{"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/53","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":53,"pages_in_order":135,"rows_per_page":100,"rows":[5201,5300],"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/52","next":"/task/reinforcement-learning-2/papers/54","papers":[{"url":null,"slug":"contractual-reinforcement-learning-pulling","title":"Contractual Reinforcement Learning: Pulling Arms with Invisible Hands","date":"2024-07-01","arxiv_id":"2407.01458","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-reinforcement-learning-for-adverse","title":"Deep Reinforcement Learning for Adverse Garage Scenario Generation","date":"2024-07-01","arxiv_id":"2407.01333","repositories_listed":0,"syntology":null},{"url":null,"slug":"normalization-and-effective-learning-rates-in","title":"Normalization and effective learning rates in reinforcement learning","date":"2024-07-01","arxiv_id":"2407.01800","repositories_listed":0,"syntology":null},{"url":null,"slug":"benchmarks-for-reinforcement-learning-with","title":"Benchmarks for Reinforcement Learning with Biased Offline Data and Imperfect Simulators","date":"2024-06-30","arxiv_id":"2407.00806","repositories_listed":0,"syntology":null},{"url":null,"slug":"disentangled-representations-for-causal","title":"Disentangled Representations for Causal Cognition","date":"2024-06-30","arxiv_id":"2407.00744","repositories_listed":0,"syntology":null},{"url":null,"slug":"safe-reinforcement-learning-for-power-system","title":"Safe Reinforcement Learning for Power System Control: A Review","date":"2024-06-30","arxiv_id":"2407.00681","repositories_listed":0,"syntology":null},{"url":null,"slug":"tackling-long-horizon-tasks-with-model-based","title":"Model-based Offline Reinforcement Learning with Lower Expectile Q-Learning","date":"2024-06-30","arxiv_id":"2407.00699","repositories_listed":0,"syntology":null},{"url":null,"slug":"medical-knowledge-integration-into","title":"Medical Knowledge Integration into Reinforcement Learning Algorithms for Dynamic Treatment Regimes","date":"2024-06-29","arxiv_id":"2407.00364","repositories_listed":0,"syntology":null},{"url":null,"slug":"beyond-human-preferences-exploring","title":"Beyond Human Preferences: Exploring Reinforcement Learning Trajectory Evaluation and Improvement through LLMs","date":"2024-06-28","arxiv_id":"2406.19644","repositories_listed":0,"syntology":null},{"url":null,"slug":"optimizing-cyber-defense-in-dynamic-active","title":"Optimizing Cyber Defense in Dynamic Active Directories through Reinforcement Learning","date":"2024-06-28","arxiv_id":"2406.19596","repositories_listed":0,"syntology":null},{"url":null,"slug":"ai-alignment-through-reinforcement-learning","title":"AI Alignment through Reinforcement Learning from Human Feedback? Contradictions and Limitations","date":"2024-06-26","arxiv_id":"2406.18346","repositories_listed":0,"syntology":null},{"url":null,"slug":"mental-modeling-of-reinforcement-learning","title":"Mental Modeling of Reinforcement Learning Agents by Language Models","date":"2024-06-26","arxiv_id":"2406.18505","repositories_listed":0,"syntology":null},{"url":null,"slug":"preference-elicitation-for-offline","title":"Preference Elicitation for Offline Reinforcement Learning","date":"2024-06-26","arxiv_id":"2406.18450","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-with-intrinsically","title":"Reinforcement Learning with Intrinsically Motivated Feedback Graph for Lost-sales Inventory Control","date":"2024-06-26","arxiv_id":"2406.18351","repositories_listed":0,"syntology":null},{"url":null,"slug":"privacy-preserving-reinforcement-learning-for","title":"Privacy Preserving Reinforcement Learning for Population Processes","date":"2024-06-25","arxiv_id":"2406.17649","repositories_listed":0,"syntology":null},{"url":null,"slug":"model-free-robust-reinforcement-learning-with-1","title":"Model-Free Robust Reinforcement Learning with Sample Complexity Analysis","date":"2024-06-24","arxiv_id":"2406.17096","repositories_listed":0,"syntology":null},{"url":null,"slug":"diffusion-spectral-representation-for","title":"Diffusion