{"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/126","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":126,"pages_in_order":135,"rows_per_page":100,"rows":[12501,12600],"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/125","next":"/task/reinforcement-learning-2/papers/127","papers":[{"url":null,"slug":"variational-bayesian-reinforcement-learning","title":"Variational Bayesian Reinforcement Learning with Regret Bounds","date":"2018-07-25","arxiv_id":"1807.09647","repositories_listed":0,"syntology":null},{"url":null,"slug":"contrastive-explanations-for-reinforcement","title":"Contrastive Explanations for Reinforcement Learning in terms of Expected Consequences","date":"2018-07-23","arxiv_id":"1807.08706","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-to-play-pong-using-policy-gradient","title":"Learning to Play Pong using Policy Gradient Learning","date":"2018-07-23","arxiv_id":"1807.08452","repositories_listed":0,"syntology":null},{"url":null,"slug":"accelerated-structure-aware-reinforcement","title":"Accelerated Structure-Aware Reinforcement Learning for Delay-Sensitive Energy Harvesting Wireless Sensors","date":"2018-07-22","arxiv_id":"1807.08315","repositories_listed":0,"syntology":null},{"url":null,"slug":"asynchronous-advantage-actor-critic-agent-for","title":"Asynchronous Advantage Actor-Critic Agent for Starcraft II","date":"2018-07-22","arxiv_id":"1807.08217","repositories_listed":0,"syntology":null},{"url":null,"slug":"navren-rl-learning-to-fly-in-real-environment","title":"NAVREN-RL: Learning to fly in real environment via end-to-end deep reinforcement learning using monocular images","date":"2018-07-22","arxiv_id":"1807.08241","repositories_listed":0,"syntology":null},{"url":null,"slug":"fuzzergym-a-competitive-framework-for-fuzzing","title":"FuzzerGym: A Competitive Framework for Fuzzing and Learning","date":"2018-07-19","arxiv_id":"1807.07490","repositories_listed":0,"syntology":null},{"url":null,"slug":"self-organizing-maps-as-a-storage-and","title":"Self-Organizing Maps as a Storage and Transfer Mechanism in Reinforcement Learning","date":"2018-07-19","arxiv_id":"1807.07530","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-explainable-and-controllable-open","title":"Towards Explainable and Controllable Open Domain Dialogue Generation with Dialogue Acts","date":"2018-07-19","arxiv_id":"1807.07255","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-for-ltlfldlf-goals","title":"Foundations for Restraining Bolts: Reinforcement Learning with LTLf/LDLf restraining specifications","date":"2018-07-17","arxiv_id":"1807.06333","repositories_listed":0,"syntology":null},{"url":null,"slug":"discrete-linear-complexity-reinforcement","title":"Discrete linear-complexity reinforcement learning in continuous action spaces for Q-learning algorithms","date":"2018-07-16","arxiv_id":"1807.06957","repositories_listed":0,"syntology":null},{"url":null,"slug":"online-robust-policy-learning-in-the-presence","title":"Online Robust Policy Learning in the Presence of Unknown Adversaries","date":"2018-07-16","arxiv_id":"1807.06064","repositories_listed":0,"syntology":null},{"url":null,"slug":"shielded-decision-making-in-mdps","title":"Safe Reinforcement Learning via Probabilistic Shields","date":"2018-07-16","arxiv_id":"1807.06096","repositories_listed":0,"syntology":null},{"url":null,"slug":"toward-interpretable-deep-reinforcement","title":"Toward Interpretable Deep Reinforcement Learning with Linear Model U-Trees","date":"2018-07-16","arxiv_id":"1807.05887","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-hierarchy-aware-inverse","title":"Exploring Hierarchy-Aware Inverse Reinforcement Learning","date":"2018-07-13","arxiv_id":"1807.05037","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-affective-robot-companion-for-assisting","title":"An Affective Robot Companion for Assisting the Elderly in a Cognitive Game Scenario","date":"2018-07-12","arxiv_id":"1807.09825","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-bottleneck-simulator-a-model-based-deep","title":"The Bottleneck Simulator: A Model-based Deep Reinforcement Learning Approach","date":"2018-07-12","arxiv_id":"1807.04723","repositories_listed":0,"syntology":null},{"url":null,"slug":"will-it-blend-composing-value-functions-in","title":"Will it Blend? Composing Value Functions in Reinforcement Learning","date":"2018-07-12","arxiv_id":"1807.04439","repositories_listed":0,"syntology":null},{"url":null,"slug":"cirl-controllable-imitative-reinforcement","title":"CIRL: