{"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/77","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":77,"pages_in_order":132,"rows_per_page":100,"rows":[7601,7700],"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/76","next":"/task/reinforcement-learning/papers/78","papers":[{"url":null,"slug":"learning-two-step-hybrid-policy-for-graph-1","title":"Learning Two-Step Hybrid Policy for Graph-Based Interpretable Reinforcement Learning","date":"2022-01-21","arxiv_id":"2201.08520","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-for-personalized-drug","title":"Reinforcement Learning for Personalized Drug Discovery and Design for Complex Diseases: A Systems Pharmacology Perspective","date":"2022-01-21","arxiv_id":"2201.08894","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-your-way-agent","title":"Reinforcement Learning Your Way: Agent Characterization through Policy Regularization","date":"2022-01-21","arxiv_id":"2201.10003","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-prescriptive-dirichlet-power-allocation","title":"A Prescriptive Dirichlet Power Allocation Policy with Deep Reinforcement Learning","date":"2022-01-20","arxiv_id":"2201.08445","repositories_listed":0,"syntology":null},{"url":null,"slug":"recursive-constraints-to-prevent-instability","title":"Recursive Constraints to Prevent Instability in Constrained Reinforcement Learning","date":"2022-01-20","arxiv_id":"2201.07958","repositories_listed":0,"syntology":null},{"url":null,"slug":"resource-allocation-algorithm-for-mec-based","title":"Resource allocation algorithm for MEC based on Deep Reinforcement Learning","date":"2022-01-20","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"safety-awaremulti-agent-apprenticeship","title":"Safety-Aware Multi-Agent Apprenticeship Learning","date":"2022-01-20","arxiv_id":"2201.08111","repositories_listed":0,"syntology":null},{"url":null,"slug":"anytime-optimal-psro-for-two-player-zero-sum","title":"Anytime PSRO for Two-Player Zero-Sum Games","date":"2022-01-19","arxiv_id":"2201.07700","repositories_listed":0,"syntology":null},{"url":null,"slug":"online-poi-recommendation-learning-dynamic","title":"Online POI Recommendation: Learning Dynamic Geo-Human Interactions in Streams","date":"2022-01-19","arxiv_id":"2201.10983","repositories_listed":0,"syntology":null},{"url":null,"slug":"conservative-distributional-reinforcement","title":"Conservative Distributional Reinforcement Learning with Safety Constraints","date":"2022-01-18","arxiv_id":"2201.07286","repositories_listed":0,"syntology":null},{"url":null,"slug":"differentially-private-reinforcement-learning","title":"Differentially Private Reinforcement Learning with Linear Function Approximation","date":"2022-01-18","arxiv_id":"2201.07052","repositories_listed":0,"syntology":null},{"url":null,"slug":"k-nearest-multi-agent-deep-reinforcement","title":"K-nearest Multi-agent Deep Reinforcement Learning for Collaborative Tasks with a Variable Number of Agents","date":"2022-01-18","arxiv_id":"2201.07092","repositories_listed":0,"syntology":null},{"url":null,"slug":"11-summaries-of-papers-on-explainable","title":"11 Summaries of Papers on Explainable Reinforcement Learning With Some Commentary","date":"2022-01-17","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"an-improved-reinforcement-learning-algorithm","title":"An Improved Reinforcement Learning Algorithm for Learning to Branch","date":"2022-01-17","arxiv_id":"2201.06213","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploration-by-random-network-distillation-1","title":"Exploration by Random Network Distillation","date":"2022-01-17","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"implementations-that-matter-in-cooperative","title":"Implementations that Matter in Cooperative Multi-Agent Reinforcement