe Policies with Expert Guidance","date":"2018-05-21","arxiv_id":"1805.08313","repositories_listed":0,"syntology":null},{"url":null,"slug":"multiple-step-greedy-policies-in-online-and","title":"Multiple-Step Greedy Policies in Online and Approximate Reinforcement Learning","date":"2018-05-21","arxiv_id":"1805.07956","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-real-world-robot-policies-by","title":"Learning Real-World Robot Policies by Dreaming","date":"2018-05-20","arxiv_id":"1805.07813","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-to-teach-in-cooperative-multiagent","title":"Learning to Teach in Cooperative Multiagent Reinforcement Learning","date":"2018-05-20","arxiv_id":"1805.07830","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-of-theorem-proving","title":"Reinforcement Learning of Theorem Proving","date":"2018-05-19","arxiv_id":"1805.07563","repositories_listed":0,"syntology":null},{"url":null,"slug":"hierarchical-reinforcement-learning-with-deep","title":"Hierarchical Reinforcement Learning with Deep Nested Agents","date":"2018-05-18","arxiv_id":"1805.07008","repositories_listed":0,"syntology":null},{"url":null,"slug":"two-geometric-input-transformation-methods","title":"Two geometric input transformation methods for fast online reinforcement learning with neural nets","date":"2018-05-18","arxiv_id":"1805.07476","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-reinforcement-learning-for-resource","title":"Deep Reinforcement Learning for Resource Management in Network Slicing","date":"2018-05-17","arxiv_id":"1805.06591","repositories_listed":0,"syntology":null},{"url":null,"slug":"language-expansion-in-text-based-games","title":"Language Expansion In Text-Based Games","date":"2018-05-17","arxiv_id":"1805.07274","repositories_listed":0,"syntology":null},{"url":null,"slug":"fast-retinomorphic-event-stream-for-video","title":"Fast Retinomorphic Event Stream for Video Recognition and Reinforcement Learning","date":"2018-05-16","arxiv_id":"1805.06374","repositories_listed":0,"syntology":null},{"url":null,"slug":"follownet-robot-navigation-by-following","title":"FollowNet: Robot Navigation by Following Natural Language Directions with Deep Reinforcement Learning","date":"2018-05-16","arxiv_id":"1805.06150","repositories_listed":0,"syntology":null},{"url":null,"slug":"optimized-computation-offloading-performance","title":"Optimized Computation Offloading Performance in Virtual Edge Computing Systems via Deep Reinforcement Learning","date":"2018-05-16","arxiv_id":"1805.06146","repositories_listed":0,"syntology":null},{"url":null,"slug":"feedback-based-tree-search-for-reinforcement","title":"Feedback-Based Tree Search for Reinforcement Learning","date":"2018-05-15","arxiv_id":"1805.05935","repositories_listed":0,"syntology":null},{"url":null,"slug":"graph-signal-sampling-via-reinforcement","title":"Graph Signal Sampling via Reinforcement Learning","date":"2018-05-15","arxiv_id":"1805.05827","repositories_listed":0,"syntology":null},{"url":null,"slug":"leveraging-human-knowledge-in-tabular","title":"Leveraging human knowledge in tabular reinforcement learning: A study of human subjects","date":"2018-05-15","arxiv_id":"1805.05769","repositories_listed":0,"syntology":null},{"url":null,"slug":"generating-rescheduling-knowledge-using","title":"Generating Rescheduling Knowledge using Reinforcement Learning in a Cognitive Architecture","date":"2018-05-12","arxiv_id":"1805.04752","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-autonomous-reinforcement-learning","title":"Towards Autonomous Reinforcement Learning: Automatic Setting of Hyper-parameters using Bayesian Optimization","date":"2018-05-12","arxiv_id":"1805.04748","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-hierarchical-reinforcement-learning","title":"Deep Hierarchical Reinforcement Learning Algorithm in Partially Observable Markov Decision Processes","date":"2018-05-11","arxiv_id":"1805.04419","repositories_listed":0,"syntology":null},{"url":null,"slug":"interactive-reinforcement-learning-with","title":"Interactive Reinforcement Learning with Dynamic Reuse of Prior Knowledge from Human/Agent's Demonstration","date":"2018-05-11","arxiv_id":"1805.04493","repositories_listed":0,"syntology":null},{"url":null,"slug":"leveraging-grammar-and-reinforcement-learning","title":"Leveraging Grammar and Reinforcement Learning for Neural Program Synthesis","date":"2018-05-11","arxiv_id":"1805.04276","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-reinforcement-learning-for-optimal","title":"Deep Reinforcement Learning for Optimal Control of Space