{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/reinforcement-learning-2/papers/71","list_of":"/task/reinforcement-learning-2","task":"reinforcement-learning","archive":{"snapshot":"2025-07-28"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"repositories listed in the archive (most first), then date (newest first), then slug","page":71,"pages_in_order":135,"rows_per_page":100,"rows":[7001,7100],"of":13427,"counts":{"archive_papers_tagged":13427,"with_a_code_link":4119,"where_syntology_ran_a_sample":1165,"not_listed_spam_title":0,"listed":13427,"listed_where_code_ran":1165,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":973,"every_run_a_failure_of_syntologys_instrument":192,"listed_with_a_run_with_no_instrument_failure":973,"listed_every_run_a_failure_of_syntologys_instrument":192,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/task/reinforcement-learning-2","prev":"/task/reinforcement-learning-2/papers/70","next":"/task/reinforcement-learning-2/papers/72","papers":[{"url":null,"slug":"enabling-surrogate-assisted-evolutionary","title":"Enabling surrogate-assisted evolutionary reinforcement learning via policy embedding","date":"2023-01-31","arxiv_id":"2301.13374","repositories_listed":0,"syntology":null},{"url":null,"slug":"partitioning-distributed-compute-jobs-with","title":"Partitioning Distributed Compute Jobs with Reinforcement Learning and Graph Neural Networks","date":"2023-01-31","arxiv_id":"2301.13799","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-and-decision-making","title":"Towards interpretable quantum machine learning via single-photon quantum walks","date":"2023-01-31","arxiv_id":"2301.13669","repositories_listed":0,"syntology":null},{"url":null,"slug":"scalable-grid-aware-dynamic-matching-using","title":"Scalable Grid-Aware Dynamic Matching using Deep Reinforcement Learning","date":"2023-01-31","arxiv_id":"2301.13796","repositories_listed":0,"syntology":null},{"url":null,"slug":"scaling-laws-for-single-agent-reinforcement","title":"Scaling laws for single-agent reinforcement learning","date":"2023-01-31","arxiv_id":"2301.13442","repositories_listed":0,"syntology":null},{"url":null,"slug":"scheduling-inference-workloads-on-distributed","title":"Scheduling Inference Workloads on Distributed Edge Clusters with Reinforcement Learning","date":"2023-01-31","arxiv_id":"2301.13618","repositories_listed":0,"syntology":null},{"url":null,"slug":"hierarchical-programmatic-reinforcement","title":"Hierarchical Programmatic Reinforcement Learning via Learning to Compose Programs","date":"2023-01-30","arxiv_id":"2301.12950","repositories_listed":0,"syntology":null},{"url":null,"slug":"improved-regret-for-efficient-online","title":"Improved Regret for Efficient Online Reinforcement Learning with Linear Function Approximation","date":"2023-01-30","arxiv_id":"2301.13087","repositories_listed":0,"syntology":null},{"url":null,"slug":"regret-bounds-for-markov-decision-processes","title":"Regret Bounds for Markov Decision Processes with Recursive Optimized Certainty Equivalents","date":"2023-01-30","arxiv_id":"2301.12601","repositories_listed":0,"syntology":null},{"url":null,"slug":"singularity-aware-reinforcement-learning","title":"STEEL: Singularity-aware Reinforcement Learning","date":"2023-01-30","arxiv_id":"2301.13152","repositories_listed":0,"syntology":null},{"url":null,"slug":"transferring-multiple-policies-to-hotstart","title":"Transferring Multiple Policies to Hotstart Reinforcement Learning in an Air Compressor Management Problem","date":"2023-01-30","arxiv_id":"2301.12820","repositories_listed":0,"syntology":null},{"url":null,"slug":"v2n-service-scaling-with-deep-reinforcement","title":"V2N Service Scaling with Deep Reinforcement Learning","date":"2023-01-30","arxiv_id":"2301.13324","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-deep-reinforcement-learning-framework-for-7","title":"A Deep Reinforcement Learning Framework for Optimizing Congestion Control in Data