Learning","date":"2022-01-17","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"railway-operation-rescheduling-system-via","title":"Railway Operation Rescheduling System via Dynamic Simulation and Reinforcement Learning","date":"2022-01-17","arxiv_id":"2201.06276","repositories_listed":0,"syntology":null},{"url":null,"slug":"spatiotemporal-costmap-inference-for-mpc-via","title":"Spatiotemporal Costmap Inference for MPC via Deep Inverse Reinforcement Learning","date":"2022-01-17","arxiv_id":"2201.06539","repositories_listed":0,"syntology":null},{"url":null,"slug":"state-of-the-art-of-reinforcement-learning","title":"State of the Art of Reinforcement Learning","date":"2022-01-17","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"a-family-of-cognitively-realistic-parsing","title":"A Family of Cognitively Realistic Parsing Environments for Deep Reinforcement Learning","date":"2022-01-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"conqrr-conversational-query-rewriting-for-1","title":"CONQRR: Conversational Query Rewriting for Retrieval with Reinforcement Learning","date":"2022-01-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"inherently-explainable-reinforcement-learning-1","title":"Inherently Explainable Reinforcement Learning in Natural Language","date":"2022-01-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"jointly-reinforced-user-simulator-and-task","title":"Jointly Reinforced User Simulator and Task-oriented Dialog System with Simplified Generative Architecture","date":"2022-01-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-with-large-action","title":"Reinforcement Learning with Large Action Spaces for Neural Machine Translation","date":"2022-01-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-reinforcement-learning-for-shared","title":"Deep Reinforcement Learning for Shared Autonomous Vehicles (SAV) Fleet Management","date":"2022-01-15","arxiv_id":"2201.05720","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-based-air-combat","title":"Reinforcement Learning based Air Combat Maneuver Generation","date":"2022-01-14","arxiv_id":"2201.05528","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-in-time-varying","title":"Demystifying Reinforcement Learning in Time-Varying Systems","date":"2022-01-14","arxiv_id":"2201.05560","repositories_listed":0,"syntology":null},{"url":null,"slug":"automated-reinforcement-learning-an-overview","title":"Automated Reinforcement Learning: An Overview","date":"2022-01-13","arxiv_id":"2201.05000","repositories_listed":0,"syntology":null},{"url":null,"slug":"criticality-based-varying-step-number","title":"Criticality-Based Varying Step-Number Algorithm for Reinforcement Learning","date":"2022-01-13","arxiv_id":"2201.05034","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-recurrent-reinforcement-learning-crypto","title":"The Recurrent Reinforcement Learning Crypto Agent","date":"2022-01-12","arxiv_id":"2201.04699","repositories_listed":0,"syntology":null},{"url":null,"slug":"active-reinforcement-learning-a-roadmap","title":"Active Reinforcement Learning -- A Roadmap Towards Curious Classifier Systems for Self-Adaptation","date":"2022-01-11","arxiv_id":"2201.03947","repositories_listed":0,"syntology":null},{"url":null,"slug":"automated-reinforcement-learning-autorl-a","title":"Automated Reinforcement Learning (AutoRL): A Survey and Open Problems","date":"2022-01-11","arxiv_id":"2201.03916","repositories_listed":0,"syntology":null},{"url":null,"slug":"benchmarking-deep-reinforcement-learning","title":"Benchmarking Deep Reinforcement Learning Algorithms for Vision-based Robotics","date":"2022-01-11","arxiv_id":"2201.04224","repositories_listed":0,"syntology":null},{"url":null,"slug":"task-independent-capsule-based-agents-for","title":"Task Independent Capsule-Based Agents for Deep