{"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":"/method/q-learning/papers/4","list_of":"/method/q-learning","method":"Q-Learning","archive":{"snapshot":"2025-07-28"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"date (newest first), then slug","page":4,"pages_in_order":18,"rows_per_page":100,"rows":[301,400],"of":1734,"counts":{"archive_papers_tagged":1734,"with_a_code_link":464,"where_syntology_ran_a_sample":126,"not_listed_spam_title":0,"listed":1734,"listed_where_code_ran":126,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":105,"every_run_a_failure_of_syntologys_instrument":21,"listed_with_a_run_with_no_instrument_failure":105,"listed_every_run_a_failure_of_syntologys_instrument":21,"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":"/method/q-learning","prev":"/method/q-learning/papers/3","next":"/method/q-learning/papers/5","papers":[{"paper":null,"slug":"single-task-continual-offline-reinforcement","title":"Data-Incremental Continual Offline Reinforcement Learning","date":"2024-04-19","arxiv_id":"2404.12639","n_code_links":0,"syntology":null},{"paper":null,"slug":"from-r-to-q-your-language-model-is-secretly-a","title":"From $r$ to $Q^*$: Your Language Model is Secretly a Q-Function","date":"2024-04-18","arxiv_id":"2404.12358","n_code_links":0,"syntology":null},{"paper":null,"slug":"empowering-embodied-visual-tracking-with","title":"Empowering Embodied Visual Tracking with Visual Foundation Models and Offline RL","date":"2024-04-15","arxiv_id":"2404.09857","n_code_links":0,"syntology":null},{"paper":null,"slug":"advancing-forest-fire-prevention-deep","title":"Advancing Forest Fire Prevention: Deep Reinforcement Learning for Effective Firebreak Placement","date":"2024-04-12","arxiv_id":"2404.08523","n_code_links":0,"syntology":null},{"paper":null,"slug":"traffic-signal-control-and-speed-offset","title":"Traffic Signal Control and Speed Offset Coordination Using Q-Learning for Arterial Road Networks","date":"2024-04-09","arxiv_id":"2404.06382","n_code_links":0,"syntology":null},{"paper":null,"slug":"deep-reinforcement-learning-control-for","title":"Deep Reinforcement Learning Control for Disturbance Rejection in a Nonlinear Dynamic System with Parametric Uncertainty","date":"2024-04-06","arxiv_id":"2404.04699","n_code_links":0,"syntology":null},{"paper":null,"slug":"growing-q-networks-solving-continuous-control","title":"Growing Q-Networks: Solving Continuous Control Tasks with Adaptive Control Resolution","date":"2024-04-05","arxiv_id":"2404.04253","n_code_links":0,"syntology":null},{"paper":"/paper/superior-genetic-algorithms-for-the-target","slug":"superior-genetic-algorithms-for-the-target","title":"Superior Genetic Algorithms for the Target Set Selection Problem Based on Power-Law Parameter Choices and Simple Greedy Heuristics","date":"2024-04-05","arxiv_id":"2404.04018","n_code_links":1,"syntology":null},{"paper":"/paper/laser-learning-environment-a-new-environment","slug":"laser-learning-environment-a-new-environment","title":"Laser Learning Environment: A new environment for coordination-critical multi-agent tasks","date":"2024-04-04","arxiv_id":"2404.03596","n_code_links":1,"syntology":null},{"paper":null,"slug":"tuning-for-the-unknown-revisiting-evaluation","title":"K-percent Evaluation for Lifelong RL","date":"2024-04-02","arxiv_id":"2404.02113","n_code_links":0,"syntology":null},{"paper":null,"slug":"utilizing-maximum-mean-discrepancy-barycenter","title":"Utilizing Maximum Mean Discrepancy Barycenter for Propagating the Uncertainty of Value Functions in Reinforcement Learning","date":"2024-03-31","arxiv_id":"2404.00686","n_code_links":0,"syntology":null},{"paper":null,"slug":"encomp-enhanced-covert-maneuver-planning","title":"EnCoMP: Enhanced Covert Maneuver Planning with Adaptive Threat-Aware Visibility Estimation using Offline Reinforcement Learning","date":"2024-03-29","arxiv_id":"2403.20016","n_code_links":0,"syntology":null},{"paper":"/paper/from-two-dimensional-to-three-dimensional-1","slug":"from-two-dimensional-to-three-dimensional-1","title":"From