Centers","date":"2023-01-29","arxiv_id":"2301.12558","repositories_listed":0,"syntology":null},{"url":null,"slug":"autonomous-satellite-docking-via-adaptive","title":"Autonomous Satellite Docking via Adaptive Optimal Output Rregulation: A Reinforcement Learning Approach","date":"2023-01-29","arxiv_id":"2301.12489","repositories_listed":0,"syntology":null},{"url":null,"slug":"sample-efficient-deep-reinforcement-learning-3","title":"Sample Efficient Deep Reinforcement Learning via Local Planning","date":"2023-01-29","arxiv_id":"2301.12579","repositories_listed":0,"syntology":null},{"url":null,"slug":"saformer-a-conditional-sequence-modeling","title":"SaFormer: A Conditional Sequence Modeling Approach to Offline Safe Reinforcement Learning","date":"2023-01-28","arxiv_id":"2301.12203","repositories_listed":0,"syntology":null},{"url":null,"slug":"steering-stein-information-directed","title":"STEERING: Stein Information Directed Exploration for Model-Based Reinforcement Learning","date":"2023-01-28","arxiv_id":"2301.12038","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-learning-rubik-s-cube-with-n-tuple","title":"Towards Learning Rubik's Cube with N-tuple-based Reinforcement Learning","date":"2023-01-28","arxiv_id":"2301.12167","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-memory-efficient-deep-reinforcement","title":"A Memory Efficient Deep Reinforcement Learning Approach For Snake Game Autonomous Agents","date":"2023-01-27","arxiv_id":"2301.11977","repositories_listed":0,"syntology":null},{"url":null,"slug":"behaviour-discriminator-a-simple-data","title":"Improving Behavioural Cloning with Positive Unlabeled Learning","date":"2023-01-27","arxiv_id":"2301.11734","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-deep-reinforcement-learning-for","title":"Exploring Deep Reinforcement Learning for Holistic Smart Building Control","date":"2023-01-27","arxiv_id":"2301.11510","repositories_listed":0,"syntology":null},{"url":null,"slug":"generalized-munchausen-reinforcement-learning","title":"Generalized Munchausen Reinforcement Learning using Tsallis KL Divergence","date":"2023-01-27","arxiv_id":"2301.11476","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-from-diverse-human","title":"Reinforcement Learning from Diverse Human Preferences","date":"2023-01-27","arxiv_id":"2301.11774","repositories_listed":0,"syntology":null},{"url":null,"slug":"single-trajectory-distributionally-robust","title":"Single-Trajectory Distributionally Robust Reinforcement Learning","date":"2023-01-27","arxiv_id":"2301.11721","repositories_listed":0,"syntology":null},{"url":null,"slug":"snerl-semantic-aware-neural-radiance-fields","title":"SNeRL: Semantic-aware Neural Radiance Fields for Reinforcement Learning","date":"2023-01-27","arxiv_id":"2301.11520","repositories_listed":0,"syntology":null},{"url":null,"slug":"solving-constrained-reinforcement-learning","title":"Solving Richly Constrained Reinforcement Learning through State Augmentation and Reward Penalties","date":"2023-01-27","arxiv_id":"2301.11592","repositories_listed":0,"syntology":null},{"url":null,"slug":"collaborative-regret-minimization-in-multi","title":"Communication-Efficient Collaborative Regret Minimization in Multi-Armed Bandits","date":"2023-01-26","arxiv_id":"2301.11442","repositories_listed":0,"syntology":null},{"url":null,"slug":"fedhql-federated-heterogeneous-q-learning","title":"FedHQL: Federated Heterogeneous Q-Learning","date":"2023-01-26","arxiv_id":"2301.11135","repositories_listed":0,"syntology":null},{"url":null,"slug":"model-based-offline-reinforcement-learning-1","title":"Model-based Offline Reinforcement Learning with Local Misspecification","date":"2023-01-26","arxiv_id":"2301.11426","repositories_listed":0,"syntology":null},{"url":null,"slug":"policy-optimization-with-robustness","title":"Certifiably Robust Reinforcement Learning through Model-Based Abstract Interpretation","date":"2023-01-26","arxiv_id":"2301.11374","repositories_listed":0,"syntology":null},{"url":null,"slug":"principled-reinforcement-learning-with-human","title":"Principled Reinforcement Learning with Human Feedback from Pairwise