{"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/130","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":130,"pages_in_order":132,"rows_per_page":100,"rows":[12901,13000],"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/129","next":"/task/reinforcement-learning/papers/131","papers":[{"url":null,"slug":"on-the-convergence-of-cycle-detection-for","title":"On the convergence of cycle detection for navigational reinforcement learning","date":"2015-11-27","arxiv_id":"1511.08724","repositories_listed":0,"syntology":null},{"url":null,"slug":"incremental-truncated-lstd","title":"Incremental Truncated LSTD","date":"2015-11-26","arxiv_id":"1511.08495","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-vision-based-deep-reinforcement","title":"Towards Vision-Based Deep Reinforcement Learning for Robotic Motion Control","date":"2015-11-12","arxiv_id":"1511.03791","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-unfair-trading-a-market-manipulation","title":"Learning Unfair Trading: a Market Manipulation Analysis From the Reinforcement Learning Perspective","date":"2015-11-02","arxiv_id":"1511.00740","repositories_listed":0,"syntology":null},{"url":null,"slug":"generating-text-with-deep-reinforcement","title":"Generating Text with Deep Reinforcement Learning","date":"2015-10-30","arxiv_id":"1510.09202","repositories_listed":0,"syntology":null},{"url":null,"slug":"sample-complexity-of-episodic-fixed-horizon","title":"Sample Complexity of Episodic Fixed-Horizon Reinforcement Learning","date":"2015-10-29","arxiv_id":"1510.08906","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-the-computability-of-aixi","title":"On the Computability of AIXI","date":"2015-10-19","arxiv_id":"1510.05572","repositories_listed":0,"syntology":null},{"url":null,"slug":"dual-control-for-approximate-bayesian","title":"Dual Control for Approximate Bayesian Reinforcement Learning","date":"2015-10-13","arxiv_id":"1510.03591","repositories_listed":0,"syntology":null},{"url":null,"slug":"data-efficient-learning-of-feedback-policies","title":"Data-Efficient Learning of Feedback Policies from Image Pixels using Deep Dynamical Models","date":"2015-10-08","arxiv_id":"1510.02173","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-empowerment","title":"Efficient Empowerment","date":"2015-09-28","arxiv_id":"1509.08455","repositories_listed":0,"syntology":null},{"url":null,"slug":"model-based-reinforcement-learning-with","title":"Model-based Reinforcement Learning with Parametrized Physical Models and Optimism-Driven Exploration","date":"2015-09-23","arxiv_id":"1509.06824","repositories_listed":0,"syntology":null},{"url":null,"slug":"one-shot-learning-of-manipulation-skills-with","title":"One-Shot Learning of Manipulation Skills with Online Dynamics Adaptation and Neural Network Priors","date":"2015-09-23","arxiv_id":"1509.06841","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-deep-control-policies-for-autonomous","title":"Learning Deep Control Policies for Autonomous Aerial Vehicles with MPC-Guided Policy Search","date":"2015-09-22","arxiv_id":"1509.06791","repositories_listed":0,"syntology":null},{"url":null,"slug":"benchmarking-for-bayesian-reinforcement","title":"Benchmarking for Bayesian Reinforcement Learning","date":"2015-09-14","arxiv_id":"1509.04064","repositories_listed":0,"syntology":null},{"url":null,"slug":"optimization-of-anemia-treatment-in","title":"Optimization of anemia treatment in hemodialysis patients via reinforcement learning","date":"2015-09-14","arxiv_id":"1509.03977","repositories_listed":0,"syntology":null},{"url":null,"slug":"compatible-value-gradients-for-reinforcement","title":"Compatible Value Gradients for Reinforcement Learning of Continuous Deep Policies","date":"2015-09-10","arxiv_id":"1509.03005","repositories_listed":0,"syntology":null},{"url":null,"slug":"recurrent-reinforcement-learning-a-hybrid","title":"Recurrent Reinforcement Learning: A Hybrid Approach","date":"2015-09-10","arxiv_id":"1509.03044","repositories_listed":0,"syntology":null},{"url":null,"slug":"hyper-parameter-optimisation-of-gaussian","title":"Hyper-parameter Optimisation of Gaussian Process Reinforcement Learning for Statistical Dialogue Management","date":"2015-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"optimising-turn-taking-strategies-with","title":"Optimising