{"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/53","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":53,"pages_in_order":132,"rows_per_page":100,"rows":[5201,5300],"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/52","next":"/task/reinforcement-learning/papers/54","papers":[{"url":null,"slug":"deep-reinforcement-learning-for-multi-2","title":"Deep Reinforcement Learning for Multi-Objective Optimization: Enhancing Wind Turbine Energy Generation while Mitigating Noise Emissions","date":"2024-07-18","arxiv_id":"2407.13320","repositories_listed":0,"syntology":null},{"url":null,"slug":"limt-language-informed-multi-task-visual","title":"LIMT: Language-Informed Multi-Task Visual World Models","date":"2024-07-18","arxiv_id":"2407.13466","repositories_listed":0,"syntology":null},{"url":null,"slug":"model-based-policy-optimization-using","title":"Model-based Policy Optimization using Symbolic World Model","date":"2024-07-18","arxiv_id":"2407.13518","repositories_listed":0,"syntology":null},{"url":null,"slug":"optimistic-q-learning-for-average-reward-and","title":"Optimistic Q-learning for average reward and episodic reinforcement learning","date":"2024-07-18","arxiv_id":"2407.13743","repositories_listed":0,"syntology":null},{"url":null,"slug":"pg-rainbow-using-distributional-reinforcement","title":"PG-Rainbow: Using Distributional Reinforcement Learning in Policy Gradient Methods","date":"2024-07-18","arxiv_id":"2407.13146","repositories_listed":0,"syntology":null},{"url":null,"slug":"random-latent-exploration-for-deep","title":"Random Latent Exploration for Deep Reinforcement Learning","date":"2024-07-18","arxiv_id":"2407.13755","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-tutorial-and-survey","title":"Reinforcement Learning: Tutorial and Survey","date":"2024-07-18","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"estimating-reaction-barriers-with-deep","title":"Estimating Reaction Barriers with Deep Reinforcement Learning","date":"2024-07-17","arxiv_id":"2407.12453","repositories_listed":0,"syntology":null},{"url":null,"slug":"maintenance-strategies-for-sewer-pipes-with","title":"Maintenance Strategies for Sewer Pipes with Multi-State Degradation and Deep Reinforcement Learning","date":"2024-07-17","arxiv_id":"2407.12894","repositories_listed":0,"syntology":null},{"url":null,"slug":"sparsity-based-safety-conservatism-for","title":"Sparsity-based Safety Conservatism for Constrained Offline Reinforcement Learning","date":"2024-07-17","arxiv_id":"2407.13006","repositories_listed":0,"syntology":null},{"url":null,"slug":"subequivariant-reinforcement-learning-in-3d","title":"Subequivariant Reinforcement Learning in 3D Multi-Entity Physical Environments","date":"2024-07-17","arxiv_id":"2407.12505","repositories_listed":0,"syntology":null},{"url":null,"slug":"bellman-diffusion-models","title":"Bellman Diffusion Models","date":"2024-07-16","arxiv_id":"2407.12163","repositories_listed":0,"syntology":null},{"url":null,"slug":"satisficing-exploration-for-deep","title":"Satisficing Exploration for Deep Reinforcement Learning","date":"2024-07-16","arxiv_id":"2407.12185","repositories_listed":0,"syntology":null},{"url":null,"slug":"why-long-model-based-rollouts-are-no-reason","title":"Why long model-based rollouts are no reason for bad Q-value estimates","date":"2024-07-16","arxiv_id":"2407.11751","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploration-in-knowledge-transfer-utilizing","title":"Exploration in Knowledge Transfer Utilizing Reinforcement Learning","date":"2024-07-15","arxiv_id":"2407.10835","repositories_listed":0,"syntology":null},{"url":null,"slug":"offline-reinforcement-learning-with-imputed","title":"Offline Reinforcement Learning with Imputed Rewards","date":"2024-07-15","arxiv_id":"2407.10839","repositories_listed":0,"syntology":null},{"url":null,"slug":"three-dogmas-of-reinforcement-learning","title":"Three Dogmas of Reinforcement Learning","date":"2024-07-15","arxiv_id":"2407.10583","repositories_listed":0,"syntology":null},{"url":null,"slug":"walking-the-values-in-bayesian-inverse","title":"Walking the Values in Bayesian Inverse Reinforcement Learning","date":"2024-07-15","arxiv_id":"2407.10971","repositories_listed":0,"syntology":null},{"url":null,"slug":"affordance-guided-reinforcement-learning-via","title":"Affordance-Guided