Two-Dimensional to Three-Dimensional Environment with Q-Learning: Modeling Autonomous Navigation with Reinforcement Learning and no Libraries","date":"2024-03-27","arxiv_id":"2403.18219","n_code_links":1,"syntology":null},{"paper":null,"slug":"dasa-delay-adaptive-multi-agent-stochastic","title":"DASA: Delay-Adaptive Multi-Agent Stochastic Approximation","date":"2024-03-25","arxiv_id":"2403.17247","n_code_links":0,"syntology":null},{"paper":null,"slug":"semantic-aware-remote-estimation-of-multiple","title":"Semantic-Aware Remote Estimation of Multiple Markov Sources Under Constraints","date":"2024-03-25","arxiv_id":"2403.16855","n_code_links":0,"syntology":null},{"paper":"/paper/a-fairness-oriented-reinforcement-learning","slug":"a-fairness-oriented-reinforcement-learning","title":"A Fairness-Oriented Reinforcement Learning Approach for the Operation and Control of Shared Micromobility Services","date":"2024-03-23","arxiv_id":"2403.15780","n_code_links":1,"syntology":null},{"paper":null,"slug":"dourn-improving-douzero-by-residual-neural","title":"DouRN: Improving DouZero by Residual Neural Networks","date":"2024-03-21","arxiv_id":"2403.14102","n_code_links":0,"syntology":null},{"paper":null,"slug":"sparse-bayesian-learning-based-hierarchical","title":"Sparse Bayesian Learning-Based Hierarchical Construction for 3D Radio Environment Maps Incorporating Channel Shadowing","date":"2024-03-13","arxiv_id":"2403.08323","n_code_links":0,"syntology":null},{"paper":null,"slug":"strategizing-against-q-learners-a-control","title":"Strategizing against Q-learners: A Control-theoretical Approach","date":"2024-03-13","arxiv_id":"2403.08906","n_code_links":0,"syntology":null},{"paper":null,"slug":"optimal-design-and-implementation-of-an-open","title":"Optimal Design and Implementation of an Open-source Emulation Platform for User-Centric Shared E-mobility Services","date":"2024-03-12","arxiv_id":"2403.07964","n_code_links":0,"syntology":null},{"paper":null,"slug":"finite-time-error-analysis-of-soft-q-learning","title":"Finite-Time Error Analysis of Soft Q-Learning: Switching System Approach","date":"2024-03-11","arxiv_id":"2403.06366","n_code_links":0,"syntology":null},{"paper":"/paper/scalable-online-exploration-via-coverability","slug":"scalable-online-exploration-via-coverability","title":"Scalable Online Exploration via Coverability","date":"2024-03-11","arxiv_id":"2403.06571","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["philip-amortila/l1-coverability"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"algorithmic-collusion-and-price","title":"Algorithmic Collusion and Price Discrimination: The Over-Usage of Data","date":"2024-03-10","arxiv_id":"2403.06150","n_code_links":0,"syntology":null},{"paper":null,"slug":"enhancing-classification-performance-via","title":"Enhancing Classification Performance via Reinforcement Learning for Feature Selection","date":"2024-03-09","arxiv_id":"2403.05979","n_code_links":0,"syntology":null},{"paper":"/paper/comtraq-mpc-meta-trained-dqn-mpc-integration","slug":"comtraq-mpc-meta-trained-dqn-mpc-integration","title":"ComTraQ-MPC: Meta-Trained DQN-MPC Integration for Trajectory Tracking with Limited Active Localization Updates","date":"2024-03-03","arxiv_id":"2403.01564","n_code_links":1,"syntology":null},{"paper":"/paper/efficient-episodic-memory-utilization-of","slug":"efficient-episodic-memory-utilization-of","title":"Efficient Episodic Memory Utilization of Cooperative Multi-Agent Reinforcement Learning","date":"2024-03-02","arxiv_id":"2403.01112","n_code_links":1,"syntology":{"ran":1,"of":4,"n_ran_checked":1,"n_instrument":0,"unverified":3,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","official":{"repos":["hyunghona/emu"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"q-fox-learning-breaking-tradition-in","title":"QF-tuner: Breaking Tradition in Reinforcement