or $K$-wise Comparisons","date":"2023-01-26","arxiv_id":"2301.11270","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-novel-deep-reinforcement-learning-based-2","title":"A Novel Deep Reinforcement Learning-based Approach for Enhancing Spectral Efficiency of IRS-assisted Wireless Systems","date":"2023-01-24","arxiv_id":"2302.14706","repositories_listed":0,"syntology":null},{"url":null,"slug":"asq-it-interactive-explanations-for","title":"ASQ-IT: Interactive Explanations for Reinforcement-Learning Agents","date":"2023-01-24","arxiv_id":"2301.09941","repositories_listed":0,"syntology":null},{"url":null,"slug":"autocost-evolving-intrinsic-cost-for-zero","title":"AutoCost: Evolving Intrinsic Cost for Zero-violation Reinforcement Learning","date":"2023-01-24","arxiv_id":"2301.10339","repositories_listed":0,"syntology":null},{"url":null,"slug":"autonomous-particles","title":"Autonomous particles","date":"2023-01-24","arxiv_id":"2301.10077","repositories_listed":0,"syntology":null},{"url":null,"slug":"explainable-deep-reinforcement-learning-state","title":"Explainable Deep Reinforcement Learning: State of the Art and Challenges","date":"2023-01-24","arxiv_id":"2301.09937","repositories_listed":0,"syntology":null},{"url":null,"slug":"intrinsic-motivation-in-model-based","title":"Intrinsic Motivation in Model-based Reinforcement Learning: A Brief Review","date":"2023-01-24","arxiv_id":"2301.10067","repositories_listed":0,"syntology":null},{"url":null,"slug":"minimal-value-equivalent-partial-models-for","title":"Minimal Value-Equivalent Partial Models for Scalable and Robust Planning in Lifelong Reinforcement Learning","date":"2023-01-24","arxiv_id":"2301.10119","repositories_listed":0,"syntology":null},{"url":null,"slug":"story-shaping-teaching-agents-human-like","title":"Story Shaping: Teaching Agents Human-like Behavior with Stories","date":"2023-01-24","arxiv_id":"2301.10107","repositories_listed":0,"syntology":null},{"url":null,"slug":"stock-trading-optimization-through-model-1","title":"Model Based Reinforcement Learning with Non-Gaussian Environment Dynamics and its Application to Portfolio Optimization","date":"2023-01-23","arxiv_id":"2301.09297","repositories_listed":0,"syntology":null},{"url":null,"slug":"quasi-optimal-learning-with-continuous","title":"Quasi-optimal Reinforcement Learning with Continuous Actions","date":"2023-01-21","arxiv_id":"2301.08940","repositories_listed":0,"syntology":null},{"url":null,"slug":"asynchronous-deep-double-duelling-q-learning","title":"Asynchronous Deep Double Duelling Q-Learning for Trading-Signal Execution in Limit Order Book Markets","date":"2023-01-20","arxiv_id":"2301.08688","repositories_listed":0,"syntology":null},{"url":null,"slug":"energy-efficient-task-offloading-for-semantic","title":"Resource Optimization for Semantic-Aware Networks with Task Offloading","date":"2023-01-20","arxiv_id":"2301.08376","repositories_listed":0,"syntology":null},{"url":null,"slug":"generative-slate-recommendation-with","title":"Generative Slate Recommendation with Reinforcement Learning","date":"2023-01-20","arxiv_id":"2301.08632","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-agent-reinforcement-learning-with-graph-2","title":"Multi-agent Reinforcement Learning with Graph Q-Networks for Antenna Tuning","date":"2023-01-20","arxiv_id":"2302.01199","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-armed-bandits-and-quantum-channel","title":"Multi-Armed Bandits and Quantum Channel Oracles","date":"2023-01-20","arxiv_id":"2301.08544","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-based-estimation-for","title":"Reinforcement learning-based estimation for partial differential equations","date":"2023-01-20","arxiv_id":"2302.01189","repositories_listed":0,"syntology":null},{"url":null,"slug":"revisiting-estimation-bias-in-policy","title":"Revisiting Estimation Bias in Policy Gradients for Deep Reinforcement Learning","date":"2023-01-20","arxiv_id":"2301.08442","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-survey-of-meta-reinforcement-learning","title":"A