Q-Learning","date":"2022-01-11","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"distributed-cooperative-multi-agent","title":"Distributed Cooperative Multi-Agent Reinforcement Learning with Directed Coordination Graph","date":"2022-01-10","arxiv_id":"2201.04962","repositories_listed":0,"syntology":null},{"url":null,"slug":"state-of-the-art-of-user-simulation","title":"State of the Art of User Simulation approaches for conversational information retrieval","date":"2022-01-10","arxiv_id":"2201.03435","repositories_listed":0,"syntology":null},{"url":null,"slug":"assessing-policy-loss-and-planning","title":"Assessing Policy, Loss and Planning Combinations in Reinforcement Learning using a New Modular Architecture","date":"2022-01-08","arxiv_id":"2201.02874","repositories_listed":0,"syntology":null},{"url":null,"slug":"neural-network-optimization-for-reinforcement","title":"Neural Network Optimization for Reinforcement Learning Tasks Using Sparse Computations","date":"2022-01-07","arxiv_id":"2201.02571","repositories_listed":0,"syntology":null},{"url":null,"slug":"offline-reinforcement-learning-for-road","title":"Offline Reinforcement Learning for Road Traffic Control","date":"2022-01-07","arxiv_id":"2201.02381","repositories_listed":0,"syntology":null},{"url":null,"slug":"combining-reinforcement-learning-and-inverse","title":"Combining Reinforcement Learning and Inverse Reinforcement Learning for Asset Allocation Recommendations","date":"2022-01-06","arxiv_id":"2201.01874","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-reinforcement-learning-1","title":"Deep Reinforcement Learning, a textbook","date":"2022-01-04","arxiv_id":"2201.02135","repositories_listed":0,"syntology":null},{"url":null,"slug":"execute-order-66-targeted-data-poisoning-for","title":"Execute Order 66: Targeted Data Poisoning for Reinforcement Learning","date":"2022-01-03","arxiv_id":"2201.00762","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-for-task","title":"Reinforcement Learning for Task Specifications with Action-Constraints","date":"2022-01-02","arxiv_id":"2201.00286","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-surrogate-assisted-controller-for-expensive","title":"A Surrogate-Assisted Controller for Expensive Evolutionary Reinforcement Learning","date":"2022-01-01","arxiv_id":"2201.00129","repositories_listed":0,"syntology":null},{"url":null,"slug":"operator-deep-q-learning-zero-shot-reward","title":"Operator Deep Q-Learning: Zero-Shot Reward Transferring in Reinforcement Learning","date":"2022-01-01","arxiv_id":"2201.00236","repositories_listed":0,"syntology":null},{"url":null,"slug":"importance-of-empirical-sample-complexity","title":"Importance of Empirical Sample Complexity Analysis for Offline Reinforcement Learning","date":"2021-12-31","arxiv_id":"2112.15578","repositories_listed":0,"syntology":null},{"url":null,"slug":"single-shot-pruning-for-offline-reinforcement","title":"Single-Shot Pruning for Offline Reinforcement Learning","date":"2021-12-31","arxiv_id":"2112.15579","repositories_listed":0,"syntology":null},{"url":null,"slug":"stochastic-convex-optimization-for-provably","title":"Stochastic convex optimization for provably efficient apprenticeship learning","date":"2021-12-31","arxiv_id":"2201.00039","repositories_listed":0,"syntology":null},{"url":null,"slug":"using-graph-aware-reinforcement-learning-to","title":"Using Graph-Aware Reinforcement Learning to Identify Winning Strategies in Diplomacy Games (Student Abstract)","date":"2021-12-31","arxiv_id":"2112.15331","repositories_listed":0,"syntology":null},{"url":null,"slug":"reversible-upper-confidence-bound-algorithm","title":"Reversible Upper Confidence Bound Algorithm to Generate Diverse Optimized Candidates","date":"2021-12-30","arxiv_id":"2112.14893","repositories_listed":0,"syntology":null},{"url":null,"slug":"stability-preserving-automatic-tuning-of-pid","title":"Stability-Preserving