Learning","date":"2024-02-26","arxiv_id":"2402.16562","n_code_links":0,"syntology":null},{"paper":null,"slug":"optimizing-portfolio-management-and-risk","title":"Optimizing Portfolio Management and Risk Assessment in Digital Assets Using Deep Learning for Predictive Analysis","date":"2024-02-25","arxiv_id":"2402.15994","n_code_links":0,"syntology":null},{"paper":null,"slug":"computation-offloading-for-multi-server-multi","title":"Computation Offloading for Multi-server Multi-access Edge Vehicular Networks: A DDQN-based Method","date":"2024-02-21","arxiv_id":"2404.07215","n_code_links":0,"syntology":null},{"paper":null,"slug":"an-index-policy-based-on-sarsa-and-q-learning","title":"An Index Policy Based on Sarsa and Q-learning for Heterogeneous Smart Target Tracking","date":"2024-02-19","arxiv_id":"2402.12015","n_code_links":0,"syntology":null},{"paper":null,"slug":"easy-as-abcs-unifying-boltzmann-q-learning","title":"Easy as ABCs: Unifying Boltzmann Q-Learning and Counterfactual Regret Minimization","date":"2024-02-19","arxiv_id":"2402.11835","n_code_links":0,"syntology":null},{"paper":null,"slug":"interference-mitigation-in-leo-constellations","title":"Interference Mitigation in LEO Constellations with Limited Radio Environment Information","date":"2024-02-19","arxiv_id":"2402.12103","n_code_links":0,"syntology":null},{"paper":null,"slug":"reinforcement-learning-to-maximise-wind","title":"Reinforcement learning to maximise wind turbine energy generation","date":"2024-02-17","arxiv_id":"2402.11384","n_code_links":0,"syntology":null},{"paper":null,"slug":"enhancing-courier-scheduling-in-crowdsourced","title":"Enhancing Courier Scheduling in Crowdsourced Last-Mile Delivery through Dynamic Shift Extensions: A Deep Reinforcement Learning Approach","date":"2024-02-15","arxiv_id":"2402.09961","n_code_links":0,"syntology":null},{"paper":null,"slug":"exploiting-estimation-bias-in-deep-double-q","title":"Exploiting Estimation Bias in Clipped Double Q-Learning for Continous Control Reinforcement Learning Tasks","date":"2024-02-14","arxiv_id":"2402.09078","n_code_links":0,"syntology":null},{"paper":"/paper/conservative-and-risk-aware-offline-multi","slug":"conservative-and-risk-aware-offline-multi","title":"Conservative and Risk-Aware Offline Multi-Agent Reinforcement Learning","date":"2024-02-13","arxiv_id":"2402.08421","n_code_links":1,"syntology":{"ran":2,"of":3,"n_ran_checked":2,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["eslam211/conservative-and-distributional-marl"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"enhanced-deep-q-learning-for-2d-self-driving","title":"Enhanced Deep Q-Learning for 2D Self-Driving Cars: Implementation and Evaluation on a Custom Track Environment","date":"2024-02-13","arxiv_id":"2402.08780","n_code_links":0,"syntology":null},{"paper":null,"slug":"intelligent-agricultural-management","title":"Intelligent Agricultural Management Considering N$_2$O Emission and Climate Variability with Uncertainties","date":"2024-02-13","arxiv_id":"2402.08832","n_code_links":0,"syntology":null},{"paper":"/paper/leveraging-digital-cousins-for-ensemble-q","slug":"leveraging-digital-cousins-for-ensemble-q","title":"Leveraging Digital Cousins for Ensemble Q-Learning in Large-Scale Wireless Networks","date":"2024-02-12","arxiv_id":"2402.08022","n_code_links":1,"syntology":null},{"paper":null,"slug":"orient-a-priority-aware-energy-efficient","title":"ORIENT: A Priority-Aware Energy-Efficient Approach for Latency-Sensitive Applications in 6G","date":"2024-02-10","arxiv_id":"2402.06931","n_code_links":0,"syntology":null},{"paper":"/paper/solving-deep-reinforcement-learning","slug":"solving-deep-reinforcement-learning","title":"Solving Deep Reinforcement Learning Tasks with Evolution Strategies and Linear Policy Networks","date":"2024-02-10","arxiv_id":"2402.06912","n_code_links":1,"syntology":null},{"paper":null,"slug":"rleegnet-integrating-brain-computer","title":"RLEEGNet: Integrating Brain-Computer Interfaces with Adaptive AI for Intuitive