Survey of Meta-Reinforcement Learning","date":"2023-01-19","arxiv_id":"2301.08028","repositories_listed":0,"syntology":null},{"url":null,"slug":"advanced-scaling-methods-for-vnf-deployment","title":"Advanced Scaling Methods for VNF deployment with Reinforcement Learning","date":"2023-01-19","arxiv_id":"2301.08325","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-reinforcement-learning-for-gas-trading","title":"Domain-adapted Learning and Interpretability: DRL for Gas Trading","date":"2023-01-19","arxiv_id":"2301.08359","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-reinforcement-learning-for-power-trading","title":"Domain-adapted Learning and Imitation: DRL for Power Arbitrage","date":"2023-01-19","arxiv_id":"2301.08360","repositories_listed":0,"syntology":null},{"url":null,"slug":"tight-guarantees-for-interactive-decision","title":"Tight Guarantees for Interactive Decision Making with the Decision-Estimation Coefficient","date":"2023-01-19","arxiv_id":"2301.08215","repositories_listed":0,"syntology":null},{"url":null,"slug":"human-timescale-adaptation-in-an-open-ended","title":"Human-Timescale Adaptation in an Open-Ended Task Space","date":"2023-01-18","arxiv_id":"2301.07608","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-compartment-neuron-and-population","title":"Multi-compartment Neuron and Population Encoding Powered Spiking Neural Network for Deep Distributional Reinforcement Learning","date":"2023-01-18","arxiv_id":"2301.07275","repositories_listed":0,"syntology":null},{"url":null,"slug":"adversarial-robust-deep-reinforcement","title":"Adversarial Robust Deep Reinforcement Learning Requires Redefining Robustness","date":"2023-01-17","arxiv_id":"2301.07487","repositories_listed":0,"syntology":null},{"url":null,"slug":"dqnas-neural-architecture-search-using","title":"DQNAS: Neural Architecture Search using Reinforcement Learning","date":"2023-01-17","arxiv_id":"2301.06687","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-to-solve-arithmetic-problems-with-a","title":"Learning to solve arithmetic problems with a virtual abacus","date":"2023-01-17","arxiv_id":"2301.06870","repositories_listed":0,"syntology":null},{"url":null,"slug":"show-me-what-you-want-inverse-reinforcement","title":"Show me what you want: Inverse reinforcement learning to automatically design robot swarms by demonstration","date":"2023-01-17","arxiv_id":"2301.06864","repositories_listed":0,"syntology":null},{"url":null,"slug":"neuro-symbolic-world-models-for-adapting-to","title":"Neuro-Symbolic World Models for Adapting to Open World Novelty","date":"2023-01-16","arxiv_id":"2301.06294","repositories_listed":0,"syntology":null},{"url":null,"slug":"modeling-human-cognition-with-a-hybrid-deep","title":"CogReact: A Reinforced Framework to Model Human Cognitive Reaction Modulated by Dynamic Intervention","date":"2023-01-15","arxiv_id":"2301.06216","repositories_listed":0,"syntology":null},{"url":null,"slug":"neuro-symbolic-meta-reinforcement-learning","title":"Neuro-symbolic Meta Reinforcement Learning for Trading","date":"2023-01-15","arxiv_id":"2302.08996","repositories_listed":0,"syntology":null},{"url":null,"slug":"first-three-years-of-the-international","title":"First Three Years of the International Verification of Neural Networks Competition (VNN-COMP)","date":"2023-01-14","arxiv_id":"2301.05815","repositories_listed":0,"syntology":null},{"url":null,"slug":"prudex-compass-towards-systematic-evaluation","title":"PRUDEX-Compass: Towards Systematic Evaluation of Reinforcement Learning in Financial Markets","date":"2023-01-14","arxiv_id":"2302.00586","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-for-protocol-synthesis","title":"Reinforcement Learning for Protocol Synthesis in Resource-Constrained Wireless Sensor and IoT Networks","date":"2023-01-14","arxiv_id":"2302.05300","repositories_listed":0,"syntology":null},{"url":null,"slug":"risk-averse-reinforcement-learning-via","title":"Risk-Averse Reinforcement Learning via Dynamic Time-Consistent Risk