Controllable Imitative Reinforcement Learning for Vision-based Self-driving","date":"2018-07-10","arxiv_id":"1807.03776","repositories_listed":0,"syntology":null},{"url":null,"slug":"partial-policy-based-reinforcement-learning","title":"Partial Policy-based Reinforcement Learning for Anatomical Landmark Localization in 3D Medical Images","date":"2018-07-09","arxiv_id":"1807.02908","repositories_listed":0,"syntology":null},{"url":null,"slug":"video-summarisation-by-classification-with","title":"Video Summarisation by Classification with Deep Reinforcement Learning","date":"2018-07-09","arxiv_id":"1807.03089","repositories_listed":0,"syntology":null},{"url":null,"slug":"auto-deep-compression-by-reinforcement","title":"Auto Deep Compression by Reinforcement Learning Based Actor-Critic Structure","date":"2018-07-08","arxiv_id":"1807.02886","repositories_listed":0,"syntology":null},{"url":null,"slug":"end-to-end-race-driving-with-deep","title":"End-to-End Race Driving with Deep Reinforcement Learning","date":"2018-07-06","arxiv_id":"1807.02371","repositories_listed":0,"syntology":null},{"url":null,"slug":"variance-reduction-for-reinforcement-learning","title":"Variance Reduction for Reinforcement Learning in Input-Driven Environments","date":"2018-07-06","arxiv_id":"1807.02264","repositories_listed":0,"syntology":null},{"url":null,"slug":"arcades-a-deep-model-for-adaptive-decision","title":"Arcades: A deep model for adaptive decision making in voice controlled smart-home","date":"2018-07-05","arxiv_id":"1807.01970","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-reinforcement-learning-for-doom-using","title":"Deep Reinforcement Learning for Doom using Unsupervised Auxiliary Tasks","date":"2018-07-05","arxiv_id":"1807.01960","repositories_listed":0,"syntology":null},{"url":null,"slug":"goal-oriented-trajectories-for-efficient","title":"Goal-oriented Trajectories for Efficient Exploration","date":"2018-07-05","arxiv_id":"1807.02078","repositories_listed":0,"syntology":null},{"url":null,"slug":"intelligent-traffic-signal-control-using","title":"Using Reinforcement Learning with Partial Vehicle Detection for Intelligent Traffic Signal Control","date":"2018-07-04","arxiv_id":"1807.01628","repositories_listed":0,"syntology":null},{"url":null,"slug":"region-growing-curriculum-generation-for","title":"Region Growing Curriculum Generation for Reinforcement Learning","date":"2018-07-04","arxiv_id":"1807.01425","repositories_listed":0,"syntology":null},{"url":null,"slug":"supervised-reinforcement-learning-with","title":"Supervised Reinforcement Learning with Recurrent Neural Network for Dynamic Treatment Recommendation","date":"2018-07-04","arxiv_id":"1807.01473","repositories_listed":0,"syntology":null},{"url":null,"slug":"transfer-with-model-features-in-reinforcement","title":"Transfer with Model Features in Reinforcement Learning","date":"2018-07-04","arxiv_id":"1807.01736","repositories_listed":0,"syntology":null},{"url":"/paper/a-language-model-based-evaluator-for-sentence","slug":"a-language-model-based-evaluator-for-sentence","title":"A Language Model based Evaluator for Sentence Compression","date":"2018-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"a-reinforcement-learning-neural-network-for","title":"A Reinforcement Learning Neural Network for Robotic Manipulator Control","date":"2018-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"beyond-the-one-step-greedy-approach-in","title":"Beyond the One-Step Greedy Approach in Reinforcement Learning","date":"2018-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"beyond-winning-and-losing-modeling-human","title":"Beyond Winning and Losing: Modeling Human Motivations and Behaviors Using Inverse Reinforcement Learning","date":"2018-07-01","arxiv_id":"1807.00366","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-reinforcement-learning-for-nlp","title":"Deep Reinforcement Learning for NLP","date":"2018-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"feudal-dialogue-management-with-jointly","title":"Feudal Dialogue Management with Jointly Learned Feature Extractors","date":"2018-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-hierarchical-structures-on-the-fly","title":"Learning Hierarchical Structures On-The-Fly with a Recurrent-Recursive Model for Sequences","date":"2018-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-to-act-in-decentralized-partially","title":"Learning to Act in Decentralized Partially Observable