Responsiveness and High-Accuracy Motor Imagery Classification","date":"2024-02-09","arxiv_id":"2402.09465","n_code_links":0,"syntology":null},{"paper":null,"slug":"value-function-interference-and-greedy-action","title":"Value function interference and greedy action selection in value-based multi-objective reinforcement learning","date":"2024-02-09","arxiv_id":"2402.06266","n_code_links":0,"syntology":null},{"paper":null,"slug":"enhancement-of-high-definition-map-update","title":"Enhancement of High-definition Map Update Service Through Coverage-aware and Reinforcement Learning","date":"2024-02-08","arxiv_id":"2402.14582","n_code_links":0,"syntology":null},{"paper":null,"slug":"federated-offline-reinforcement-learning-1","title":"Federated Offline Reinforcement Learning: Collaborative Single-Policy Coverage Suffices","date":"2024-02-08","arxiv_id":"2402.05876","n_code_links":0,"syntology":null},{"paper":"/paper/improving-token-based-world-models-with","slug":"improving-token-based-world-models-with","title":"Improving Token-Based World Models with Parallel Observation Prediction","date":"2024-02-08","arxiv_id":"2402.05643","n_code_links":1,"syntology":{"ran":8,"of":9,"n_ran_checked":8,"n_instrument":0,"unverified":1,"pointer_only":9,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["leor-c/rem"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/multi-timescale-ensemble-q-learning-for","slug":"multi-timescale-ensemble-q-learning-for","title":"Multi-Timescale Ensemble Q-learning for Markov Decision Process Policy Optimization","date":"2024-02-08","arxiv_id":"2402.05476","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-deep-reinforcement-learning-approach-for-17","title":"A Deep Reinforcement Learning Approach for Adaptive Traffic Routing in Next-gen Networks","date":"2024-02-07","arxiv_id":"2402.04515","n_code_links":0,"syntology":null},{"paper":"/paper/compound-returns-reduce-variance-in","slug":"compound-returns-reduce-variance-in","title":"Averaging $n$-step Returns Reduces Variance in Reinforcement Learning","date":"2024-02-06","arxiv_id":"2402.03903","n_code_links":0,"syntology":{"ran":5,"of":8,"n_ran_checked":4,"n_instrument":1,"unverified":3,"pointer_only":6,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","official":null}},{"paper":"/paper/logical-specifications-guided-dynamic-task","slug":"logical-specifications-guided-dynamic-task","title":"Logical Specifications-guided Dynamic Task Sampling for Reinforcement Learning Agents","date":"2024-02-06","arxiv_id":"2402.03678","n_code_links":1,"syntology":null},{"paper":null,"slug":"diffusion-world-model","title":"Diffusion World Model: Future Modeling Beyond Step-by-Step Rollout for Offline Reinforcement Learning","date":"2024-02-05","arxiv_id":"2402.03570","n_code_links":0,"syntology":null},{"paper":"/paper/hyperagent-a-simple-scalable-efficient-and","slug":"hyperagent-a-simple-scalable-efficient-and","title":"Q-Star Meets Scalable Posterior Sampling: Bridging Theory and Practice via HyperAgent","date":"2024-02-05","arxiv_id":"2402.10228","n_code_links":3,"syntology":{"ran":3,"of":7,"n_ran_checked":3,"n_instrument":0,"unverified":4,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","official":{"repos":["szrlee/hyperagent"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"drl-based-dynamic-channel-access-and-sclar","title":"DRL-Based Dynamic Channel Access and SCLAR Maximization for Networks Under Jamming","date":"2024-02-02","arxiv_id":"2402.01574","n_code_links":0,"syntology":null},{"paper":null,"slug":"deep-robot-sketching-an-application-of-deep-q","title":"Deep Robot Sketching: An application of Deep Q-Learning Networks for human-like sketching","date":"2024-02-01","arxiv_id":"2402.00676","n_code_links":0,"syntology":null},{"paper":null,"slug":"fm3q-factorized-multi-agent-minimax-q","title":"FM3Q: Factorized Multi-Agent MiniMax Q-Learning for Two-Team Zero-Sum Markov