Reinforcement Learning via Visual Prompting","date":"2024-07-14","arxiv_id":"2407.10341","repositories_listed":0,"syntology":null},{"url":null,"slug":"ontology-driven-reinforcement-learning-for","title":"Ontology-driven Reinforcement Learning for Personalized Student Support","date":"2024-07-14","arxiv_id":"2407.10332","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-adapting-reinforcement-learning","title":"Towards Adapting Reinforcement Learning Agents to New Tasks: Insights from Q-Values","date":"2024-07-14","arxiv_id":"2407.10335","repositories_listed":0,"syntology":null},{"url":null,"slug":"communication-aware-reinforcement-learning","title":"Communication-Aware Reinforcement Learning for Cooperative Adaptive Cruise Control","date":"2024-07-12","arxiv_id":"2407.08964","repositories_listed":0,"syntology":null},{"url":null,"slug":"decentralized-multi-agent-reinforcement-7","title":"Decentralized multi-agent reinforcement learning algorithm using a cluster-synchronized laser network","date":"2024-07-12","arxiv_id":"2407.09124","repositories_listed":0,"syntology":null},{"url":null,"slug":"hamilton-jacobi-reachability-in-reinforcement","title":"Hamilton-Jacobi Reachability in Reinforcement Learning: A Survey","date":"2024-07-12","arxiv_id":"2407.09645","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-cantor-kantorovich-metric-between-markov","title":"A Cantor-Kantorovich Metric Between Markov Decision Processes with Application to Transfer Learning","date":"2024-07-11","arxiv_id":"2407.08324","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-review-of-nine-physics-engines-for","title":"A Review of Nine Physics Engines for Reinforcement Learning Research","date":"2024-07-11","arxiv_id":"2407.08590","repositories_listed":0,"syntology":null},{"url":null,"slug":"hierarchical-consensus-based-multi-agent","title":"Hierarchical Consensus-Based Multi-Agent Reinforcement Learning for Multi-Robot Cooperation Tasks","date":"2024-07-11","arxiv_id":"2407.08164","repositories_listed":0,"syntology":null},{"url":null,"slug":"continuous-control-with-coarse-to-fine","title":"Continuous Control with Coarse-to-fine Reinforcement Learning","date":"2024-07-10","arxiv_id":"2407.07787","repositories_listed":0,"syntology":null},{"url":null,"slug":"leveraging-llms-to-explain-drl-decisions-for","title":"Leveraging LLMs to explain DRL decisions for transparent 6G network slicing","date":"2024-07-10","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"pessimism-meets-risk-risk-sensitive-offline","title":"Pessimism Meets Risk: Risk-Sensitive Offline Reinforcement Learning","date":"2024-07-10","arxiv_id":"2407.07631","repositories_listed":0,"syntology":null},{"url":null,"slug":"real-time-system-optimal-traffic-routing","title":"Real-time system optimal traffic routing under uncertainties -- Can physics models boost reinforcement learning?","date":"2024-07-10","arxiv_id":"2407.07364","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-of-adaptive","title":"Reinforcement Learning of Adaptive Acquisition Policies for Inverse Problems","date":"2024-07-10","arxiv_id":"2407.07794","repositories_listed":0,"syntology":null},{"url":null,"slug":"hierarchical-average-reward-linearly-solvable","title":"Hierarchical Average-Reward Linearly-solvable Markov Decision Processes","date":"2024-07-09","arxiv_id":"2407.06690","repositories_listed":0,"syntology":null},{"url":null,"slug":"intercepting-unauthorized-aerial-robots-in","title":"Intercepting Unauthorized Aerial Robots in Controlled Airspace Using Reinforcement Learning","date":"2024-07-09","arxiv_id":"2407.06909","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-open-source-multi-agent-deep-reinforcement","title":"An open source Multi-Agent Deep Reinforcement Learning Routing Simulator for satellite networks","date":"2024-07-08","arxiv_id":"2407.11047","repositories_listed":0,"syntology":null},{"url":null,"slug":"graph-anomaly-detection-with-noisy-labels-by","title":"Graph Anomaly Detection with Noisy Labels by Reinforcement Learning","date":"2024-07-08","arxiv_id":"2407.05934","repositories_listed":0,"syntology":null},{"url":null,"slug":"mathrm-e-2-cfd-towards-effective-and","title":"$\\mathrm{E^{2}CFD}$: Towards Effective and Efficient Cost Function Design for