MDPs","date":"2018-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-to-explore-via-meta-policy-gradient","title":"Learning to Explore via Meta-Policy Gradient","date":"2018-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"mix-match-agent-curricula-for-reinforcement","title":"Mix & Match - Agent Curricula for Reinforcement Learning","date":"2018-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"policy-and-value-transfer-in-lifelong","title":"Policy and Value Transfer in Lifelong Reinforcement Learning","date":"2018-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"spotlight-optimizing-device-placement-for","title":"Spotlight: Optimizing Device Placement for Training Deep Neural Networks","date":"2018-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"state-abstractions-for-lifelong-reinforcement","title":"State Abstractions for Lifelong Reinforcement Learning","date":"2018-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-mixed-optimization-for-reinforcement","title":"Towards Mixed Optimization for Reinforcement Learning with Program Synthesis","date":"2018-07-01","arxiv_id":"1807.00403","repositories_listed":0,"syntology":null},{"url":null,"slug":"understanding-and-simplifying-one-shot","title":"Understanding and Simplifying One-Shot Architecture Search","date":"2018-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"hierarchical-reinforcement-learning-with","title":"Hierarchical Reinforcement Learning with Abductive Planning","date":"2018-06-28","arxiv_id":"1806.10792","repositories_listed":0,"syntology":null},{"url":null,"slug":"monas-multi-objective-neural-architecture","title":"MONAS: Multi-Objective Neural Architecture Search using Reinforcement Learning","date":"2018-06-27","arxiv_id":"1806.10332","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-agent-inverse-reinforcement-learning-1","title":"Multi-agent Inverse Reinforcement Learning for Certain General-sum Stochastic Games","date":"2018-06-26","arxiv_id":"1806.09795","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-reinforcement-learning-an-overview-1","title":"Deep Reinforcement Learning: An Overview","date":"2018-06-23","arxiv_id":"1806.08894","repositories_listed":0,"syntology":null},{"url":null,"slug":"human-interactive-subgoal-supervision-for","title":"Human-Interactive Subgoal Supervision for Efficient Inverse Reinforcement Learning","date":"2018-06-22","arxiv_id":"1806.08479","repositories_listed":0,"syntology":null},{"url":null,"slug":"many-goals-reinforcement-learning","title":"Many-Goals Reinforcement Learning","date":"2018-06-22","arxiv_id":"1806.09605","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-new-approach-for-resource-scheduling-with","title":"A New Approach for Resource Scheduling with Deep Reinforcement Learning","date":"2018-06-21","arxiv_id":"1806.08122","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-dissection-of-overfitting-and","title":"A Dissection of Overfitting and Generalization in Continuous Reinforcement Learning","date":"2018-06-20","arxiv_id":"1806.07937","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-using-augmented-neural","title":"Reinforcement Learning using Augmented Neural Networks","date":"2018-06-20","arxiv_id":"1806.07692","repositories_listed":0,"syntology":null},{"url":null,"slug":"skilled-experience-catalogue-a-skill","title":"Skilled Experience Catalogue: A Skill-Balancing Mechanism for Non-Player Characters using Reinforcement Learning","date":"2018-06-20","arxiv_id":"1806.07637","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-survey-of-inverse-reinforcement-learning","title":"A Survey of Inverse Reinforcement Learning: Challenges, Methods and Progress","date":"2018-06-18","arxiv_id":"1806.06877","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-unified-strategy-for-implementing-curiosity","title":"A unified strategy for implementing curiosity and empowerment driven reinforcement learning","date":"2018-06-18","arxiv_id":"1806.06505","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-from-outside-the-viability-kernel","title":"Learning from Outside the Viability Kernel: Why we Should Build Robots that can Fall with Grace","date":"2018-06-18","arxiv_id":"1806.06569","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-policy-representations-in-multiagent","title":"Learning Policy Representations in Multiagent Systems","date":"2018-06-17","arxiv_id":"1806.06464","repositories_listed":0,"syntology":null},{"url":null,"slug":"handling-cold-start-collaborative-filtering","title":"Handling Cold-Start