Automatic Tuning of PID Control with Reinforcement Learning","date":"2021-12-30","arxiv_id":"2112.15187","repositories_listed":0,"syntology":null},{"url":null,"slug":"control-theoretic-analysis-of-temporal","title":"Control Theoretic Analysis of Temporal Difference Learning","date":"2021-12-29","arxiv_id":"2112.14417","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-performance-bounds-for-primal-dual","title":"Efficient Performance Bounds for Primal-Dual Reinforcement Learning from Demonstrations","date":"2021-12-28","arxiv_id":"2112.14004","repositories_listed":0,"syntology":null},{"url":null,"slug":"robustness-and-risk-management-via","title":"Robustness and risk management via distributional dynamic programming","date":"2021-12-28","arxiv_id":"2112.15430","repositories_listed":0,"syntology":null},{"url":null,"slug":"2112-13937","title":"Multiagent Model-based Credit Assignment for Continuous Control","date":"2021-12-27","arxiv_id":"2112.13937","repositories_listed":0,"syntology":null},{"url":null,"slug":"reldec-reinforcement-learning-based-decoding","title":"RELDEC: Reinforcement Learning-Based Decoding of Moderate Length LDPC Codes","date":"2021-12-27","arxiv_id":"2112.13934","repositories_listed":0,"syntology":null},{"url":null,"slug":"safe-reinforcement-learning-with-chance","title":"Safe Reinforcement Learning with Chance-constrained Model Predictive Control","date":"2021-12-27","arxiv_id":"2112.13941","repositories_listed":0,"syntology":null},{"url":null,"slug":"abstractions-of-general-reinforcement","title":"Abstractions of General Reinforcement Learning","date":"2021-12-26","arxiv_id":"2112.13404","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-survey-on-interpretable-reinforcement","title":"A Survey on Interpretable Reinforcement Learning","date":"2021-12-24","arxiv_id":"2112.13112","repositories_listed":0,"syntology":null},{"url":null,"slug":"dynamic-channel-access-via-meta-reinforcement","title":"Dynamic Channel Access via Meta-Reinforcement Learning","date":"2021-12-24","arxiv_id":"2201.09075","repositories_listed":0,"syntology":null},{"url":null,"slug":"rediscovering-affordance-a-reinforcement","title":"Rediscovering Affordance: A Reinforcement Learning Perspective","date":"2021-12-24","arxiv_id":"2112.12886","repositories_listed":0,"syntology":null},{"url":null,"slug":"local-advantage-networks-for-cooperative","title":"Local Advantage Networks for Cooperative Multi-Agent Reinforcement Learning","date":"2021-12-23","arxiv_id":"2112.12458","repositories_listed":0,"syntology":null},{"url":null,"slug":"graph-augmented-deep-reinforcement-learning","title":"Graph augmented Deep Reinforcement Learning in the GameRLand3D environment","date":"2021-12-22","arxiv_id":"2112.11731","repositories_listed":0,"syntology":null},{"url":null,"slug":"do-androids-dream-of-electric-fences-safety-1","title":"Do Androids Dream of Electric Fences? Safety-Aware Reinforcement Learning with Latent Shielding","date":"2021-12-21","arxiv_id":"2112.11490","repositories_listed":0,"syntology":null},{"url":null,"slug":"interpretable-preference-based-reinforcement","title":"Interpretable Preference-based Reinforcement Learning with Tree-Structured Reward Functions","date":"2021-12-20","arxiv_id":"2112.11230","repositories_listed":0,"syntology":null},{"url":null,"slug":"safe-multi-agent-deep-reinforcement-learning","title":"Safe multi-agent deep reinforcement learning for joint bidding and maintenance scheduling of generation units","date":"2021-12-20","arxiv_id":"2112.10459","repositories_listed":0,"syntology":null},{"url":null,"slug":"creativity-of-ai-automatic-symbolic-option","title":"Creativity of AI: Hierarchical Planning Model Learning for Facilitating Deep Reinforcement