Safe Reinforcement Learning via Large Language Model","date":"2024-07-08","arxiv_id":"2407.05580","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-agent-reinforcement-learning-based-5","title":"Multi-agent Reinforcement Learning-based Network Intrusion Detection System","date":"2024-07-08","arxiv_id":"2407.05766","repositories_listed":0,"syntology":null},{"url":null,"slug":"system-stabilization-with-policy-optimization","title":"System stabilization with policy optimization on unstable latent manifolds","date":"2024-07-08","arxiv_id":"2407.06418","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-reinforcement-learning-approach-for-9","title":"A Reinforcement Learning Approach for Wildfire Tracking with UAV Swarms","date":"2024-07-07","arxiv_id":"2407.05473","repositories_listed":0,"syntology":null},{"url":null,"slug":"discounted-pseudocosts-in-milp","title":"Discounted Pseudocosts in MILP","date":"2024-07-07","arxiv_id":"2407.06237","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-agent-off-policy-actor-critic","title":"Multi-agent Off-policy Actor-Critic Reinforcement Learning for Partially Observable Environments","date":"2024-07-06","arxiv_id":"2407.04974","repositories_listed":0,"syntology":null},{"url":null,"slug":"augmented-bayesian-policy-search","title":"Augmented Bayesian Policy Search","date":"2024-07-05","arxiv_id":"2407.04864","repositories_listed":0,"syntology":null},{"url":null,"slug":"graph-reinforcement-learning-in-power-grids-a","title":"Graph Reinforcement Learning for Power Grids: A Comprehensive Survey","date":"2024-07-05","arxiv_id":"2407.04522","repositories_listed":0,"syntology":null},{"url":null,"slug":"question-answering-with-texts-and-tables","title":"Question Answering with Texts and Tables through Deep Reinforcement Learning","date":"2024-07-05","arxiv_id":"2407.04858","repositories_listed":0,"syntology":null},{"url":null,"slug":"unsupervised-video-summarization-via-1","title":"Unsupervised Video Summarization via Reinforcement Learning and a Trained Evaluator","date":"2024-07-05","arxiv_id":"2407.04258","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-pareto-reinforcement-learning-for-multi","title":"Deep Pareto Reinforcement Learning for Multi-Objective Recommender Systems","date":"2024-07-04","arxiv_id":"2407.03580","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-for-sequence-design","title":"Reinforcement Learning for Sequence Design Leveraging Protein Language Models","date":"2024-07-03","arxiv_id":"2407.03154","repositories_listed":0,"syntology":null},{"url":null,"slug":"beyond-numeric-awards-in-context-dueling","title":"Beyond Numeric Awards: In-Context Dueling Bandits with LLM Agents","date":"2024-07-02","arxiv_id":"2407.01887","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-and-machine-ethics-a","title":"Reinforcement Learning and Machine ethics:a systematic review","date":"2024-07-02","arxiv_id":"2407.02425","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-from-human-feedback-2","title":"Reinforcement Learning from Human Feedback: Whose Culture, Whose Values, Whose Perspectives?","date":"2024-07-02","arxiv_id":"2407.17482","repositories_listed":0,"syntology":null},{"url":null,"slug":"research-on-autonomous-robots-navigation","title":"Research on Autonomous Robots Navigation based on Reinforcement Learning","date":"2024-07-02","arxiv_id":"2407.02539","repositories_listed":0,"syntology":null},{"url":null,"slug":"text-aware-diffusion-for-policy-learning","title":"Text-Aware Diffusion for Policy Learning","date":"2024-07-02","arxiv_id":"2407.01903","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-deep-reinforcement-learning-approach-to-8","title":"A Deep Reinforcement Learning Approach to Battery Management in Dairy Farming via Proximal Policy Optimization","date":"2024-07-01","arxiv_id":"2407.01653","repositories_listed":0,"syntology":null},{"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":"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":"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":"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":"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}],"record_sha256":"09138a2c9160ac4bc2528fed8e03a63165e2a026d3a8136c0523734dd4d2b6c3","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}