{"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/50","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":50,"pages_in_order":132,"rows_per_page":100,"rows":[4901,5000],"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/49","next":"/task/reinforcement-learning/papers/51","papers":[{"url":null,"slug":"video-to-video-generative-adversarial-network","title":"Video to Video Generative Adversarial Network for Few-shot Learning Based on Policy Gradient","date":"2024-10-28","arxiv_id":"2410.20657","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-diversity-based-experience-replay","title":"Efficient Diversity-based Experience Replay for Deep Reinforcement Learning","date":"2024-10-27","arxiv_id":"2410.20487","repositories_listed":0,"syntology":null},{"url":null,"slug":"overcoming-the-sim-to-real-gap-leveraging","title":"Overcoming the Sim-to-Real Gap: Leveraging Simulation to Learn to Explore for Real-World RL","date":"2024-10-26","arxiv_id":"2410.20254","repositories_listed":0,"syntology":null},{"url":null,"slug":"uncertainty-penalized-direct-preference","title":"Uncertainty-Penalized Direct Preference Optimization","date":"2024-10-26","arxiv_id":"2410.20187","repositories_listed":0,"syntology":null},{"url":null,"slug":"evolving-choice-hysteresis-in-reinforcement","title":"Evolving choice hysteresis in reinforcement learning: comparing the adaptive value of positivity bias and gradual perseveration","date":"2024-10-25","arxiv_id":"2410.19434","repositories_listed":0,"syntology":null},{"url":null,"slug":"miles-making-imitation-learning-easy-with","title":"MILES: Making Imitation Learning Easy with Self-Supervision","date":"2024-10-25","arxiv_id":"2410.19693","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-agent-reinforcement-learning-with-9","title":"Multi-Agent Reinforcement Learning with Selective State-Space Models","date":"2024-10-25","arxiv_id":"2410.19382","repositories_listed":0,"syntology":null},{"url":null,"slug":"offline-to-online-multi-agent-reinforcement","title":"Offline-to-Online Multi-Agent Reinforcement Learning with Offline Value Function Memory and Sequential Exploration","date":"2024-10-25","arxiv_id":"2410.19450","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-robot-reinforcement-learning-with-goal","title":"On-Robot Reinforcement Learning with Goal-Contrastive Rewards","date":"2024-10-25","arxiv_id":"2410.19989","repositories_listed":0,"syntology":null},{"url":null,"slug":"provably-adaptive-average-reward","title":"Provably Adaptive Average Reward Reinforcement Learning for Metric Spaces","date":"2024-10-25","arxiv_id":"2410.19919","repositories_listed":0,"syntology":null},{"url":null,"slug":"sad-state-action-distillation-for-in-context","title":"Random Policy Enables In-Context Reinforcement Learning within Trust Horizons","date":"2024-10-25","arxiv_id":"2410.19982","repositories_listed":0,"syntology":null},{"url":null,"slug":"pointpatchrl-masked-reconstruction-improves","title":"PointPatchRL -- Masked Reconstruction Improves Reinforcement Learning on Point Clouds","date":"2024-10-24","arxiv_id":"2410.18800","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-the-chromatic","title":"Reinforcement Learning the Chromatic Symmetric Function","date":"2024-10-24","arxiv_id":"2410.19189","repositories_listed":0,"syntology":null},{"url":null,"slug":"samg-state-action-aware-offline-to-online","title":"SAMG: State-Action-Aware Offline-to-Online Reinforcement Learning with Offline Model Guidance","date":"2024-10-24","arxiv_id":"2410.18626","repositories_listed":0,"syntology":null},{"url":null,"slug":"bridging-swarm-intelligence-and-reinforcement","title":"The Hive Mind is a Single Reinforcement Learning Agent","date":"2024-10-23","arxiv_id":"2410.17517","repositories_listed":0,"syntology":null},{"url":null,"slug":"multimodal-information-bottleneck-for-deep","title":"Multimodal Information Bottleneck for Deep Reinforcement Learning with Multiple Sensors","date":"2024-10-23","arxiv_id":"2410.17551","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-under-latent-dynamics","title":"Reinforcement