Learning","date":"2021-12-18","arxiv_id":"2112.09836","repositories_listed":0,"syntology":null},{"url":null,"slug":"contrastive-explanations-for-comparing","title":"Contrastive Explanations for Comparing Preferences of Reinforcement Learning Agents","date":"2021-12-17","arxiv_id":"2112.09462","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-reward-machines-a-study-in-partially","title":"Learning Reward Machines: A Study in Partially Observable Reinforcement Learning","date":"2021-12-17","arxiv_id":"2112.09477","repositories_listed":0,"syntology":null},{"url":null,"slug":"personalized-lane-change-decision-algorithm","title":"Personalized Lane Change Decision Algorithm Using Deep Reinforcement Learning Approach","date":"2021-12-17","arxiv_id":"2112.13646","repositories_listed":0,"syntology":null},{"url":null,"slug":"unsupervised-compressive-text-summarisation","title":"Unsupervised Compressive Text Summarisation with Reinforcement Learning","date":"2021-12-17","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"benchmarking-safe-deep-reinforcement-learning","title":"Benchmarking Safe Deep Reinforcement Learning in Aquatic Navigation","date":"2021-12-16","arxiv_id":"2112.10593","repositories_listed":0,"syntology":null},{"url":null,"slug":"conqrr-conversational-query-rewriting-for","title":"CONQRR: Conversational Query Rewriting for Retrieval with Reinforcement Learning","date":"2021-12-16","arxiv_id":"2112.08558","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-reinforcement-learning-policies-learn","title":"Deep Reinforcement Learning Policies Learn Shared Adversarial Features Across MDPs","date":"2021-12-16","arxiv_id":"2112.09025","repositories_listed":0,"syntology":null},{"url":null,"slug":"automatic-tuning-of-hyper-parameters-of","title":"Automatic tuning of hyper-parameters of reinforcement learning algorithms using Bayesian optimization with behavioral cloning","date":"2021-12-15","arxiv_id":"2112.08094","repositories_listed":0,"syntology":null},{"url":null,"slug":"meta-cpr-generalize-to-unseen-large-number-of","title":"Meta-CPR: Generalize to Unseen Large Number of Agents with Communication Pattern Recognition Module","date":"2021-12-14","arxiv_id":"2112.07222","repositories_listed":0,"syntology":null},{"url":null,"slug":"representation-and-invariance-in","title":"Representation and Invariance in Reinforcement Learning","date":"2021-12-14","arxiv_id":"2112.07752","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-benchmark-for-low-switching-cost","title":"A Benchmark for Low-Switching-Cost Reinforcement Learning","date":"2021-12-13","arxiv_id":"2112.06424","repositories_listed":0,"syntology":null},{"url":null,"slug":"contextual-exploration-using-a-linear","title":"Contextual Exploration Using a Linear Approximation Method Based on Satisficing","date":"2021-12-13","arxiv_id":"2112.06452","repositories_listed":0,"syntology":null},{"url":null,"slug":"teaching-a-robot-to-walk-using-reinforcement","title":"Teaching a Robot to Walk Using Reinforcement Learning","date":"2021-12-13","arxiv_id":"2112.07031","repositories_listed":0,"syntology":null},{"url":null,"slug":"federated-reinforcement-learning-at-the-edge","title":"Federated Reinforcement Learning at the Edge","date":"2021-12-11","arxiv_id":"2112.05908","repositories_listed":0,"syntology":null},{"url":null,"slug":"formalising-the-foundations-of-discrete","title":"Formalising the Foundations of Discrete Reinforcement Learning in Isabelle/HOL","date":"2021-12-11","arxiv_id":"2112.05996","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-validation-tool-for-designing-reinforcement","title":"A Validation Tool for Designing Reinforcement Learning Environments","date":"2021-12-10","arxiv_id":"2112.05519","repositories_listed":0,"syntology":null},{"url":null,"slug":"edge-compatible-reinforcement-learning-for","title":"Edge-Compatible