Spectral Representation for Reinforcement Learning","date":"2024-06-23","arxiv_id":"2406.16121","repositories_listed":0,"syntology":null},{"url":null,"slug":"position-benchmarking-is-limited-in","title":"Position: Benchmarking is Limited in Reinforcement Learning Research","date":"2024-06-23","arxiv_id":"2406.16241","repositories_listed":0,"syntology":null},{"url":null,"slug":"understanding-and-diagnosing-deep","title":"Understanding and Diagnosing Deep Reinforcement Learning","date":"2024-06-23","arxiv_id":"2406.16979","repositories_listed":0,"syntology":null},{"url":null,"slug":"distributionally-robust-constrained","title":"Distributionally Robust Constrained Reinforcement Learning under Strong Duality","date":"2024-06-22","arxiv_id":"2406.15788","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-idiosyncrasy-of-time-discretization-in","title":"An Idiosyncrasy of Time-discretization in Reinforcement Learning","date":"2024-06-21","arxiv_id":"2406.14951","repositories_listed":0,"syntology":null},{"url":null,"slug":"knobtree-intelligent-database-parameter","title":"KnobTree: Intelligent Database Parameter Configuration via Explainable Reinforcement Learning","date":"2024-06-21","arxiv_id":"2406.15073","repositories_listed":0,"syntology":null},{"url":null,"slug":"robust-reinforcement-learning-from-corrupted","title":"Robust Reinforcement Learning from Corrupted Human Feedback","date":"2024-06-21","arxiv_id":"2406.15568","repositories_listed":0,"syntology":null},{"url":null,"slug":"2406-15508","title":"What Teaches Robots to Walk, Teaches Them to Trade too -- Regime Adaptive Execution using Informed Data and LLMs","date":"2024-06-20","arxiv_id":"2406.15508","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-general-control-theoretic-approach-for","title":"A General Control-Theoretic Approach for Reinforcement Learning: Theory and Algorithms","date":"2024-06-20","arxiv_id":"2406.14753","repositories_listed":0,"syntology":null},{"url":null,"slug":"bayesian-inverse-reinforcement-learning-for-1","title":"Bayesian Inverse Reinforcement Learning for Non-Markovian Rewards","date":"2024-06-20","arxiv_id":"2406.13991","repositories_listed":0,"syntology":null},{"url":null,"slug":"constrained-meta-agnostic-reinforcement","title":"Constrained Meta Agnostic Reinforcement Learning","date":"2024-06-20","arxiv_id":"2406.14047","repositories_listed":0,"syntology":null},{"url":null,"slug":"equivariant-offline-reinforcement-learning","title":"Equivariant Offline Reinforcement Learning","date":"2024-06-20","arxiv_id":"2406.13961","repositories_listed":0,"syntology":null},{"url":null,"slug":"tractable-equilibrium-computation-in-markov","title":"Tractable Equilibrium Computation in Markov Games through Risk Aversion","date":"2024-06-20","arxiv_id":"2406.14156","repositories_listed":0,"syntology":null},{"url":null,"slug":"urban-focused-multi-task-offline","title":"Urban-Focused Multi-Task Offline Reinforcement Learning with Contrastive Data Sharing","date":"2024-06-20","arxiv_id":"2406.14054","repositories_listed":0,"syntology":null},{"url":null,"slug":"learned-graph-rewriting-with-equality","title":"Learned Graph Rewriting with Equality Saturation: A New Paradigm in Relational Query Rewrite and Beyond","date":"2024-06-19","arxiv_id":"2407.12794","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-for-infinite-horizon","title":"Infinite-Horizon Reinforcement Learning with Multinomial Logistic Function Approximation","date":"2024-06-19","arxiv_id":"2406.13633","repositories_listed":0,"syntology":null},{"url":null,"slug":"trapezoidal-gradient-descent-for-effective","title":"Trapezoidal Gradient Descent for Effective Reinforcement Learning in Spiking Networks","date":"2024-06-19","arxiv_id":"2406.13568","repositories_listed":0,"syntology":null},{"url":null,"slug":"quantum-compiling-with-reinforcement-learning","title":"Quantum Compiling with Reinforcement Learning on a Superconducting Processor","date":"2024-06-18","arxiv_id":"2406.12195","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-for-corporate-bond","title":"Reinforcement