Measures","date":"2023-01-14","arxiv_id":"2301.05981","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-constrained-optimization-approach-to-the","title":"A Constrained-Optimization Approach to the Execution of Prioritized Stacks of Learned Multi-Robot Tasks","date":"2023-01-13","arxiv_id":"2301.05346","repositories_listed":0,"syntology":null},{"url":null,"slug":"decentralized-model-free-reinforcement","title":"Decentralized model-free reinforcement learning in stochastic games with average-reward objective","date":"2023-01-13","arxiv_id":"2301.05630","repositories_listed":0,"syntology":null},{"url":null,"slug":"hierarchical-deep-q-learning-based-handover","title":"Hierarchical Deep Q-Learning Based Handover in Wireless Networks with Dual Connectivity","date":"2023-01-13","arxiv_id":"2301.05391","repositories_listed":0,"syntology":null},{"url":null,"slug":"risk-sensitive-dead-end-identification-in","title":"Risk Sensitive Dead-end Identification in Safety-Critical Offline Reinforcement Learning","date":"2023-01-13","arxiv_id":"2301.05664","repositories_listed":0,"syntology":null},{"url":null,"slug":"asynchronous-training-of-quantum","title":"Asynchronous training of quantum reinforcement learning","date":"2023-01-12","arxiv_id":"2301.05096","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-based-joint-handover","title":"Reinforcement Learning-based Joint Handover and Beam Tracking in Millimeter-wave Networks","date":"2023-01-12","arxiv_id":"2301.05305","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-analysis-of-quantile-temporal-difference","title":"An Analysis of Quantile Temporal-Difference Learning","date":"2023-01-11","arxiv_id":"2301.04462","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-preference-based-reinforcement","title":"Efficient Preference-Based Reinforcement Learning Using Learned Dynamics Models","date":"2023-01-11","arxiv_id":"2301.04741","repositories_listed":0,"syntology":null},{"url":null,"slug":"sok-adversarial-machine-learning-attacks-and","title":"SoK: Adversarial Machine Learning Attacks and Defences in Multi-Agent Reinforcement Learning","date":"2023-01-11","arxiv_id":"2301.04299","repositories_listed":0,"syntology":null},{"url":null,"slug":"switchable-lightweight-anti-symmetric","title":"Switchable Lightweight Anti-symmetric Processing (SLAP) with CNN Outspeeds Data Augmentation by Smaller Sample -- Application in Gomoku Reinforcement Learning","date":"2023-01-11","arxiv_id":"2301.04746","repositories_listed":0,"syntology":null},{"url":null,"slug":"actor-director-critic-a-novel-deep","title":"Actor-Director-Critic: A Novel Deep Reinforcement Learning Framework","date":"2023-01-10","arxiv_id":"2301.03887","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploration-in-model-based-reinforcement-1","title":"Exploration in Model-based Reinforcement Learning with Randomized Reward","date":"2023-01-09","arxiv_id":"2301.03142","repositories_listed":0,"syntology":null},{"url":null,"slug":"minimax-weight-learning-for-absorbing-mdps","title":"Minimax Weight Learning for Absorbing MDPs","date":"2023-01-09","arxiv_id":"2301.03183","repositories_listed":0,"syntology":null},{"url":null,"slug":"network-slicing-via-transfer-learning-aided","title":"Network Slicing via Transfer Learning aided Distributed Deep Reinforcement Learning","date":"2023-01-09","arxiv_id":"2301.03262","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-enhanced-pichunter-for","title":"Reinforcement Learning Enhanced PicHunter for Interactive Search","date":"2023-01-09","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"tuning-path-tracking-controllers-for","title":"Tuning Path Tracking Controllers for Autonomous Cars Using Reinforcement Learning","date":"2023-01-09","arxiv_id":"2301.03363","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-survey-on-transformers-in-reinforcement","title":"A Survey on Transformers in Reinforcement Learning","date":"2023-01-08","arxiv_id":"2301.03044","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-symbolic-representations-for","title":"Learning