Collaborative Filtering with Reinforcement Learning","date":"2018-06-16","arxiv_id":"1806.06192","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-width-based-planning-with-compact","title":"Improving width-based planning with compact policies","date":"2018-06-15","arxiv_id":"1806.05898","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-level-policy-and-reward-reinforcement","title":"Multi-Level Policy and Reward Reinforcement Learning for Image Captioning","date":"2018-06-15","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"adaptive-shooting-for-bots-in-first-person","title":"Adaptive Shooting for Bots in First Person Shooter Games Using Reinforcement Learning","date":"2018-06-14","arxiv_id":"1806.05554","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-reinforcement-learning-for-dynamic-urban","title":"Deep Reinforcement Learning for Dynamic Urban Transportation Problems","date":"2018-06-14","arxiv_id":"1806.05310","repositories_listed":0,"syntology":null},{"url":null,"slug":"qualitative-measurements-of-policy","title":"Qualitative Measurements of Policy Discrepancy for Return-Based Deep Q-Network","date":"2018-06-14","arxiv_id":"1806.06953","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-with-function-valued","title":"Reinforcement Learning with Function-Valued Action Spaces for Partial Differential Equation Control","date":"2018-06-13","arxiv_id":"1806.06931","repositories_listed":0,"syntology":null},{"url":null,"slug":"meta-learning-transferable-active-learning","title":"Meta-Learning Transferable Active Learning Policies by Deep Reinforcement Learning","date":"2018-06-12","arxiv_id":"1806.04798","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-agent-deep-reinforcement-learning-with-1","title":"Multi-Agent Deep Reinforcement Learning with Human Strategies","date":"2018-06-12","arxiv_id":"1806.04562","repositories_listed":0,"syntology":null},{"url":null,"slug":"unsupervised-meta-learning-for-reinforcement","title":"Unsupervised Meta-Learning for Reinforcement Learning","date":"2018-06-12","arxiv_id":"1806.04640","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-efficient-generalized-bellman-update-for","title":"An Efficient, Generalized Bellman Update For Cooperative Inverse Reinforcement Learning","date":"2018-06-11","arxiv_id":"1806.03820","repositories_listed":0,"syntology":null},{"url":null,"slug":"implicit-policy-for-reinforcement-learning","title":"Implicit Policy for Reinforcement Learning","date":"2018-06-10","arxiv_id":"1806.06798","repositories_listed":0,"syntology":null},{"url":null,"slug":"automatic-view-planning-with-multi-scale-deep","title":"Automatic View Planning with Multi-scale Deep Reinforcement Learning Agents","date":"2018-06-08","arxiv_id":"1806.03228","repositories_listed":0,"syntology":null},{"url":null,"slug":"program-synthesis-through-reinforcement","title":"Program Synthesis Through Reinforcement Learning Guided Tree Search","date":"2018-06-08","arxiv_id":"1806.02932","repositories_listed":0,"syntology":null},{"url":null,"slug":"self-consistent-trajectory-autoencoder","title":"Self-Consistent Trajectory Autoencoder: Hierarchical Reinforcement Learning with Trajectory Embeddings","date":"2018-06-07","arxiv_id":"1806.02813","repositories_listed":0,"syntology":null},{"url":null,"slug":"discovering-and-removing-exogenous-state","title":"Discovering and Removing Exogenous State Variables and Rewards for Reinforcement Learning","date":"2018-06-05","arxiv_id":"1806.01584","repositories_listed":0,"syntology":null},{"url":null,"slug":"mixmatch-agent-curricula-for-reinforcement","title":"Mix&Match - Agent Curricula for Reinforcement Learning","date":"2018-06-05","arxiv_id":"1806.01780","repositories_listed":0,"syntology":null},{"url":null,"slug":"adversarial-reinforcement-learning-framework","title":"Adversarial Reinforcement Learning Framework for Benchmarking Collision Avoidance Mechanisms in Autonomous Vehicles","date":"2018-06-04","arxiv_id":"1806.01368","repositories_listed":0,"syntology":null},{"url":null,"slug":"mitigation-of-policy-manipulation-attacks-on","title":"Mitigation of Policy Manipulation Attacks on Deep Q-Networks with Parameter-Space Noise","date":"2018-06-04","arxiv_id":"1806.02190","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploration-in-structured-reinforcement","title":"Exploration in Structured Reinforcement Learning","date":"2018-06-03","arxiv_id":"1806.00775","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-agent-reinforcement-learning-via-double","title":"Multi-Agent