Reinforcement Learning for Recommendations","date":"2021-12-10","arxiv_id":"2112.05812","repositories_listed":0,"syntology":null},{"url":null,"slug":"quantum-architecture-search-via-continual","title":"Quantum Architecture Search via Continual Reinforcement Learning","date":"2021-12-10","arxiv_id":"2112.05779","repositories_listed":0,"syntology":null},{"url":null,"slug":"dr3-value-based-deep-reinforcement-learning-1","title":"DR3: Value-Based Deep Reinforcement Learning Requires Explicit Regularization","date":"2021-12-09","arxiv_id":"2112.04716","repositories_listed":0,"syntology":null},{"url":null,"slug":"high-dimensional-stock-portfolio-trading-with","title":"High-Dimensional Stock Portfolio Trading with Deep Reinforcement Learning","date":"2021-12-09","arxiv_id":"2112.04755","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-with-almost-sure","title":"Reinforcement Learning with Almost Sure Constraints","date":"2021-12-09","arxiv_id":"2112.05198","repositories_listed":0,"syntology":null},{"url":null,"slug":"ambiguous-dynamic-treatment-regimes-a","title":"Ambiguous Dynamic Treatment Regimes: A Reinforcement Learning Approach","date":"2021-12-08","arxiv_id":"2112.04571","repositories_listed":0,"syntology":null},{"url":null,"slug":"application-of-deep-reinforcement-learning-to","title":"Application of Deep Reinforcement Learning to Payment Fraud","date":"2021-12-08","arxiv_id":"2112.04236","repositories_listed":0,"syntology":null},{"url":null,"slug":"comps-continual-meta-policy-search-1","title":"CoMPS: Continual Meta Policy Search","date":"2021-12-08","arxiv_id":"2112.04467","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-to-select-the-next-reasonable","title":"Learning to Select the Next Reasonable Mention for Entity Linking","date":"2021-12-08","arxiv_id":"2112.04104","repositories_listed":0,"syntology":null},{"url":null,"slug":"recent-advances-in-reinforcement-learning-in","title":"Recent Advances in Reinforcement Learning in Finance","date":"2021-12-08","arxiv_id":"2112.04553","repositories_listed":0,"syntology":null},{"url":null,"slug":"first-order-regret-in-reinforcement-learning","title":"First-Order Regret in Reinforcement Learning with Linear Function Approximation: A Robust Estimation Approach","date":"2021-12-07","arxiv_id":"2112.03432","repositories_listed":0,"syntology":null},{"url":null,"slug":"juewu-mc-playing-minecraft-with-sample","title":"JueWu-MC: Playing Minecraft with Sample-efficient Hierarchical Reinforcement Learning","date":"2021-12-07","arxiv_id":"2112.04907","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-differentiable-reinforcement-learning","title":"Deep differentiable reinforcement learning and optimal trading","date":"2021-12-06","arxiv_id":"2112.02944","repositories_listed":0,"syntology":null},{"url":null,"slug":"distilled-domain-randomization","title":"Distilled Domain Randomization","date":"2021-12-06","arxiv_id":"2112.03149","repositories_listed":0,"syntology":null},{"url":null,"slug":"lecture-notes-on-partially-known-mdps","title":"Lecture Notes on Partially Known MDPs","date":"2021-12-06","arxiv_id":"2112.02976","repositories_listed":0,"syntology":null},{"url":null,"slug":"temporal-spatial-causal-interpretations-for","title":"Temporal-Spatial Causal Interpretations for Vision-Based Reinforcement Learning","date":"2021-12-06","arxiv_id":"2112.03020","repositories_listed":0,"syntology":null},{"url":null,"slug":"benchmark-for-out-of-distribution-detection","title":"Benchmark for Out-of-Distribution Detection in Deep Reinforcement Learning","date":"2021-12-05","arxiv_id":"2112.02694","repositories_listed":0,"syntology":null}],"record_sha256":"4ff749200f2fcb0152a01e8bc1e0de5d8d8e9b1561003c6e5680aaef58b21754","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}