Turn-Taking Strategies With Reinforcement Learning","date":"2015-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-in-multi-party-trading","title":"Reinforcement Learning in Multi-Party Trading Dialog","date":"2015-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-of-multi-issue","title":"Reinforcement Learning of Multi-Issue Negotiation Dialogue Policies","date":"2015-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"a-cognitive-architecture-based-on-a-learning","title":"A Cognitive Architecture Based on a Learning Classifier System with Spiking Classifiers","date":"2015-08-31","arxiv_id":"1508.07700","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-efficient-representations-for","title":"Learning Efficient Representations for Reinforcement Learning","date":"2015-08-28","arxiv_id":"1509.02413","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-agent-reinforcement-learning-with-1","title":"Multi-agent Reinforcement Learning with Sparse Interactions by Negotiation and Knowledge Transfer","date":"2015-08-21","arxiv_id":"1508.05328","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-to-predict-independent-of-span","title":"Learning to Predict Independent of Span","date":"2015-08-19","arxiv_id":"1508.04582","repositories_listed":0,"syntology":null},{"url":null,"slug":"distributed-deep-q-learning","title":"Distributed Deep Q-Learning","date":"2015-08-18","arxiv_id":"1508.04186","repositories_listed":0,"syntology":null},{"url":null,"slug":"reward-shaping-with-recurrent-neural-networks-1","title":"Reward Shaping with Recurrent Neural Networks for Speeding up On-Line Policy Learning in Spoken Dialogue Systems","date":"2015-08-14","arxiv_id":"1508.03391","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-from-real-users-rating-dialogue","title":"Learning from Real Users: Rating Dialogue Success with Neural Networks for Reinforcement Learning in Spoken Dialogue Systems","date":"2015-08-13","arxiv_id":"1508.03386","repositories_listed":0,"syntology":null},{"url":null,"slug":"episodic-multi-armed-bandits","title":"Episodic Multi-armed Bandits","date":"2015-08-04","arxiv_id":"1508.00641","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-reinforcement-learning-approach-to-online","title":"A Reinforcement Learning Approach to Online Learning of Decision Trees","date":"2015-07-24","arxiv_id":"1507.06923","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-for-the-unit","title":"Reinforcement Learning for the Unit Commitment Problem","date":"2015-07-19","arxiv_id":"1507.05268","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-the-computability-of-solomonoff-induction","title":"On the Computability of Solomonoff Induction and Knowledge-Seeking","date":"2015-07-15","arxiv_id":"1507.04124","repositories_listed":0,"syntology":null},{"url":null,"slug":"experimental-analysis-of-data-driven-control","title":"Experimental analysis of data-driven control for a building heating system","date":"2015-07-13","arxiv_id":"1507.03638","repositories_listed":0,"syntology":null},{"url":null,"slug":"online-transfer-learning-in-reinforcement","title":"Online Transfer Learning in Reinforcement Learning Domains","date":"2015-07-02","arxiv_id":"1507.00436","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-empirical-evaluation-of-true-online-td","title":"An Empirical Evaluation of True Online TD(λ)","date":"2015-07-01","arxiv_id":"1507.00353","repositories_listed":0,"syntology":null},{"url":null,"slug":"bootstrapped-thompson-sampling-and-deep","title":"Bootstrapped Thompson Sampling and Deep Exploration","date":"2015-07-01","arxiv_id":"1507.00300","repositories_listed":0,"syntology":null},{"url":null,"slug":"online-learning-to-sample","title":"Online Learning to Sample","date":"2015-06-30","arxiv_id":"1506.09016","repositories_listed":0,"syntology":null},{"url":null,"slug":"bootstrapping-skills","title":"Bootstrapping Skills","date":"2015-06-11","arxiv_id":"1506.03624","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-online-coupon-collector-problem-and-its","title":"The Online Coupon-Collector Problem and Its Application to Lifelong Reinforcement Learning","date":"2015-06-10","arxiv_id":"1506.03379","repositories_listed":0,"syntology":null},{"url":null,"slug":"cumulative-prospect-theory-meets","title":"Cumulative Prospect Theory Meets Reinforcement Learning: Prediction and Control","date":"2015-06-08","arxiv_id":"1506.02632","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-framework-for-constrained-and-adaptive","title":"A Framework for Constrained and Adaptive Behavior-Based Agents","date":"2015-06-07","arxiv_id":"1506.02312","repositories_listed":0,"syntology":null},{"url":null,"slug":"local-nonstationarity-for-efficient-bayesian","title":"Local Nonstationarity for Efficient Bayesian Optimization","date":"2015-06-05","arxiv_id":"1506.02080","repositories_listed":0,"syntology":null},{"url":null,"slug":"safe-policy-search-for-lifelong-reinforcement","title":"Safe Policy Search for Lifelong Reinforcement Learning with Sublinear Regret","date":"2015-05-21","arxiv_id":"1505.05798","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-definition-of-happiness-for-reinforcement","title":"A Definition of Happiness for Reinforcement Learning Agents","date":"2015-05-18","arxiv_id":"1505.04497","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-applied-to-single","title":"Reinforcement Learning applied to Single Neuron","date":"2015-05-15","arxiv_id":"1505.04150","repositories_listed":0,"syntology":null},{"url":null,"slug":"context-aware-mobility-management-in-hetnets","title":"Context-Aware Mobility Management in HetNets: A Reinforcement Learning Approach","date":"2015-05-07","arxiv_id":"1505.01625","repositories_listed":0,"syntology":null},{"url":null,"slug":"optimal-neuron-selection-nk-echo-state","title":"Optimal Neuron Selection: NK Echo State Networks for Reinforcement Learning","date":"2015-05-07","arxiv_id":"1505.01887","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforced-decision-trees","title":"Reinforced Decision Trees","date":"2015-05-05","arxiv_id":"1505.00908","repositories_listed":0,"syntology":null},{"url":null,"slug":"using-pca-to-efficiently-represent-state","title":"Using PCA to Efficiently Represent State Spaces","date":"2015-05-02","arxiv_id":"1505.00322","repositories_listed":0,"syntology":null},{"url":null,"slug":"stability-of-stochastic-approximations-with","title":"Stability of Stochastic Approximations with `Controlled Markov' Noise and Temporal Difference Learning","date":"2015-04-23","arxiv_id":"1504.06043","repositories_listed":0,"syntology":null},{"url":null,"slug":"optimal-nudging-solving-average-reward-semi","title":"Optimal Nudging: Solving Average-Reward Semi-Markov Decision Processes as a Minimal Sequence of Cumulative Tasks","date":"2015-04-20","arxiv_id":"1504.05122","repositories_listed":0,"syntology":null},{"url":null,"slug":"projective-simulation-with-generalization","title":"Projective simulation with generalization","date":"2015-04-09","arxiv_id":"1504.02247","repositories_listed":0,"syntology":null},{"url":null,"slug":"autonomous-crm-control-via-clv-approximation","title":"Autonomous CRM Control via CLV Approximation with Deep Reinforcement Learning in Discrete and Continuous Action Space","date":"2015-04-08","arxiv_id":"1504.01840","repositories_listed":0,"syntology":null},{"url":null,"slug":"residential-demand-response-applications","title":"Residential Demand Response Applications Using Batch Reinforcement Learning","date":"2015-04-08","arxiv_id":"1504.02125","repositories_listed":0,"syntology":null},{"url":null,"slug":"end-to-end-training-of-deep-visuomotor","title":"End-to-End Training of Deep Visuomotor Policies","date":"2015-04-02","arxiv_id":"1504.00702","repositories_listed":0,"syntology":null},{"url":null,"slug":"universal-psychometrics-tasks-difficulty","title":"Universal Psychometrics Tasks: difficulty, composition and decomposition","date":"2015-03-26","arxiv_id":"1503.07587","repositories_listed":0,"syntology":null},{"url":null,"slug":"correct-by-synthesis-reinforcement-learning","title":"Correct-by-synthesis reinforcement learning with temporal logic constraints","date":"2015-03-05","arxiv_id":"1503.01793","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-in-a-neurally","title":"Reinforcement Learning in a Neurally Controlled Robot Using Dopamine Modulated STDP","date":"2015-02-21","arxiv_id":"1502.06096","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-biologically-plausible-deep-learning","title":"Towards Biologically Plausible Deep Learning","date":"2015-02-14","arxiv_id":"1502.04156","repositories_listed":0,"syntology":null},{"url":null,"slug":"policy-gradient-for-coherent-risk-measures","title":"Policy