Reinforcement Learning via Double Averaging Primal-Dual Optimization","date":"2018-06-03","arxiv_id":"1806.00877","repositories_listed":0,"syntology":null},{"url":null,"slug":"daqn-deep-auto-encoder-and-q-network","title":"DAQN: Deep Auto-encoder and Q-Network","date":"2018-06-02","arxiv_id":"1806.00630","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-pepper-expert-iteration-based-chess","title":"Deep Pepper: Expert Iteration based Chess agent in the Reinforcement Learning Setting","date":"2018-06-02","arxiv_id":"1806.00683","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-entropy-for-policy-gradient-with","title":"Efficient Entropy for Policy Gradient with Multidimensional Action Space","date":"2018-06-02","arxiv_id":"1806.00589","repositories_listed":0,"syntology":null},{"url":null,"slug":"internal-model-from-observations-for-reward","title":"Internal Model from Observations for Reward Shaping","date":"2018-06-02","arxiv_id":"1806.01267","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-reinforcement-learning-approach-to-age-of","title":"A Reinforcement Learning Approach to Age of Information in Multi-User Networks","date":"2018-06-01","arxiv_id":"1806.00336","repositories_listed":0,"syntology":null},{"url":"/paper/deep-progressive-reinforcement-learning-for","slug":"deep-progressive-reinforcement-learning-for","title":"Deep Progressive Reinforcement Learning for Skeleton-Based Action Recognition","date":"2018-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"environment-upgrade-reinforcement-learning","title":"Environment Upgrade Reinforcement Learning for Non-Differentiable Multi-Stage Pipelines","date":"2018-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"equivalence-between-wasserstein-and-value","title":"Equivalence Between Wasserstein and Value-Aware Loss for Model-based Reinforcement Learning","date":"2018-06-01","arxiv_id":"1806.01265","repositories_listed":0,"syntology":null},{"url":null,"slug":"fast-exploration-with-simplified-models-and","title":"Fast Exploration with Simplified Models and Approximately Optimistic Planning in Model Based Reinforcement Learning","date":"2018-06-01","arxiv_id":"1806.00175","repositories_listed":0,"syntology":null},{"url":null,"slug":"graphbit-bitwise-interaction-mining-via-deep","title":"GraphBit: Bitwise Interaction Mining via Deep Reinforcement Learning","date":"2018-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"improved-oracle-complexity-for-stochastic","title":"Improved Sample Complexity for Stochastic Compositional Variance Reduced Gradient","date":"2018-06-01","arxiv_id":"1806.00458","repositories_listed":0,"syntology":null},{"url":null,"slug":"inference-aided-reinforcement-learning-for","title":"Inference Aided Reinforcement Learning for Incentive Mechanism Design in Crowdsourcing","date":"2018-06-01","arxiv_id":"1806.00206","repositories_listed":0,"syntology":null},{"url":null,"slug":"integrating-episodic-memory-into-a","title":"Integrating Episodic Memory into a Reinforcement Learning Agent using Reservoir Sampling","date":"2018-06-01","arxiv_id":"1806.00540","repositories_listed":0,"syntology":null},{"url":null,"slug":"mining-evidences-for-concept-stock","title":"Mining Evidences for Concept Stock Recommendation","date":"2018-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"quality-signals-in-generated-stories","title":"Quality Signals in Generated Stories","date":"2018-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"seednet-automatic-seed-generation-with-deep","title":"SeedNet: Automatic Seed Generation With Deep Reinforcement Learning for Robust Interactive Segmentation","date":"2018-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"evaluating-reinforcement-learning-algorithms","title":"Evaluating Reinforcement Learning Algorithms in Observational Health Settings","date":"2018-05-31","arxiv_id":"1805.12298","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-a-prior-over-intent-via-meta-inverse","title":"Learning a Prior over Intent via Meta-Inverse Reinforcement Learning","date":"2018-05-31","arxiv_id":"1805.12573","repositories_listed":0,"syntology":null},{"url":null,"slug":"depth-and-nonlinearity-induce-implicit","title":"Depth and nonlinearity induce implicit exploration for RL","date":"2018-05-29","arxiv_id":"1805.11711","repositories_listed":0,"syntology":null}],"record_sha256":"0ff6252feff4587ee3c0e7d0ac817161642ddc8ba2a86ca54b79927f64000cf9","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}