Learning for Corporate Bond Trading: A Sell Side Perspective","date":"2024-06-18","arxiv_id":"2406.12983","repositories_listed":0,"syntology":null},{"url":null,"slug":"sample-efficient-imitative-multi-token","title":"Physics-informed Imitative Reinforcement Learning for Real-world Driving","date":"2024-06-18","arxiv_id":"2407.02508","repositories_listed":0,"syntology":null},{"url":"/paper/adding-conditional-control-to-diffusion","slug":"adding-conditional-control-to-diffusion","title":"Adding Conditional Control to Diffusion Models with Reinforcement Learning","date":"2024-06-17","arxiv_id":"2406.12120","repositories_listed":0,"syntology":{"n":9,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":9,"phrase":"4 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; 0 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/adding-conditional-control-to-diffusion#ran","syntology_url":"https://syntology.ai/paper/2406.12120","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.12120"}},"official":null}},{"url":null,"slug":"constructing-ancestral-recombination-graphs","title":"Constructing Ancestral Recombination Graphs through Reinforcement Learning","date":"2024-06-17","arxiv_id":"2406.12022","repositories_listed":0,"syntology":null},{"url":null,"slug":"measuring-memorization-in-rlhf-for-code","title":"Measuring memorization in RLHF for code completion","date":"2024-06-17","arxiv_id":"2406.11715","repositories_listed":0,"syntology":null},{"url":null,"slug":"optimal-transport-assisted-risk-sensitive-q","title":"Optimal Transport-Assisted Risk-Sensitive Q-Learning","date":"2024-06-17","arxiv_id":"2406.11774","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-benefits-of-power-regularization-in","title":"The Benefits of Power Regularization in Cooperative Reinforcement Learning","date":"2024-06-17","arxiv_id":"2406.11240","repositories_listed":0,"syntology":null},{"url":null,"slug":"dipper-direct-preference-optimization-to","title":"DIPPER: Direct Preference Optimization to Accelerate Primitive-Enabled Hierarchical Reinforcement Learning","date":"2024-06-16","arxiv_id":"2406.10892","repositories_listed":0,"syntology":null},{"url":null,"slug":"instructrl4pix-training-diffusion-for-image","title":"InstructRL4Pix: Training Diffusion for Image Editing by Reinforcement Learning","date":"2024-06-14","arxiv_id":"2406.09973","repositories_listed":0,"syntology":null},{"url":null,"slug":"cimrl-combining-imitiation-and-reinforcement","title":"CIMRL: Combining IMitation and Reinforcement Learning for Safe Autonomous Driving","date":"2024-06-13","arxiv_id":"2406.08878","repositories_listed":0,"syntology":null},{"url":null,"slug":"current-applications-and-potential-future","title":"Current applications and potential future directions of reinforcement learning-based Digital Twins in agriculture","date":"2024-06-13","arxiv_id":"2406.08854","repositories_listed":0,"syntology":null},{"url":null,"slug":"diffpogan-diffusion-policies-with-generative","title":"DiffPoGAN: Diffusion Policies with Generative Adversarial Networks for Offline Reinforcement Learning","date":"2024-06-13","arxiv_id":"2406.09089","repositories_listed":0,"syntology":null},{"url":null,"slug":"e-cop-episodic-constrained-optimization-of","title":"e-COP : Episodic Constrained Optimization of Policies","date":"2024-06-13","arxiv_id":"2406.09563","repositories_listed":0,"syntology":null},{"url":null,"slug":"xland-100b-a-large-scale-multi-task-dataset","title":"XLand-100B: A Large-Scale Multi-Task Dataset for In-Context Reinforcement Learning","date":"2024-06-13","arxiv_id":"2406.08973","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-reinforcement-learning-with-positional","title":"Deep reinforcement learning with positional context for intraday trading","date":"2024-06-12","arxiv_id":"2406.08013","repositories_listed":0,"syntology":null},{"url":null,"slug":"explore-go-leveraging-exploration-for","title":"Explore-Go: Leveraging Exploration for Generalisation in Deep Reinforcement