Heating","date":"2018-05-10","arxiv_id":"1805.03777","repositories_listed":0,"syntology":null},{"url":null,"slug":"discourse-aware-neural-rewards-for-coherent","title":"Discourse-Aware Neural Rewards for Coherent Text Generation","date":"2018-05-10","arxiv_id":"1805.03766","repositories_listed":0,"syntology":null},{"url":null,"slug":"multimodal-hierarchical-reinforcement","title":"Multimodal Hierarchical Reinforcement Learning Policy for Task-Oriented Visual Dialog","date":"2018-05-08","arxiv_id":"1805.03257","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-reinforcement-learning-for-page-wise","title":"Deep Reinforcement Learning for Page-wise Recommendations","date":"2018-05-07","arxiv_id":"1805.02343","repositories_listed":0,"syntology":null},{"url":null,"slug":"multimodal-machine-translation-with","title":"Multimodal Machine Translation with Reinforcement Learning","date":"2018-05-07","arxiv_id":"1805.02356","repositories_listed":0,"syntology":null},{"url":null,"slug":"developing-parsimonious-ensembles-using","title":"Developing parsimonious ensembles using ensemble diversity within a reinforcement learning framework","date":"2018-05-05","arxiv_id":"1805.02103","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploration-by-distributional-reinforcement","title":"Exploration by Distributional Reinforcement Learning","date":"2018-05-04","arxiv_id":"1805.01907","repositories_listed":0,"syntology":null},{"url":null,"slug":"robust-deep-reinforcement-learning-for","title":"Robust Deep Reinforcement Learning for Security and Safety in Autonomous Vehicle Systems","date":"2018-05-02","arxiv_id":"1805.00983","repositories_listed":0,"syntology":null},{"url":null,"slug":"falsification-of-cyber-physical-systems-using","title":"Falsification of Cyber-Physical Systems Using Deep Reinforcement Learning","date":"2018-05-01","arxiv_id":"1805.00200","repositories_listed":0,"syntology":null},{"url":null,"slug":"robust-log-optimal-strategy-with","title":"Robust Log-Optimal Strategy with Reinforcement Learning","date":"2018-05-01","arxiv_id":"1805.00205","repositories_listed":0,"syntology":null},{"url":null,"slug":"generating-interpretable-fuzzy-controllers","title":"Generating Interpretable Fuzzy Controllers using Particle Swarm Optimization and Genetic Programming","date":"2018-04-29","arxiv_id":"1804.10960","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-experienced-anomaly-detector-through","title":"Towards Experienced Anomaly Detector through Reinforcement Learning","date":"2018-04-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"sentiment-adaptive-end-to-end-dialog-systems","title":"Sentiment Adaptive End-to-End Dialog Systems","date":"2018-04-28","arxiv_id":"1804.10731","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-reinforcement-learning-to-acquire","title":"Deep Reinforcement Learning to Acquire Navigation Skills for Wheel-Legged Robots in Complex Environments","date":"2018-04-27","arxiv_id":"1804.10500","repositories_listed":0,"syntology":null},{"url":null,"slug":"action-categorization-for-computationally","title":"Action Categorization for Computationally Improved Task Learning and Planning","date":"2018-04-26","arxiv_id":"1804.09856","repositories_listed":0,"syntology":null},{"url":null,"slug":"multiagent-soft-q-learning","title":"Multiagent Soft Q-Learning","date":"2018-04-25","arxiv_id":"1804.09817","repositories_listed":0,"syntology":null},{"url":null,"slug":"benchmarking-projective-simulation-in","title":"Benchmarking projective simulation in navigation problems","date":"2018-04-23","arxiv_id":"1804.08607","repositories_listed":0,"syntology":null},{"url":null,"slug":"mqgrad-reinforcement-learning-of-gradient","title":"MQGrad: Reinforcement Learning of Gradient Quantization in Parameter Server","date":"2018-04-22","arxiv_id":"1804.08066","repositories_listed":0,"syntology":null},{"url":null,"slug":"peorl-integrating-symbolic-planning-and","title":"PEORL: Integrating Symbolic Planning and Hierarchical Reinforcement Learning for Robust Decision-Making","date":"2018-04-20","arxiv_id":"1804.07779","repositories_listed":0,"syntology":null},{"url":null,"slug":"cell-selection-with-deep-reinforcement","title":"Cell Selection with Deep Reinforcement Learning in Sparse Mobile Crowdsensing","date":"2018-04-19","arxiv_id":"1804.07047","repositories_listed":0,"syntology":null},{"url":null,"slug":"disentangling-controllable-and-uncontrollable","title":"Disentangling Controllable and Uncontrollable Factors of Variation by Interacting with the World","date":"2018-04-19","arxiv_id":"1804.06955","repositories_listed":0,"syntology":null},{"url":"/paper/learning-to-extract-coherent-summary-via-deep","slug":"learning-to-extract-coherent-summary-via-deep","title":"Learning