Learning under Latent Dynamics: Toward Statistical and Algorithmic Modularity","date":"2024-10-23","arxiv_id":"2410.17904","repositories_listed":0,"syntology":null},{"url":null,"slug":"spire-synergistic-planning-imitation-and","title":"SPIRE: Synergistic Planning, Imitation, and Reinforcement Learning for Long-Horizon Manipulation","date":"2024-10-23","arxiv_id":"2410.18065","repositories_listed":0,"syntology":null},{"url":null,"slug":"drop-distributional-and-regular-optimism-and","title":"DROP: Distributional and Regular Optimism and Pessimism for Reinforcement Learning","date":"2024-10-22","arxiv_id":"2410.17473","repositories_listed":0,"syntology":null},{"url":null,"slug":"episodic-future-thinking-mechanism-for-multi","title":"Episodic Future Thinking Mechanism for Multi-agent Reinforcement Learning","date":"2024-10-22","arxiv_id":"2410.17373","repositories_listed":0,"syntology":null},{"url":null,"slug":"few-shot-in-context-preference-learning-using","title":"Large Language Models are In-context Preference Learners","date":"2024-10-22","arxiv_id":"2410.17233","repositories_listed":0,"syntology":null},{"url":null,"slug":"hierarchical-multi-agent-reinforcement-2","title":"Hierarchical Multi-agent Reinforcement Learning for Cyber Network Defense","date":"2024-10-22","arxiv_id":"2410.17351","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-modal-transformer-and-reinforcement","title":"Multi-Modal Transformer and Reinforcement Learning-based Beam Management","date":"2024-10-22","arxiv_id":"2410.19859","repositories_listed":0,"syntology":null},{"url":null,"slug":"quasinav-asymmetric-cost-aware-navigation","title":"QuasiNav: Asymmetric Cost-Aware Navigation Planning with Constrained Quasimetric Reinforcement Learning","date":"2024-10-22","arxiv_id":"2410.16666","repositories_listed":0,"syntology":null},{"url":null,"slug":"sample-efficient-curriculum-reinforcement","title":"Curriculum Reinforcement Learning for Complex Reward Functions","date":"2024-10-22","arxiv_id":"2410.16790","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-plug-and-play-fully-on-the-job-real-time","title":"A Plug-and-Play Fully On-the-Job Real-Time Reinforcement Learning Algorithm for a Direct-Drive Tandem-Wing Experiment Platforms Under Multiple Random Operating Conditions","date":"2024-10-21","arxiv_id":"2410.15554","repositories_listed":0,"syntology":null},{"url":null,"slug":"advancements-in-electric-vehicle-charging","title":"Advancements in Electric Vehicle Charging Optimization: A Survey of Reinforcement Learning Approaches","date":"2024-10-21","arxiv_id":"2410.16425","repositories_listed":0,"syntology":null},{"url":null,"slug":"attentionpainter-an-efficient-and-adaptive","title":"AttentionPainter: An Efficient and Adaptive Stroke Predictor for Scene Painting","date":"2024-10-21","arxiv_id":"2410.16418","repositories_listed":0,"syntology":null},{"url":null,"slug":"offline-reinforcement-learning-for-job-shop","title":"Offline reinforcement learning for job-shop scheduling problems","date":"2024-10-21","arxiv_id":"2410.15714","repositories_listed":0,"syntology":null},{"url":null,"slug":"rgmdt-return-gap-minimizing-decision-tree","title":"RGMDT: Return-Gap-Minimizing Decision Tree Extraction in Non-Euclidean Metric Space","date":"2024-10-21","arxiv_id":"2410.16517","repositories_listed":0,"syntology":null},{"url":null,"slug":"understanding-and-alleviating-memory","title":"Understanding and Alleviating Memory Consumption in RLHF for LLMs","date":"2024-10-21","arxiv_id":"2410.15651","repositories_listed":0,"syntology":null},{"url":null,"slug":"assemblycomplete-3d-combinatorial","title":"AssemblyComplete: 3D Combinatorial Construction with Deep Reinforcement Learning","date":"2024-10-20","arxiv_id":"2410.15469","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-novel-reinforcement-learning-model-for-post","title":"A Novel Reinforcement Learning Model for Post-Incident Malware