Learning","date":"2024-06-12","arxiv_id":"2406.08069","repositories_listed":0,"syntology":null},{"url":null,"slug":"how-social-reinforcement-learning-can-lead-to","title":"How social reinforcement learning can lead to metastable polarisation and the voter model","date":"2024-06-12","arxiv_id":"2406.07993","repositories_listed":0,"syntology":null},{"url":null,"slug":"optimizing-deep-reinforcement-learning-for-1","title":"Optimizing Deep Reinforcement Learning for Adaptive Robotic Arm Control","date":"2024-06-12","arxiv_id":"2407.02503","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-for-high-level","title":"Reinforcement Learning for High-Level Strategic Control in Tower Defense Games","date":"2024-06-12","arxiv_id":"2406.07980","repositories_listed":0,"syntology":null},{"url":null,"slug":"rile-reinforced-imitation-learning","title":"RILe: Reinforced Imitation Learning","date":"2024-06-12","arxiv_id":"2406.08472","repositories_listed":0,"syntology":null},{"url":null,"slug":"time-constrained-robust-mdps","title":"Time-Constrained Robust MDPs","date":"2024-06-12","arxiv_id":"2406.08395","repositories_listed":0,"syntology":null},{"url":null,"slug":"cdsa-conservative-denoising-score-based","title":"CDSA: Conservative Denoising Score-based Algorithm for Offline Reinforcement Learning","date":"2024-06-11","arxiv_id":"2406.07541","repositories_listed":0,"syntology":null},{"url":null,"slug":"hybrid-reinforcement-learning-from-offline","title":"Hybrid Reinforcement Learning from Offline Observation Alone","date":"2024-06-11","arxiv_id":"2406.07253","repositories_listed":0,"syntology":null},{"url":null,"slug":"joint-demonstration-and-preference-learning","title":"Learning Reward and Policy Jointly from Demonstration and Preference Improves Alignment","date":"2024-06-11","arxiv_id":"2406.06874","repositories_listed":0,"syntology":null},{"url":null,"slug":"boosting-robustness-in-preference-based","title":"Boosting Robustness in Preference-Based Reinforcement Learning with Dynamic Sparsity","date":"2024-06-10","arxiv_id":"2406.06495","repositories_listed":0,"syntology":null},{"url":null,"slug":"risk-sensitivity-in-markov-games-and-multi","title":"Risk Sensitivity in Markov Games and Multi-Agent Reinforcement Learning: A Systematic Review","date":"2024-06-10","arxiv_id":"2406.06041","repositories_listed":0,"syntology":null},{"url":null,"slug":"verification-guided-shielding-for-deep","title":"Verification-Guided Shielding for Deep Reinforcement Learning","date":"2024-06-10","arxiv_id":"2406.06507","repositories_listed":0,"syntology":null},{"url":null,"slug":"lgr2-language-guided-reward-relabeling-for","title":"LGR2: Language Guided Reward Relabeling for Accelerating Hierarchical Reinforcement Learning","date":"2024-06-09","arxiv_id":"2406.05881","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhanced-flight-envelope-protection-a-novel","title":"Enhanced Flight Envelope Protection: A Novel Reinforcement Learning Approach","date":"2024-06-08","arxiv_id":"2406.05586","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-for-intensity-control","title":"Reinforcement Learning for Intensity Control: An Application to Choice-Based Network Revenue Management","date":"2024-06-08","arxiv_id":"2406.05358","repositories_listed":0,"syntology":null},{"url":"/paper/optimizing-automatic-differentiation-with","slug":"optimizing-automatic-differentiation-with","title":"Optimizing Automatic Differentiation with Deep Reinforcement Learning","date":"2024-06-07","arxiv_id":"2406.05027","repositories_listed":0,"syntology":{"n":29,"n_ran":12,"n_constructed":0,"n_ran_checked":11,"n_instrument":1,"n_unverified":17,"n_honours":0,"n_violates":0,"n_no_contract":11,"n_pointer_only":0,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 1 where Syntology's instrument failed) · 17 unverified","sample_list":"/paper/optimizing-automatic-differentiation-with#ran","syntology_url":"https://syntology.ai/paper/2406.05027","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.05027"}},"official":null}},{"url":null,"slug":"ac4mpc-actor-critic-reinforcement-learning","title":"AC4MPC: Actor-Critic