to Extract Coherent Summary via Deep Reinforcement Learning","date":"2018-04-19","arxiv_id":"1804.07036","repositories_listed":0,"syntology":null},{"url":null,"slug":"automated-vehicles-behavior-decision-making","title":"Automated vehicle's behavior decision making using deep reinforcement learning and high-fidelity simulation environment","date":"2018-04-17","arxiv_id":"1804.06264","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-improving-deep-reinforcement-learning-for-1","title":"On Improving Deep Reinforcement Learning for POMDPs","date":"2018-04-17","arxiv_id":"1804.06309","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-how-to-self-learn-enhancing-self","title":"Learning How to Self-Learn: Enhancing Self-Training Using Neural Reinforcement Learning","date":"2018-04-16","arxiv_id":"1804.05734","repositories_listed":0,"syntology":null},{"url":null,"slug":"state-augmentation-transformations-for-risk","title":"State-Augmentation Transformations for Risk-Sensitive Reinforcement Learning","date":"2018-04-16","arxiv_id":"1804.05950","repositories_listed":0,"syntology":null},{"url":null,"slug":"robust-dual-view-deep-agent","title":"Robust Dual View Deep Agent","date":"2018-04-13","arxiv_id":"1804.05120","repositories_listed":0,"syntology":null},{"url":null,"slug":"distort-and-recover-color-enhancement-using","title":"Distort-and-Recover: Color Enhancement using Deep Reinforcement Learning","date":"2018-04-12","arxiv_id":"1804.04450","repositories_listed":0,"syntology":null},{"url":null,"slug":"feature-based-aggregation-and-deep","title":"Feature-Based Aggregation and Deep Reinforcement Learning: A Survey and Some New Implementations","date":"2018-04-12","arxiv_id":"1804.04577","repositories_listed":0,"syntology":null},{"url":null,"slug":"optimizing-query-evaluations-using","title":"Optimizing Query Evaluations using Reinforcement Learning for Web Search","date":"2018-04-12","arxiv_id":"1804.04410","repositories_listed":0,"syntology":null},{"url":null,"slug":"universal-successor-representations-for","title":"Universal Successor Representations for Transfer Reinforcement Learning","date":"2018-04-11","arxiv_id":"1804.03758","repositories_listed":0,"syntology":null},{"url":null,"slug":"binary-space-partitioning-as-intrinsic-reward","title":"Binary Space Partitioning as Intrinsic Reward","date":"2018-04-10","arxiv_id":"1804.03611","repositories_listed":0,"syntology":null},{"url":null,"slug":"outline-objects-using-deep-reinforcement","title":"Outline Objects using Deep Reinforcement Learning","date":"2018-04-10","arxiv_id":"1804.04603","repositories_listed":0,"syntology":null},{"url":null,"slug":"personalization-of-health-interventions-using","title":"A clustering-based reinforcement learning approach for tailored personalization of e-Health interventions","date":"2018-04-10","arxiv_id":"1804.03592","repositories_listed":0,"syntology":null},{"url":null,"slug":"latent-space-policies-for-hierarchical","title":"Latent Space Policies for Hierarchical Reinforcement Learning","date":"2018-04-09","arxiv_id":"1804.02808","repositories_listed":0,"syntology":null},{"url":null,"slug":"scalable-sentiment-for-sequence-to-sequence","title":"Scalable Sentiment for Sequence-to-sequence Chatbot Response with Performance Analysis","date":"2018-04-07","arxiv_id":"1804.02504","repositories_listed":0,"syntology":null},{"url":null,"slug":"programmatically-interpretable-reinforcement","title":"Programmatically Interpretable Reinforcement Learning","date":"2018-04-06","arxiv_id":"1804.02477","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-human-mixed-strategy-approach-to-deep","title":"A Human Mixed Strategy Approach to Deep Reinforcement Learning","date":"2018-04-05","arxiv_id":"1804.01874","repositories_listed":0,"syntology":null},{"url":null,"slug":"information-maximizing-exploration-with-a","title":"Information Maximizing Exploration with a Latent Dynamics Model","date":"2018-04-04","arxiv_id":"1804.01238","repositories_listed":0,"syntology":null},{"url":null,"slug":"emorl-continuous-acoustic-emotion","title":"EmoRL: Continuous Acoustic Emotion Classification using Deep Reinforcement Learning","date":"2018-04-03","arxiv_id":"1804.04053","repositories_listed":0,"syntology":null},{"url":null,"slug":"renewal-monte-carlo-renewal-theory-based","title":"Renewal Monte Carlo: Renewal theory based reinforcement learning","date":"2018-04-03","arxiv_id":"1804.01116","repositories_listed":0,"syntology":null},{"url":null,"slug":"curiosity-driven-exploration-for-mapless","title":"Curiosity-driven