Investigations","date":"2024-10-19","arxiv_id":"2410.15028","repositories_listed":0,"syntology":null},{"url":null,"slug":"gnnrl-smoothing-a-prior-free-reinforcement","title":"GNNRL-Smoothing: A Prior-Free Reinforcement Learning Model for Mesh Smoothing","date":"2024-10-19","arxiv_id":"2410.19834","repositories_listed":0,"syntology":null},{"url":null,"slug":"hierarchical-reinforced-trader-hrt-a-bi-level","title":"Hierarchical Reinforced Trader (HRT): A Bi-Level Approach for Optimizing Stock Selection and Execution","date":"2024-10-19","arxiv_id":"2410.14927","repositories_listed":0,"syntology":null},{"url":null,"slug":"semantic-information-g-theory-for-range","title":"Semantic Information G Theory for Range Control with Tradeoff between Purposiveness and Efficiency","date":"2024-10-19","arxiv_id":"2411.05789","repositories_listed":0,"syntology":null},{"url":null,"slug":"harnessing-causality-in-reinforcement","title":"Harnessing Causality in Reinforcement Learning With Bagged Decision Times","date":"2024-10-18","arxiv_id":"2410.14659","repositories_listed":0,"syntology":null},{"url":null,"slug":"interpretable-end-to-end-neurosymbolic","title":"Interpretable end-to-end Neurosymbolic Reinforcement Learning agents","date":"2024-10-18","arxiv_id":"2410.14371","repositories_listed":0,"syntology":null},{"url":null,"slug":"inverse-reinforcement-learning-from-non","title":"Inverse Reinforcement Learning from Non-Stationary Learning Agents","date":"2024-10-18","arxiv_id":"2410.14135","repositories_listed":0,"syntology":null},{"url":null,"slug":"online-reinforcement-learning-with-passive","title":"Online Reinforcement Learning with Passive Memory","date":"2024-10-18","arxiv_id":"2410.14665","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-in-non-markov-market","title":"Reinforcement Learning in Non-Markov Market-Making","date":"2024-10-18","arxiv_id":"2410.14504","repositories_listed":0,"syntology":null},{"url":null,"slug":"transfer-reinforcement-learning-in","title":"Transfer Reinforcement Learning in Heterogeneous Action Spaces using Subgoal Mapping","date":"2024-10-18","arxiv_id":"2410.14484","repositories_listed":0,"syntology":null},{"url":null,"slug":"utilizing-large-language-models-for-event","title":"Utilizing Large Language Models for Event Deconstruction to Enhance Multimodal Aspect-Based Sentiment Analysis","date":"2024-10-18","arxiv_id":"2410.14150","repositories_listed":0,"syntology":null},{"url":null,"slug":"adversarial-inception-for-bounded-backdoor","title":"Adversarial Inception Backdoor Attacks against Reinforcement Learning","date":"2024-10-17","arxiv_id":"2410.13995","repositories_listed":0,"syntology":null},{"url":null,"slug":"approximating-auction-equilibria-with","title":"Approximating Auction Equilibria with Reinforcement Learning","date":"2024-10-17","arxiv_id":"2410.13960","repositories_listed":0,"syntology":null},{"url":null,"slug":"guided-reinforcement-learning-for-robust","title":"Guided Reinforcement Learning for Robust Multi-Contact Loco-Manipulation","date":"2024-10-17","arxiv_id":"2410.13817","repositories_listed":0,"syntology":null},{"url":null,"slug":"is-prior-free-black-box-non-stationary","title":"Is Prior-Free Black-Box Non-Stationary Reinforcement Learning Feasible?","date":"2024-10-17","arxiv_id":"2410.13772","repositories_listed":0,"syntology":null},{"url":null,"slug":"rethinking-optimal-transport-in-offline","title":"Rethinking Optimal Transport in Offline Reinforcement Learning","date":"2024-10-17","arxiv_id":"2410.14069","repositories_listed":0,"syntology":null},{"url":null,"slug":"dynamic-learning-rate-for-deep-reinforcement","title":"Dynamic Learning Rate for Deep Reinforcement Learning: A Bandit Approach","date":"2024-10-16","arxiv_id":"2410.12598","repositories_listed":0,"syntology":null},{"url":null,"slug":"gan-based-top-down-view-synthesis-in","title":"GAN Based Top-Down View Synthesis in Reinforcement Learning Environments","date":"2024-10-16","arxiv_id":"2410.12372","repositories_listed":0,"syntology":null},{"url":null,"slug":"insights-from-the-inverse-reconstructing-llm","title":"Insights from the Inverse: Reconstructing LLM Training Goals Through Inverse RL","date":"2024-10-16","arxiv_id":"2410.12491","repositories_listed":0,"syntology":null},{"url":null,"slug":"spectrum-sharing-using-deep-reinforcement","title":"Spectrum Sharing using Deep Reinforcement Learning in Vehicular Networks","date":"2024-10-16","arxiv_id":"2410.12521","repositories_listed":0,"syntology":null},{"url":null,"slug":"advanced-persistent-threats-apt-attribution","title":"Advanced Persistent Threats (APT) Attribution Using Deep Reinforcement Learning","date":"2024-10-15","arxiv_id":"2410.11463","repositories_listed":0,"syntology":null},{"url":null,"slug":"disentangled-unsupervised-skill-discovery-for","title":"Disentangled Unsupervised Skill Discovery for Efficient Hierarchical Reinforcement Learning","date":"2024-10-15","arxiv_id":"2410.11251","repositories_listed":0,"syntology":null},{"url":null,"slug":"dodt-enhanced-online-decision-transformer","title":"DODT: Enhanced Online Decision Transformer Learning through Dreamer's Actor-Critic Trajectory Forecasting","date":"2024-10-15","arxiv_id":"2410.11359","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-objective-reinforcement-learning-a-tool","title":"Multi-objective Reinforcement Learning: A Tool for Pluralistic Alignment","date":"2024-10-15","arxiv_id":"2410.11221","repositories_listed":0,"syntology":null},{"url":null,"slug":"physical-informed-inspired-deep-reinforcement","title":"Physical Informed-Inspired Deep Reinforcement Learning Based Bi-Level Programming for Microgrid Scheduling","date":"2024-10-15","arxiv_id":"2410.11932","repositories_listed":0,"syntology":null},{"url":null,"slug":"solving-the-dynamic-volatility-fitting","title":"Solving The Dynamic Volatility Fitting Problem: A Deep Reinforcement Learning Approach","date":"2024-10-15","arxiv_id":"2410.11789","repositories_listed":0,"syntology":null},{"url":"/paper/action-gaps-and-advantages-in-continuous-time","slug":"action-gaps-and-advantages-in-continuous-time","title":"Action Gaps and Advantages in Continuous-Time Distributional Reinforcement Learning","date":"2024-10-14","arxiv_id":"2410.11022","repositories_listed":0,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_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) · 0 unverified","sample_list":"/paper/action-gaps-and-advantages-in-continuous-time#ran","syntology_url":"https://syntology.ai/paper/2410.11022","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.11022"}},"official":null}},{"url":null,"slug":"burning-red-unlocking-subtask-driven","title":"Burning RED: Unlocking Subtask-Driven Reinforcement Learning and Risk-Awareness in Average-Reward Markov Decision Processes","date":"2024-10-14","arxiv_id":"2410.10578","repositories_listed":0,"syntology":null},{"url":null,"slug":"compositional-shielding-and-reinforcement","title":"Compositional Shielding and Reinforcement Learning for Multi-Agent Systems","date":"2024-10-14","arxiv_id":"2410.10460","repositories_listed":0,"syntology":null},{"url":null,"slug":"diversity-aware-reinforcement-learning-for-de","title":"Diversity-Aware Reinforcement Learning for de novo Drug Design","date":"2024-10-14","arxiv_id":"2410.10431","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-robustness-in-deep-reinforcement","title":"Enhancing Robustness in Deep Reinforcement Learning: A Lyapunov Exponent Approach","date":"2024-10-14","arxiv_id":"2410.10674","repositories_listed":0,"syntology":null},{"url":null,"slug":"qe-ebm-using-quality-estimators-as-energy","title":"QE-EBM: Using Quality Estimators as Energy Loss for Machine Translation","date":"2024-10-14","arxiv_id":"2410.10228","repositories_listed":0,"syntology":null},{"url":null,"slug":"meta-reinforcement-learning-with-universal","title":"Meta-Reinforcement Learning with Universal Policy Adaptation: Provable Near-Optimality under All-task Optimum Comparator","date":"2024-10-13","arxiv_id":"2410.09728","repositories_listed":0,"syntology":null},{"url":null,"slug":"actsafe-active-exploration-with-safety","title":"ActSafe: Active Exploration with