Gradient for Coherent Risk Measures","date":"2015-02-13","arxiv_id":"1502.03919","repositories_listed":0,"syntology":null},{"url":null,"slug":"off-policy-reward-shaping-with-ensembles","title":"Off-Policy Reward Shaping with Ensembles","date":"2015-02-11","arxiv_id":"1502.03248","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-model-based-reinforcement-learning","title":"Efficient model-based reinforcement learning for approximate online optimal","date":"2015-02-09","arxiv_id":"1502.02609","repositories_listed":0,"syntology":null},{"url":null,"slug":"from-pixels-to-torques-policy-learning-with","title":"From Pixels to Torques: Policy Learning with Deep Dynamical Models","date":"2015-02-08","arxiv_id":"1502.02251","repositories_listed":0,"syntology":null},{"url":null,"slug":"implicit-temporal-differences","title":"Implicit Temporal Differences","date":"2014-12-21","arxiv_id":"1412.6734","repositories_listed":0,"syntology":null},{"url":null,"slug":"grounding-hierarchical-reinforcement-learning","title":"Grounding Hierarchical Reinforcement Learning Models for Knowledge Transfer","date":"2014-12-19","arxiv_id":"1412.6451","repositories_listed":0,"syntology":null},{"url":null,"slug":"regression-with-linear-factored-functions","title":"Regression with Linear Factored Functions","date":"2014-12-19","arxiv_id":"1412.6286","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-and-nonparametric","title":"Reinforcement Learning and Nonparametric Detection of Game-Theoretic Equilibrium Play in Social Networks","date":"2014-12-11","arxiv_id":"1501.01209","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-learning-for-real-time-atari-game-play","title":"Deep Learning for Real-Time Atari Game Play Using Offline Monte-Carlo Tree Search Planning","date":"2014-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"design-principles-of-the-hippocampal","title":"Design Principles of the Hippocampal Cognitive Map","date":"2014-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"difference-of-convex-functions-programming-1","title":"Difference of Convex Functions Programming for Reinforcement Learning","date":"2014-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"game-theoretical-control-with-continuous","title":"Game-theoretical control with continuous action sets","date":"2014-12-01","arxiv_id":"1412.0543","repositories_listed":0,"syntology":null},{"url":null,"slug":"how-hard-is-my-mdp-the-distribution-norm-to","title":"How hard is my MDP?\" The distribution-norm to the rescue\"","date":"2014-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"raam-the-benefits-of-robustness-in","title":"RAAM: The Benefits of Robustness in Approximating Aggregated MDPs in Reinforcement Learning","date":"2014-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"sparse-multi-task-reinforcement-learning","title":"Sparse Multi-Task Reinforcement Learning","date":"2014-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"weighted-importance-sampling-for-off-policy","title":"Weighted importance sampling for off-policy learning with linear function approximation","date":"2014-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"multiple-instance-reinforcement-learning-for","title":"Multiple Instance Reinforcement Learning for Efficient Weakly-Supervised Detection in Images","date":"2014-11-29","arxiv_id":"1412.0100","repositories_listed":0,"syntology":null},{"url":null,"slug":"compress-and-control","title":"Compress and Control","date":"2014-11-19","arxiv_id":"1411.5326","repositories_listed":0,"syntology":null},{"url":null,"slug":"jamming-bandits","title":"Jamming Bandits","date":"2014-11-13","arxiv_id":"1411.3652","repositories_listed":0,"syntology":null},{"url":null,"slug":"approachability-in-stackelberg-stochastic","title":"Approachability in Stackelberg Stochastic Games with Vector Costs","date":"2014-11-03","arxiv_id":"1411.0728","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-comparison-of-learning-algorithms-on-the","title":"A Comparison of learning algorithms on the Arcade Learning Environment","date":"2014-10-31","arxiv_id":"1410.8620","repositories_listed":0,"syntology":null},{"url":null,"slug":"do-artificial-reinforcement-learning-agents","title":"Do Artificial Reinforcement-Learning Agents Matter