Game","date":"2024-02-01","arxiv_id":"2402.00738","n_code_links":0,"syntology":null},{"paper":"/paper/raddqn-a-deep-q-learning-based-architecture","slug":"raddqn-a-deep-q-learning-based-architecture","title":"RadDQN: a Deep Q Learning-based Architecture for Finding Time-efficient Minimum Radiation Exposure Pathway","date":"2024-02-01","arxiv_id":"2402.00468","n_code_links":1,"syntology":null},{"paper":null,"slug":"extrinsicaly-rewarded-soft-q-imitation","title":"Extrinsicaly Rewarded Soft Q Imitation Learning with Discriminator","date":"2024-01-30","arxiv_id":"2401.16772","n_code_links":0,"syntology":null},{"paper":"/paper/a-comparison-of-rl-based-and-pid-controllers","slug":"a-comparison-of-rl-based-and-pid-controllers","title":"A comparison of RL-based and PID controllers for 6-DOF swimming robots: hybrid underwater object tracking","date":"2024-01-29","arxiv_id":"2401.16618","n_code_links":1,"syntology":null},{"paper":null,"slug":"emergence-of-cooperation-under-punishment-a","title":"Emergence of cooperation under punishment: A reinforcement learning perspective","date":"2024-01-29","arxiv_id":"2401.16073","n_code_links":0,"syntology":null},{"paper":null,"slug":"regularized-q-learning-with-linear-function","title":"Regularized Q-Learning with Linear Function Approximation","date":"2024-01-26","arxiv_id":"2401.15196","n_code_links":0,"syntology":null},{"paper":null,"slug":"constant-stepsize-q-learning-distributional","title":"Constant Stepsize Q-learning: Distributional Convergence, Bias and Extrapolation","date":"2024-01-25","arxiv_id":"2401.13884","n_code_links":0,"syntology":null},{"paper":null,"slug":"multi-agent-deep-reinforcement-learning-for-15","title":"Tacit algorithmic collusion in deep reinforcement learning guided price competition: A study using EV charge pricing game","date":"2024-01-25","arxiv_id":"2401.15108","n_code_links":0,"syntology":null},{"paper":"/paper/vqc-based-reinforcement-learning-with-data-re","slug":"vqc-based-reinforcement-learning-with-data-re","title":"VQC-Based Reinforcement Learning with Data Re-uploading: Performance and Trainability","date":"2024-01-21","arxiv_id":"2401.11555","n_code_links":1,"syntology":null},{"paper":"/paper/attention-based-cnn-bilstm-for-sleep-state","slug":"attention-based-cnn-bilstm-for-sleep-state","title":"Attention-Based CNN-BiLSTM for Sleep State Classification of Spatiotemporal Wide-Field Calcium Imaging Data","date":"2024-01-16","arxiv_id":"2401.08098","n_code_links":1,"syntology":null},{"paper":null,"slug":"revalued-regularised-ensemble-value","title":"REValueD: Regularised Ensemble Value-Decomposition for Factorisable Markov Decision Processes","date":"2024-01-16","arxiv_id":"2401.08850","n_code_links":0,"syntology":null},{"paper":"/paper/a-semantic-aware-multiple-access-scheme-for","slug":"a-semantic-aware-multiple-access-scheme-for","title":"A Semantic-Aware Multiple Access Scheme for Distributed, Dynamic 6G-Based Applications","date":"2024-01-12","arxiv_id":"2401.06308","n_code_links":1,"syntology":null},{"paper":null,"slug":"graph-q-learning-for-combinatorial","title":"Graph Q-Learning for Combinatorial Optimization","date":"2024-01-11","arxiv_id":"2401.05610","n_code_links":0,"syntology":null},{"paper":null,"slug":"model-free-reinforcement-learning-for-4","title":"Model-Free Reinforcement Learning for Automated Fluid Administration in Critical Care","date":"2024-01-11","arxiv_id":"2401.06299","n_code_links":0,"syntology":null},{"paper":null,"slug":"deep-reinforcement-multi-agent-learning","title":"Deep Reinforcement Multi-agent Learning framework for Information Gathering with Local Gaussian Processes for Water Monitoring","date":"2024-01-09","arxiv_id":"2401.04631","n_code_links":0,"syntology":null},{"paper":null,"slug":"inverse-like-antagonistic-scene-text-spotting","title":"Inverse-like Antagonistic Scene Text Spotting via Reading-Order Estimation and Dynamic Sampling","date":"2024-01-08","arxiv_id":"2401.03637","n_code_links":0,"syntology":null},{"paper":null,"slug":"an-empirical-investigation-of-value-based","title":"An