Reinforcement Learning for Nonlinear Model Predictive Control","date":"2024-06-06","arxiv_id":"2406.03995","repositories_listed":0,"syntology":null},{"url":null,"slug":"atradiff-accelerating-online-reinforcement","title":"ATraDiff: Accelerating Online Reinforcement Learning with Imaginary Trajectories","date":"2024-06-06","arxiv_id":"2406.04323","repositories_listed":0,"syntology":null},{"url":null,"slug":"behavior-targeted-attack-on-reinforcement","title":"Behavior-Targeted Attack on Reinforcement Learning with Limited Access to Victim's Policy","date":"2024-06-06","arxiv_id":"2406.03862","repositories_listed":0,"syntology":null},{"url":null,"slug":"bootstrapping-expectiles-in-reinforcement","title":"Bootstrapping Expectiles in Reinforcement Learning","date":"2024-06-06","arxiv_id":"2406.04081","repositories_listed":0,"syntology":null},{"url":null,"slug":"breeding-programs-optimization-with","title":"Breeding Programs Optimization with Reinforcement Learning","date":"2024-06-06","arxiv_id":"2406.03932","repositories_listed":0,"syntology":null},{"url":null,"slug":"excluding-the-irrelevant-focusing","title":"Excluding the Irrelevant: Focusing Reinforcement Learning through Continuous Action Masking","date":"2024-06-06","arxiv_id":"2406.03704","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-pessimism-and-optimism-dynamics-in","title":"Exploring Pessimism and Optimism Dynamics in Deep Reinforcement Learning","date":"2024-06-06","arxiv_id":"2406.03890","repositories_listed":0,"syntology":null},{"url":null,"slug":"gensafe-a-generalizable-safety-enhancer-for","title":"GenSafe: A Generalizable Safety Enhancer for Safe Reinforcement Learning Algorithms Based on Reduced Order Markov Decision Process Model","date":"2024-06-06","arxiv_id":"2406.03912","repositories_listed":0,"syntology":null},{"url":null,"slug":"optimizing-autonomous-driving-for-safety-a","title":"Optimizing Autonomous Driving for Safety: A Human-Centric Approach with LLM-Enhanced RLHF","date":"2024-06-06","arxiv_id":"2406.04481","repositories_listed":0,"syntology":null},{"url":null,"slug":"self-play-with-adversarial-critic-provable","title":"Self-Play with Adversarial Critic: Provable and Scalable Offline Alignment for Language Models","date":"2024-06-06","arxiv_id":"2406.04274","repositories_listed":0,"syntology":null},{"url":null,"slug":"inductive-generalization-in-reinforcement","title":"Inductive Generalization in Reinforcement Learning from Specifications","date":"2024-06-05","arxiv_id":"2406.03651","repositories_listed":0,"syntology":null},{"url":null,"slug":"physics-informed-critic-in-an-actor-critic","title":"Physics-Guided Actor-Critic Reinforcement Learning for Swimming in Turbulence","date":"2024-06-05","arxiv_id":"2406.10242","repositories_listed":0,"syntology":null},{"url":null,"slug":"representation-learning-for-efficient-deep","title":"Representation Learning For Efficient Deep Multi-Agent Reinforcement Learning","date":"2024-06-05","arxiv_id":"2406.02890","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-unifying-framework-for-action-conditional","title":"A Unifying Framework for Action-Conditional Self-Predictive Reinforcement Learning","date":"2024-06-04","arxiv_id":"2406.02035","repositories_listed":0,"syntology":null},{"url":null,"slug":"adaptive-preference-scaling-for-reinforcement","title":"Adaptive Preference Scaling for Reinforcement Learning with Human Feedback","date":"2024-06-04","arxiv_id":"2406.02764","repositories_listed":0,"syntology":null},{"url":null,"slug":"algorithmic-collusion-in-dynamic-pricing-with","title":"Algorithmic Collusion in Dynamic Pricing with Deep Reinforcement Learning","date":"2024-06-04","arxiv_id":"2406.02437","repositories_listed":0,"syntology":null},{"url":null,"slug":"fightladder-a-benchmark-for-competitive-multi","title":"FightLadder: A Benchmark for Competitive Multi-Agent Reinforcement Learning","date":"2024-06-04","arxiv_id":"2406.02081","repositories_listed":0,"syntology":null},{"url":null,"slug":"iqrl-implicitly-quantized-representations-for","title":"iQRL -- Implicitly