Exploration for Mapless Navigation with Deep Reinforcement Learning","date":"2018-04-02","arxiv_id":"1804.00456","repositories_listed":0,"syntology":null},{"url":null,"slug":"recall-traces-backtracking-models-for","title":"Recall Traces: Backtracking Models for Efficient Reinforcement Learning","date":"2018-04-02","arxiv_id":"1804.00379","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-to-run-challenge-synthesizing","title":"Learning to Run challenge: Synthesizing physiologically accurate motion using deep reinforcement learning","date":"2018-03-31","arxiv_id":"1804.00198","repositories_listed":0,"syntology":null},{"url":null,"slug":"snap-angle-prediction-for-360circ-panoramas","title":"Snap Angle Prediction for 360$^{\\circ}$ Panoramas","date":"2018-03-31","arxiv_id":"1804.00126","repositories_listed":0,"syntology":null},{"url":null,"slug":"how-an-electrical-engineer-became-an","title":"How an Electrical Engineer Became an Artificial Intelligence Researcher, a Multiphase Active Contours Analysis","date":"2018-03-29","arxiv_id":"1803.11261","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-for-non-prehensile","title":"Reinforcement learning for non-prehensile manipulation: Transfer from simulation to physical system","date":"2018-03-28","arxiv_id":"1803.10371","repositories_listed":0,"syntology":null},{"url":"/paper/deep-communicating-agents-for-abstractive","slug":"deep-communicating-agents-for-abstractive","title":"Deep Communicating Agents for Abstractive Summarization","date":"2018-03-27","arxiv_id":"1803.10357","repositories_listed":0,"syntology":null},{"url":null,"slug":"forward-backward-reinforcement-learning","title":"Forward-Backward Reinforcement Learning","date":"2018-03-27","arxiv_id":"1803.10227","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-for-fair-dynamic","title":"Reinforcement Learning for Fair Dynamic Pricing","date":"2018-03-27","arxiv_id":"1803.09967","repositories_listed":0,"syntology":null},{"url":null,"slug":"scalable-photonic-reinforcement-learning-by","title":"Scalable photonic reinforcement learning by time-division multiplexing of laser chaos","date":"2018-03-26","arxiv_id":"1803.09425","repositories_listed":0,"syntology":null},{"url":null,"slug":"autonomous-ramp-merge-maneuver-based-on","title":"Autonomous Ramp Merge Maneuver Based on Reinforcement Learning with Continuous Action Space","date":"2018-03-25","arxiv_id":"1803.09203","repositories_listed":0,"syntology":null},{"url":null,"slug":"dop-deep-optimistic-planning-with-approximate","title":"DOP: Deep Optimistic Planning with Approximate Value Function Evaluation","date":"2018-03-22","arxiv_id":"1803.08501","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-state-representations-for-query","title":"Learning State Representations for Query Optimization with Deep Reinforcement Learning","date":"2018-03-22","arxiv_id":"1803.08604","repositories_listed":0,"syntology":null},{"url":null,"slug":"meta-reinforcement-learning-with-latent","title":"Meta Reinforcement Learning with Latent Variable Gaussian Processes","date":"2018-03-20","arxiv_id":"1803.07551","repositories_listed":0,"syntology":null},{"url":null,"slug":"natural-gradient-deep-q-learning","title":"Natural Gradient Deep Q-learning","date":"2018-03-20","arxiv_id":"1803.07482","repositories_listed":0,"syntology":null},{"url":null,"slug":"optimizing-sponsored-search-ranking-strategy","title":"Optimizing Sponsored Search Ranking Strategy by Deep Reinforcement Learning","date":"2018-03-20","arxiv_id":"1803.07347","repositories_listed":0,"syntology":null},{"url":null,"slug":"variance-reduction-for-policy-gradient-with","title":"Variance Reduction for Policy Gradient with Action-Dependent Factorized Baselines","date":"2018-03-20","arxiv_id":"1803.07246","repositories_listed":0,"syntology":null},{"url":null,"slug":"neural-text-generation-past-present-and","title":"Neural Text Generation: Past, Present and Beyond","date":"2018-03-15","arxiv_id":"1803.07133","repositories_listed":0,"syntology":null},{"url":null,"slug":"rearrangement-with-nonprehensile-manipulation","title":"Rearrangement with Nonprehensile Manipulation Using Deep Reinforcement Learning","date":"2018-03-15","arxiv_id":"1803.05752","repositories_listed":0,"syntology":null},{"url":null,"slug":"automated-speed-and-lane-change-decision","title":"Automated Speed and Lane Change Decision Making using Deep Reinforcement Learning","date":"2018-03-14","arxiv_id":"1803.10056","repositories_listed":0,"syntology":null}],"record_sha256":"082716e3bda82ce1b22bc63153ab0ed733a2948b70002ddcf0fcbee758670c5b","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}