Safety Constraints for Reinforcement Learning","date":"2024-10-12","arxiv_id":"2410.09486","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-in-hyperbolic-spaces","title":"Reinforcement Learning in Hyperbolic Spaces: Models and Experiments","date":"2024-10-12","arxiv_id":"2410.09466","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-a-domain-specific-modelling","title":"Towards a Domain-Specific Modelling Environment for Reinforcement Learning","date":"2024-10-12","arxiv_id":"2410.09368","repositories_listed":0,"syntology":null},{"url":null,"slug":"hierarchical-universal-value-function","title":"Hierarchical Universal Value Function Approximators","date":"2024-10-11","arxiv_id":"2410.08997","repositories_listed":0,"syntology":null},{"url":null,"slug":"sold-reinforcement-learning-with-slot-object","title":"SOLD: Slot Object-Centric Latent Dynamics Models for Relational Manipulation Learning from Pixels","date":"2024-10-11","arxiv_id":"2410.08822","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-reinforcement-learning-with-large","title":"Efficient Reinforcement Learning with Large Language Model Priors","date":"2024-10-10","arxiv_id":"2410.07927","repositories_listed":0,"syntology":null},{"url":null,"slug":"neuroplastic-expansion-in-deep-reinforcement","title":"Neuroplastic Expansion in Deep Reinforcement Learning","date":"2024-10-10","arxiv_id":"2410.07994","repositories_listed":0,"syntology":null},{"url":null,"slug":"offline-hierarchical-reinforcement-learning","title":"Offline Hierarchical Reinforcement Learning via Inverse Optimization","date":"2024-10-10","arxiv_id":"2410.07933","repositories_listed":0,"syntology":null},{"url":null,"slug":"offline-inverse-constrained-reinforcement","title":"Offline Inverse Constrained Reinforcement Learning for Safe-Critical Decision Making in Healthcare","date":"2024-10-10","arxiv_id":"2410.07525","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-the-grid-sampling-limit-sde","title":"On the grid-sampling limit SDE","date":"2024-10-10","arxiv_id":"2410.07778","repositories_listed":0,"syntology":null},{"url":null,"slug":"probabilistic-satisfaction-of-temporal-logic","title":"Probabilistic Satisfaction of Temporal Logic Constraints in Reinforcement Learning via Adaptive Policy-Switching","date":"2024-10-10","arxiv_id":"2410.08022","repositories_listed":0,"syntology":null},{"url":null,"slug":"rethinking-adversarial-inverse-reinforcement-1","title":"On Reward Transferability in Adversarial Inverse Reinforcement Learning: Insights from Random Matrix Theory","date":"2024-10-10","arxiv_id":"2410.07643","repositories_listed":0,"syntology":null},{"url":null,"slug":"fostering-intrinsic-motivation-in","title":"Fostering Intrinsic Motivation in Reinforcement Learning with Pretrained Foundation Models","date":"2024-10-09","arxiv_id":"2410.07404","repositories_listed":0,"syntology":null},{"url":null,"slug":"honesty-to-subterfuge-in-context","title":"Honesty to Subterfuge: In-Context Reinforcement Learning Can Make Honest Models Reward Hack","date":"2024-10-09","arxiv_id":"2410.06491","repositories_listed":0,"syntology":null},{"url":null,"slug":"motionrl-align-text-to-motion-generation-to","title":"MotionRL: Align Text-to-Motion Generation to Human Preferences with Multi-Reward Reinforcement Learning","date":"2024-10-09","arxiv_id":"2410.06513","repositories_listed":0,"syntology":null},{"url":null,"slug":"reindiffuse-crafting-physically-plausible","title":"ReinDiffuse: Crafting Physically Plausible Motions with Reinforced Diffusion Model","date":"2024-10-09","arxiv_id":"2410.07296","repositories_listed":0,"syntology":null},{"url":null,"slug":"transfer-learning-for-a-class-of-cascade","title":"Transfer Learning for a Class of Cascade Dynamical Systems","date":"2024-10-09","arxiv_id":"2410.06828","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-policy-evaluation-with-safety","title":"Efficient Policy Evaluation with Safety Constraint for Reinforcement Learning","date":"2024-10-08","arxiv_id":"2410.05655","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-from-imperfect-1","title":"Reinforcement