Quantized Representations for Sample-efficient Reinforcement Learning","date":"2024-06-04","arxiv_id":"2406.02696","repositories_listed":0,"syntology":null},{"url":null,"slug":"rectifying-reinforcement-learning-for-reward","title":"Rectifying Reinforcement Learning for Reward Matching","date":"2024-06-04","arxiv_id":"2406.02213","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-based-architecture","title":"Reinforcement learning-based architecture search for quantum machine learning","date":"2024-06-04","arxiv_id":"2406.02717","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-with-lookahead","title":"Reinforcement Learning with Lookahead Information","date":"2024-06-04","arxiv_id":"2406.02258","repositories_listed":0,"syntology":null},{"url":null,"slug":"test-time-regret-minimization-in-meta","title":"Test-Time Regret Minimization in Meta Reinforcement Learning","date":"2024-06-04","arxiv_id":"2406.02282","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-new-view-on-planning-in-online","title":"A New View on Planning in Online Reinforcement Learning","date":"2024-06-03","arxiv_id":"2406.01562","repositories_listed":0,"syntology":null},{"url":null,"slug":"causal-prompting-model-based-offline","title":"Causal prompting model-based offline reinforcement learning","date":"2024-06-03","arxiv_id":"2406.01065","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-reinforcement-learning-behavioral-mode","title":"Deep Reinforcement Learning Behavioral Mode Switching Using Optimal Control Based on a Latent Space Objective","date":"2024-06-03","arxiv_id":"2406.01178","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-reinforcement-learning-for-weakly","title":"Deep reinforcement learning for weakly coupled MDP's with continuous actions","date":"2024-06-03","arxiv_id":"2406.01099","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-agent-assignment-via-state-augmented","title":"Multi-agent assignment via state augmented reinforcement learning","date":"2024-06-03","arxiv_id":"2406.01782","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-agent-reinforcement-learning-meets-leaf","title":"Multi-Agent Reinforcement Learning Meets Leaf Sequencing in Radiotherapy","date":"2024-06-03","arxiv_id":"2406.01853","repositories_listed":0,"syntology":null},{"url":null,"slug":"scalable-ensembling-for-mitigating-reward","title":"Scalable Ensembling For Mitigating Reward Overoptimisation","date":"2024-06-03","arxiv_id":"2406.01013","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-digital-twin-framework-for-reinforcement","title":"A Digital Twin Framework for Reinforcement Learning with Real-Time Self-Improvement via Human Assistive Teleoperation","date":"2024-06-02","arxiv_id":"2406.00732","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-to-play-7-wonders-duel-without-human","title":"Learning to Play 7 Wonders Duel Without Human Supervision","date":"2024-06-02","arxiv_id":"2406.00741","repositories_listed":0,"syntology":null},{"url":null,"slug":"maximum-entropy-regularized-decision","title":"Maximum-Entropy Regularized Decision Transformer with Reward Relabelling for Dynamic Recommendation","date":"2024-06-02","arxiv_id":"2406.00725","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-dimensional-optimization-for-text","title":"Multi-Dimensional Optimization for Text Summarization via Reinforcement Learning","date":"2024-06-01","arxiv_id":"2406.00303","repositories_listed":0,"syntology":null},{"url":null,"slug":"decision-mamba-reinforcement-learning-via-1","title":"Decision Mamba: Reinforcement Learning via Hybrid Selective Sequence Modeling","date":"2024-05-31","arxiv_id":"2406.00079","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploratory-preference-optimization","title":"Exploratory Preference Optimization: Harnessing Implicit Q*-Approximation for Sample-Efficient RLHF","date":"2024-05-31","arxiv_id":"2405.21046","repositories_listed":0,"syntology":null}],"record_sha256":"ac0716c36bfcd522ea1c63f17be7e5b9fb5f84379267e6607a0297d54ce144fc","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}