Empirical Investigation of Value-Based Multi-objective Reinforcement Learning for Stochastic Environments","date":"2024-01-06","arxiv_id":"2401.03163","n_code_links":0,"syntology":null},{"paper":null,"slug":"semi-supervised-learning-via-dqn-for-log","title":"Semi-supervised learning via DQN for log anomaly detection","date":"2024-01-06","arxiv_id":"2401.03151","n_code_links":0,"syntology":null},{"paper":"/paper/spqr-controlling-q-ensemble-independence-with-1","slug":"spqr-controlling-q-ensemble-independence-with-1","title":"SPQR: Controlling Q-ensemble Independence with Spiked Random Model for Reinforcement Learning","date":"2024-01-06","arxiv_id":"2401.03137","n_code_links":1,"syntology":{"ran":2,"of":5,"n_ran_checked":0,"n_instrument":2,"unverified":3,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","official":{"repos":["dohyeoklee/SPQR"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"a-deep-q-learning-based-smart-scheduling-of","title":"A Deep Q-Learning based Smart Scheduling of EVs for Demand Response in Smart Grids","date":"2024-01-05","arxiv_id":"2401.02653","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-best-time-for-an-update-risk-sensitive","title":"The Best Time for an Update: Risk-Sensitive Minimization of Age-Based Metrics","date":"2024-01-03","arxiv_id":"2401.10265","n_code_links":0,"syntology":null},{"paper":null,"slug":"dynamic-decision-making-in-engineering-system","title":"Dynamic Decision Making in Engineering System Design: A Deep Q-Learning Approach","date":"2023-12-28","arxiv_id":"2312.17284","n_code_links":0,"syntology":null},{"paper":null,"slug":"reinforcement-learning-for-safe-occupancy","title":"Reinforcement Learning for Safe Occupancy Strategies in Educational Spaces during an Epidemic","date":"2023-12-23","arxiv_id":"2312.15163","n_code_links":0,"syntology":null},{"paper":null,"slug":"federated-q-learning-linear-regret-speedup","title":"Federated Q-Learning: Linear Regret Speedup with Low Communication Cost","date":"2023-12-22","arxiv_id":"2312.15023","n_code_links":0,"syntology":null},{"paper":null,"slug":"optimal-coordination-in-minority-game-a","title":"Optimal coordination of resources: A solution from reinforcement learning","date":"2023-12-20","arxiv_id":"2312.14970","n_code_links":0,"syntology":null},{"paper":"/paper/investigating-the-performance-and-reliability","slug":"investigating-the-performance-and-reliability","title":"Investigating the Performance and Reliability, of the Q-Learning Algorithm in Various Unknown Environments","date":"2023-12-19","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/modeling-non-linear-effects-with-neural","slug":"modeling-non-linear-effects-with-neural","title":"Modeling non-linear Effects with Neural Networks in Relational Event Models","date":"2023-12-19","arxiv_id":"2312.12357","n_code_links":1,"syntology":null},{"paper":"/paper/sample-efficient-reinforcement-learning-with-4","slug":"sample-efficient-reinforcement-learning-with-4","title":"Sample Efficient Reinforcement Learning with Partial Dynamics Knowledge","date":"2023-12-19","arxiv_id":"2312.12558","n_code_links":1,"syntology":null},{"paper":null,"slug":"stability-of-multi-agent-learning-in","title":"Stability of Multi-Agent Learning in Competitive Networks: Delaying the Onset of Chaos","date":"2023-12-19","arxiv_id":"2312.11943","n_code_links":0,"syntology":null},{"paper":null,"slug":"deep-dispatch-a-deep-reinforcement-learning","title":"Deep-Dispatch: A Deep Reinforcement Learning-Based Vehicle Dispatch Algorithm for Advanced Air Mobility","date":"2023-12-17","arxiv_id":"2312.10809","n_code_links":0,"syntology":null},{"paper":null,"slug":"on-designing-multi-uav-aided-wireless-powered","title":"On Designing Multi-UAV aided Wireless Powered Dynamic Communication via Hierarchical Deep Reinforcement Learning","date":"2023-12-13","arxiv_id":"2312.07917","n_code_links":0,"syntology":null},{"paper":"/paper/the-effective-horizon-explains-deep-rl","slug":"the-effective-horizon-explains-deep-rl","title":"The