Learning From Imperfect Corrective Actions And Proxy Rewards","date":"2024-10-08","arxiv_id":"2410.05782","repositories_listed":0,"syntology":null},{"url":null,"slug":"rlrf4rec-reinforcement-learning-from-recsys","title":"Direct Preference Optimization for LLM-Enhanced Recommendation Systems","date":"2024-10-08","arxiv_id":"2410.05939","repositories_listed":0,"syntology":null},{"url":null,"slug":"solving-multi-goal-robotic-tasks-with","title":"Solving Multi-Goal Robotic Tasks with Decision Transformer","date":"2024-10-08","arxiv_id":"2410.06347","repositories_listed":0,"syntology":null},{"url":null,"slug":"alpharouter-quantum-circuit-routing-with","title":"AlphaRouter: Quantum Circuit Routing with Reinforcement Learning and Tree Search","date":"2024-10-07","arxiv_id":"2410.05115","repositories_listed":0,"syntology":null},{"url":null,"slug":"designing-a-classifier-for-active-fire","title":"Designing a Classifier for Active Fire Detection from Multispectral Satellite Imagery Using Neural Architecture Search","date":"2024-10-07","arxiv_id":"2410.05425","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-model-based-reinforcement-learning-2","title":"Efficient Model-Based Reinforcement Learning Through Optimistic Thompson Sampling","date":"2024-10-07","arxiv_id":"2410.04988","repositories_listed":0,"syntology":null},{"url":null,"slug":"human-feedback-efficient-reinforcement","title":"HERO: Human-Feedback Efficient Reinforcement Learning for Online Diffusion Model Finetuning","date":"2024-10-07","arxiv_id":"2410.05116","repositories_listed":0,"syntology":null},{"url":null,"slug":"mastering-chinese-chess-ai-xiangqi-without","title":"Mastering Chinese Chess AI (Xiangqi) Without Search","date":"2024-10-07","arxiv_id":"2410.04865","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-using-reinforcement-learning-for","title":"Towards using Reinforcement Learning for Scaling and Data Replication in Cloud Systems","date":"2024-10-07","arxiv_id":"2410.11862","repositories_listed":0,"syntology":null},{"url":null,"slug":"adamemento-adaptive-memory-assisted-policy","title":"AdaMemento: Adaptive Memory-Assisted Policy Optimization for Reinforcement Learning","date":"2024-10-06","arxiv_id":"2410.04498","repositories_listed":0,"syntology":null},{"url":null,"slug":"data-driven-under-frequency-load-shedding","title":"Data-driven Under Frequency Load Shedding Using Reinforcement Learning","date":"2024-10-06","arxiv_id":"2410.04316","repositories_listed":0,"syntology":null},{"url":null,"slug":"toward-debugging-deep-reinforcement-learning","title":"Toward Debugging Deep Reinforcement Learning Programs with RLExplorer","date":"2024-10-06","arxiv_id":"2410.04322","repositories_listed":0,"syntology":null},{"url":null,"slug":"latent-action-priors-from-a-single-gait-cycle","title":"Latent Action Priors for Locomotion with Deep Reinforcement Learning","date":"2024-10-04","arxiv_id":"2410.03246","repositories_listed":0,"syntology":null},{"url":null,"slug":"training-on-more-reachable-tasks-for","title":"Training on more Reachable Tasks for Generalisation in Reinforcement Learning","date":"2024-10-04","arxiv_id":"2410.03565","repositories_listed":0,"syntology":null},{"url":null,"slug":"cross-embodiment-dexterous-grasping-with","title":"Cross-Embodiment Dexterous Grasping with Reinforcement Learning","date":"2024-10-03","arxiv_id":"2410.02479","repositories_listed":0,"syntology":null},{"url":null,"slug":"doubly-optimal-policy-evaluation-for","title":"Doubly Optimal Policy Evaluation for Reinforcement Learning","date":"2024-10-03","arxiv_id":"2410.02226","repositories_listed":0,"syntology":null},{"url":null,"slug":"dual-active-learning-for-reinforcement","title":"Dual Active Learning for Reinforcement Learning from Human Feedback","date":"2024-10-03","arxiv_id":"2410.02504","repositories_listed":0,"syntology":null}],"record_sha256":"d3d7515fa6589e4ea37d00cb7bfa7780b7b1785fe0f7135a2d458c90ed3e5016","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}