Morally?","date":"2014-10-30","arxiv_id":"1410.8233","repositories_listed":0,"syntology":null},{"url":null,"slug":"where-do-goals-come-from-a-generic-approach","title":"Where do goals come from? A Generic Approach to Autonomous Goal-System Development","date":"2014-10-21","arxiv_id":"1410.5557","repositories_listed":0,"syntology":null},{"url":null,"slug":"domain-independent-optimistic-initialization","title":"Domain-Independent Optimistic Initialization for Reinforcement Learning","date":"2014-10-16","arxiv_id":"1410.4604","repositories_listed":0,"syntology":null},{"url":null,"slug":"q-learning-for-optimal-control-of-continuous","title":"Q-learning for Optimal Control of Continuous-time Systems","date":"2014-10-11","arxiv_id":"1410.2954","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-sequential-neural-network","title":"Deep Sequential Neural Network","date":"2014-10-02","arxiv_id":"1410.0510","repositories_listed":0,"syntology":null},{"url":null,"slug":"dont-until-the-final-verb-wait-reinforcement","title":"Don't Until the Final Verb Wait: Reinforcement Learning for Simultaneous Machine Translation","date":"2014-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"fear-the-reaper-a-system-for-automatic-multi","title":"Fear the REAPER: A System for Automatic Multi-Document Summarization with Reinforcement Learning","date":"2014-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"an-agent-driven-semantical-identifier-using","title":"An agent-driven semantical identifier using radial basis neural networks and reinforcement learning","date":"2014-09-30","arxiv_id":"1409.8484","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-advantage-of-cross-entropy-over-entropy","title":"The Advantage of Cross Entropy over Entropy in Iterative Information Gathering","date":"2014-09-26","arxiv_id":"1409.7552","repositories_listed":0,"syntology":null},{"url":null,"slug":"inverse-reinforcement-learning-with-multi","title":"Inverse Reinforcement Learning with Multi-Relational Chains for Robot-Centered Smart Home","date":"2014-08-16","arxiv_id":"1408.3727","repositories_listed":0,"syntology":null},{"url":null,"slug":"r-ucb-a-contextual-bandit-algorithm-for-risk","title":"R-UCB: a Contextual Bandit Algorithm for Risk-Aware Recommender Systems","date":"2014-08-10","arxiv_id":"1408.2195","repositories_listed":0,"syntology":null},{"url":null,"slug":"probabilistic-inverse-reinforcement-learning","title":"Probabilistic inverse reinforcement learning in unknown environments","date":"2014-08-09","arxiv_id":"1408.2067","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-to-cooperate-via-policy-search","title":"Learning to Cooperate via Policy Search","date":"2014-08-07","arxiv_id":"1408.1484","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-of-cooperative","title":"Reinforcement Learning of Cooperative Persuasive Dialogue Policies using Framing","date":"2014-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"moneybarl-exploiting-pitcher-decision-making","title":"MONEYBaRL: Exploiting pitcher decision-making using Reinforcement Learning","date":"2014-07-31","arxiv_id":"1407.8392","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-in-games-via-reinforcement-and","title":"Learning in games via reinforcement and regularization","date":"2014-07-23","arxiv_id":"1407.6267","repositories_listed":0,"syntology":null},{"url":null,"slug":"practical-kernel-based-reinforcement-learning","title":"Practical Kernel-Based Reinforcement Learning","date":"2014-07-21","arxiv_id":"1407.5358","repositories_listed":0,"syntology":null},{"url":null,"slug":"extreme-state-aggregation-beyond-mdps","title":"Extreme State Aggregation Beyond MDPs","date":"2014-07-12","arxiv_id":"1407.3341","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-based-algorithm-for","title":"Reinforcement Learning Based Algorithm for the Maximization of EV Charging Station Revenue","date":"2014-07-04","arxiv_id":"1407.1291","repositories_listed":0,"syntology":null},{"url":null,"slug":"classification-based-approximate-policy","title":"Classification-based Approximate Policy Iteration: Experiments and Extended Discussions","date":"2014-07-02","arxiv_id":"1407.0449","repositories_listed":0,"syntology":null}],"record_sha256":"f8b7c0df4a7d6bbd23c4833411cf22136b04785cc6534ecbfd94ec37647adc2e","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}