Effective Horizon Explains Deep RL Performance in Stochastic Environments","date":"2023-12-13","arxiv_id":"2312.08369","n_code_links":1,"syntology":null},{"paper":null,"slug":"enhanced-q-learning-approach-to-finite-time","title":"Enhanced Q-Learning Approach to Finite-Time Reachability with Maximum Probability for Probabilistic Boolean Control Networks","date":"2023-12-12","arxiv_id":"2312.06904","n_code_links":0,"syntology":null},{"paper":"/paper/i-open-at-the-close-a-deep-reinforcement","slug":"i-open-at-the-close-a-deep-reinforcement","title":"I Open at the Close: A Deep Reinforcement Learning Evaluation of Open Streets Initiatives","date":"2023-12-12","arxiv_id":"2312.07680","n_code_links":1,"syntology":null},{"paper":"/paper/efficient-sparse-reward-goal-conditioned","slug":"efficient-sparse-reward-goal-conditioned","title":"Efficient Sparse-Reward Goal-Conditioned Reinforcement Learning with a High Replay Ratio and Regularization","date":"2023-12-10","arxiv_id":"2312.05787","n_code_links":1,"syntology":null},{"paper":"/paper/synthesis-of-temporally-robust-policies-for","slug":"synthesis-of-temporally-robust-policies-for","title":"Synthesis of Temporally-Robust Policies for Signal Temporal Logic Tasks using Reinforcement Learning","date":"2023-12-10","arxiv_id":"2312.05764","n_code_links":1,"syntology":null},{"paper":"/paper/multi-agent-reinforcement-learning-via-1","slug":"multi-agent-reinforcement-learning-via-1","title":"Multi-Agent Reinforcement Learning via Distributed MPC as a Function Approximator","date":"2023-12-08","arxiv_id":"2312.05166","n_code_links":1,"syntology":null},{"paper":"/paper/optimizing-distributed-reinforcement-learning","slug":"optimizing-distributed-reinforcement-learning","title":"Efficient Parallel Reinforcement Learning Framework using the Reactor Model","date":"2023-12-07","arxiv_id":"2312.04704","n_code_links":1,"syntology":null},{"paper":null,"slug":"an-efficient-data-based-off-policy-q-learning","title":"An efficient data-based off-policy Q-learning algorithm for optimal output feedback control of linear systems","date":"2023-12-06","arxiv_id":"2312.03451","n_code_links":0,"syntology":null},{"paper":null,"slug":"wake-sleep-consolidated-learning","title":"Wake-Sleep Consolidated Learning","date":"2023-12-06","arxiv_id":"2401.08623","n_code_links":0,"syntology":null},{"paper":null,"slug":"lights-out-training-rl-agents-robust-to","title":"Lights out: training RL agents robust to temporary blindness","date":"2023-12-05","arxiv_id":"2312.02665","n_code_links":0,"syntology":null},{"paper":null,"slug":"provable-reinforcement-learning-for-networked","title":"Provable Reinforcement Learning for Networked Control Systems with Stochastic Packet Disordering","date":"2023-12-05","arxiv_id":"2312.02498","n_code_links":0,"syntology":null},{"paper":null,"slug":"spontaneous-coupling-of-q-learning-algorithms","title":"Algorithmic collusion under competitive design","date":"2023-12-05","arxiv_id":"2312.02644","n_code_links":0,"syntology":null},{"paper":"/paper/adsorbrl-deep-multi-objective-reinforcement","slug":"adsorbrl-deep-multi-objective-reinforcement","title":"AdsorbRL: Deep Multi-Objective Reinforcement Learning for Inverse Catalysts Design","date":"2023-12-04","arxiv_id":"2312.02308","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["rlacombe/adsorbrl"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"anomaly-detection-via-learning-based","title":"Anomaly Detection via Learning-Based Sequential Controlled Sensing","date":"2023-11-30","arxiv_id":"2312.00088","n_code_links":0,"syntology":null},{"paper":null,"slug":"data-efficient-deep-reinforcement-learning-2","title":"Data-efficient Deep Reinforcement Learning for Vehicle Trajectory Control","date":"2023-11-30","arxiv_id":"2311.18393","n_code_links":0,"syntology":null}],"record_sha256":"05560d54e49d44760a63c155b08a2f6d2b24a3c2a84c93cd6703161aa200711b","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}