Symbolic Representations for Reinforcement Learning of Non-Markovian Behavior","date":"2023-01-08","arxiv_id":"2301.02952","repositories_listed":0,"syntology":null},{"url":null,"slug":"hierarchical-reinforcement-learning-for-ris","title":"Hierarchical Reinforcement Learning for RIS-Assisted Energy-Efficient RAN","date":"2023-01-07","arxiv_id":"2301.02771","repositories_listed":0,"syntology":null},{"url":null,"slug":"laga-a-learning-adaptive-genetic-algorithm","title":"Mathematical Models and Reinforcement Learning based Evolutionary Algorithm Framework for Satellite Scheduling Problem","date":"2023-01-07","arxiv_id":"2301.02764","repositories_listed":0,"syntology":null},{"url":null,"slug":"markov-chain-concentration-with-an","title":"Markov Chain Concentration with an Application in Reinforcement Learning","date":"2023-01-07","arxiv_id":"2301.02926","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-deep-reinforcement-learning-based","title":"A Deep Reinforcement Learning-Based Controller for Magnetorheological-Damped Vehicle Suspension","date":"2023-01-06","arxiv_id":"2301.02714","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-agent-reinforcement-learning-for-fast","title":"Multi-Agent Reinforcement Learning for Fast-Timescale Demand Response of Residential Loads","date":"2023-01-06","arxiv_id":"2301.02593","repositories_listed":0,"syntology":null},{"url":null,"slug":"provable-reset-free-reinforcement-learning-by","title":"Provable Reset-free Reinforcement Learning by No-Regret Reduction","date":"2023-01-06","arxiv_id":"2301.02389","repositories_listed":0,"syntology":null},{"url":null,"slug":"data-driven-inverse-reinforcement-learning","title":"Data-Driven Inverse Reinforcement Learning for Expert-Learner Zero-Sum Games","date":"2023-01-05","arxiv_id":"2301.01997","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-based-air-traffic","title":"Reinforcement Learning-Based Air Traffic Deconfliction","date":"2023-01-05","arxiv_id":"2301.01861","repositories_listed":0,"syntology":null},{"url":null,"slug":"scalable-communication-for-multi-agent","title":"Scalable Communication for Multi-Agent Reinforcement Learning via Transformer-Based Email Mechanism","date":"2023-01-05","arxiv_id":"2301.01919","repositories_listed":0,"syntology":null},{"url":null,"slug":"value-enhancement-of-reinforcement-learning","title":"Value Enhancement of Reinforcement Learning via Efficient and Robust Trust Region Optimization","date":"2023-01-05","arxiv_id":"2301.02220","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-based-mpc-from-big-data-using","title":"Learning-based MPC from Big Data Using Reinforcement Learning","date":"2023-01-04","arxiv_id":"2301.01667","repositories_listed":0,"syntology":null},{"url":null,"slug":"uav-aided-metaverse-over-wireless","title":"UAV aided Metaverse over Wireless Communications: A Reinforcement Learning Approach","date":"2023-01-04","arxiv_id":"2301.01474","repositories_listed":0,"syntology":null},{"url":null,"slug":"contextual-conservative-q-learning-for","title":"Contextual Conservative Q-Learning for Offline Reinforcement Learning","date":"2023-01-03","arxiv_id":"2301.01298","repositories_listed":0,"syntology":null},{"url":null,"slug":"faster-approximate-dynamic-programming-by","title":"Faster Reinforcement Learning by Freezing Slow States","date":"2023-01-03","arxiv_id":"2301.00922","repositories_listed":0,"syntology":null},{"url":null,"slug":"offline-evaluation-for-reinforcement-learning","title":"Offline Evaluation for Reinforcement Learning-based Recommendation: A Critical Issue and Some Alternatives","date":"2023-01-03","arxiv_id":"2301.00993","repositories_listed":0,"syntology":null},{"url":null,"slug":"safe-reinforcement-learning-for-an-energy","title":"Safe Reinforcement Learning for an Energy-Efficient Driver Assistance System","date":"2023-01-03","arxiv_id":"2301.00904","repositories_listed":0,"syntology":null}],"record_sha256":"3611898c093c53df085a5fca5c120c82878cc4f481309bd855b356d610d9a1cf","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}