{"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/120","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":120,"pages_in_order":132,"rows_per_page":100,"rows":[11901,12000],"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/119","next":"/task/reinforcement-learning/papers/121","papers":[{"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":"learning-sentence-representations-over-tree","title":"Learning Sentence Representations over Tree Structures for Target-Dependent Classification","date":"2018-06-01","arxiv_id":null,"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":"neural-control-variates-for-variance","title":"Neural Control Variates for Variance Reduction","date":"2018-06-01","arxiv_id":"1806.00159","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":"reinforcement-cutting-agent-learning-for","title":"Reinforcement Cutting-Agent Learning for Video Object Segmentation","date":"2018-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"scalable-construction-and-reasoning-of","title":"Scalable Construction and Reasoning of Massive Knowledge Bases","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":"sim2real-viewpoint-invariant-visual-servoing","title":"Sim2Real Viewpoint Invariant Visual Servoing by Recurrent Control","date":"2018-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"sint-robust-visual-tracking-via-adversarial","title":"SINT++: Robust Visual Tracking via Adversarial Positive Instance Generation","date":"2018-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"tapas-train-less-accuracy-predictor-for","title":"TAPAS: Train-less Accuracy Predictor for Architecture Search","date":"2018-06-01","arxiv_id":"1806.00250","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":"sequential-attacks-on-agents-for-long-term","title":"Sequential Attacks on Agents for Long-Term Adversarial Goals","date":"2018-05-31","arxiv_id":"1805.12487","repositories_listed":0,"syntology":null},{"url":null,"slug":"adversarial-learning-of-task-oriented-neural","title":"Adversarial Learning of Task-Oriented Neural Dialog Models","date":"2018-05-30","arxiv_id":"1805.11762","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},{"url":null,"slug":"learning-to-transcribe-by-ear","title":"Learning to Transcribe by Ear","date":"2018-05-29","arxiv_id":"1805.11526","repositories_listed":0,"syntology":null},{"url":null,"slug":"observe-and-look-further-achieving-consistent","title":"Observe and Look Further: Achieving Consistent Performance on Atari","date":"2018-05-29","arxiv_id":"1805.11593","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-actor-search-tree-critic-astc-for-off","title":"The Actor Search Tree Critic (ASTC) for Off-Policy POMDP Learning in Medical Decision Making","date":"2018-05-29","arxiv_id":"1805.11548","repositories_listed":0,"syntology":null},{"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":"fast-policy-learning-through-imitation-and","title":"Fast Policy Learning through Imitation and Reinforcement","date":"2018-05-26","arxiv_id":"1805.10413","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":"detecting-deceptive-reviews-using-generative","title":"Detecting Deceptive Reviews using Generative Adversarial Networks","date":"2018-05-25","arxiv_id":"1805.10364","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":"learning-self-imitating-diverse-policies","title":"Learning Self-Imitating Diverse Policies","date":"2018-05-25","arxiv_id":"1805.10309","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":"dyna-planning-using-a-feature-based","title":"Dyna Planning using a Feature Based Generative Model","date":"2018-05-23","arxiv_id":"1805.10129","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":"when-simple-exploration-is-sample-efficient","title":"When Simple Exploration is Sample Efficient: Identifying Sufficient Conditions for Random Exploration to Yield PAC RL Algorithms","date":"2018-05-23","arxiv_id":"1805.09045","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-to-optimize-via-wasserstein-deep","title":"Learning to Optimize via Wasserstein Deep Inverse Optimal Control","date":"2018-05-22","arxiv_id":"1805.08395","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":"hybrid-retrieval-generation-reinforced-agent","title":"Hybrid Retrieval-Generation Reinforced Agent for Medical Image Report Generation","date":"2018-05-21","arxiv_id":"1805.08298","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":"nonlinear-distributional-gradient-temporal","title":"Nonlinear Distributional Gradient Temporal-Difference Learning","date":"2018-05-20","arxiv_id":"1805.07732","repositories_listed":0,"syntology":null},{"url":null,"slug":"task-agnostic-meta-learning-for-few-shot","title":"Task-Agnostic Meta-Learning for Few-shot Learning","date":"2018-05-20","arxiv_id":"1805.07722","repositories_listed":0,"syntology":null},{"url":null,"slug":"episodic-memory-deep-q-networks","title":"Episodic Memory Deep Q-Networks","date":"2018-05-19","arxiv_id":"1805.07603","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":"evolutionary-rl-for-container-loading","title":"Evolutionary RL for Container Loading","date":"2018-05-17","arxiv_id":"1805.06664","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":"neural-user-simulation-for-corpus-based-1","title":"Neural User Simulation for Corpus-based Policy Optimisation for Spoken Dialogue Systems","date":"2018-05-17","arxiv_id":"1805.06966","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":"joint-training-of-candidate-extraction-and","title":"Joint Training of Candidate Extraction and Answer Selection for Reading Comprehension","date":"2018-05-16","arxiv_id":"1805.06145","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":"the-hierarchical-adaptive-forgetting","title":"The Hierarchical Adaptive Forgetting Variational Filter","date":"2018-05-15","arxiv_id":"1805.05703","repositories_listed":0,"syntology":null},{"url":null,"slug":"low-pass-recurrent-neural-networks-a-memory","title":"Low-pass Recurrent Neural Networks - A memory architecture for longer-term correlation discovery","date":"2018-05-13","arxiv_id":"1805.04955","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":"task-transfer-by-preference-based-cost","title":"Task Transfer by Preference-Based Cost Learning","date":"2018-05-12","arxiv_id":"1805.04686","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":"metatrace-online-step-size-tuning-by-meta","title":"Metatrace Actor-Critic: Online Step-size Tuning by Meta-gradient Descent for Reinforcement Learning Control","date":"2018-05-10","arxiv_id":"1805.04514","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-to-teach","title":"Learning to Teach","date":"2018-05-09","arxiv_id":"1805.03643","repositories_listed":0,"syntology":null},{"url":null,"slug":"image-retrieval-with-mixed-initiative-and","title":"Image Retrieval with Mixed Initiative and Multimodal Feedback","date":"2018-05-08","arxiv_id":"1805.03134","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":"planning-and-learning-with-stochastic-action","title":"Planning and Learning with Stochastic Action Sets","date":"2018-05-07","arxiv_id":"1805.02363","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":"dynamic-control-flow-in-large-scale-machine","title":"Dynamic Control Flow in Large-Scale Machine Learning","date":"2018-05-04","arxiv_id":"1805.01772","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":"approximate-temporal-difference-learning-is-a","title":"Approximate Temporal Difference Learning is a Gradient Descent for Reversible Policies","date":"2018-05-02","arxiv_id":"1805.00869","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":"how-robust-are-deep-neural-networks","title":"How Robust are Deep Neural Networks?","date":"2018-04-30","arxiv_id":"1804.11313","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":"scalable-bilinear-learning-using-state-and","title":"Scalable Bilinear $π$ Learning Using State and Action Features","date":"2018-04-27","arxiv_id":"1804.10328","repositories_listed":0,"syntology":null},{"url":null,"slug":"sim-to-real-learning-agile-locomotion-for","title":"Sim-to-Real: Learning Agile Locomotion For Quadruped Robots","date":"2018-04-27","arxiv_id":"1804.10332","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":"generative-temporal-models-with-spatial","title":"Generative Temporal Models with Spatial Memory for Partially Observed Environments","date":"2018-04-25","arxiv_id":"1804.09401","repositories_listed":0,"syntology":null}],"record_sha256":"fa39ed017dbe7baa4ac8b3691134a28dbb6853766140485a7f528541590fe5e3","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}