{"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/decision-making/papers/88","list_of":"/task/decision-making","task":"Decision Making","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":88,"pages_in_order":124,"rows_per_page":100,"rows":[8701,8800],"of":12311,"counts":{"archive_papers_tagged":12311,"with_a_code_link":2946,"where_syntology_ran_a_sample":678,"not_listed_spam_title":0,"listed":12311,"listed_where_code_ran":678,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":560,"every_run_a_failure_of_syntologys_instrument":118,"listed_with_a_run_with_no_instrument_failure":560,"listed_every_run_a_failure_of_syntologys_instrument":118,"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/decision-making","prev":"/task/decision-making/papers/87","next":"/task/decision-making/papers/89","papers":[{"url":null,"slug":"applications-of-multi-agent-reinforcement","title":"Applications of Multi-Agent Reinforcement Learning in Future Internet: A Comprehensive Survey","date":"2021-10-26","arxiv_id":"2110.13484","repositories_listed":0,"syntology":null},{"url":null,"slug":"mars-fl-a-market-share-based-decision-support","title":"MarS-FL: Enabling Competitors to Collaborate in Federated Learning","date":"2021-10-26","arxiv_id":"2110.13464","repositories_listed":0,"syntology":null},{"url":null,"slug":"provably-robust-model-centric-explanations","title":"Provably Robust Model-Centric Explanations for Critical Decision-Making","date":"2021-10-26","arxiv_id":"2110.13937","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-value-of-information-when-deciding-what","title":"The Value of Information When Deciding What to Learn","date":"2021-10-26","arxiv_id":"2110.13973","repositories_listed":0,"syntology":null},{"url":null,"slug":"computational-efficiency-in-multivariate","title":"Computational Efficiency in Multivariate Adversarial Risk Analysis Models","date":"2021-10-25","arxiv_id":"2110.12572","repositories_listed":0,"syntology":null},{"url":null,"slug":"debiasing-credit-scoring-using-evolutionary","title":"Debiasing Credit Scoring using Evolutionary Algorithms","date":"2021-10-25","arxiv_id":"2110.12838","repositories_listed":0,"syntology":null},{"url":null,"slug":"hsvi-fo-zs-posgs-using-concavity-convexity","title":"HSVI for zs-POSGs using Concavity, Convexity and Lipschitz Properties","date":"2021-10-25","arxiv_id":"2110.14529","repositories_listed":0,"syntology":null},{"url":null,"slug":"iterative-rule-extension-for-logic-analysis","title":"Iterative Rule Extension for Logic Analysis of Data: an MILP-based heuristic to derive interpretable binary classification from large datasets","date":"2021-10-25","arxiv_id":"2110.13664","repositories_listed":0,"syntology":null},{"url":null,"slug":"encoding-integrated-decision-and-control-for","title":"Self-learned Intelligence for Integrated Decision and Control of Automated Vehicles at Signalized Intersections","date":"2021-10-24","arxiv_id":"2110.12359","repositories_listed":0,"syntology":null},{"url":null,"slug":"pandemic-model-with-data-driven-phase","title":"Pandemic model with data-driven phase detection, a study using COVID-19 data","date":"2021-10-24","arxiv_id":"2110.12450","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-attention-driven-hierarchical-multi-scale","title":"An attention-driven hierarchical multi-scale representation for visual recognition","date":"2021-10-23","arxiv_id":"2110.12178","repositories_listed":0,"syntology":null},{"url":null,"slug":"analysis-of-thompson-sampling-for-partially","title":"Analysis of Thompson Sampling for Partially Observable Contextual Multi-Armed Bandits","date":"2021-10-23","arxiv_id":"2110.12175","repositories_listed":0,"syntology":null},{"url":null,"slug":"coarse-grained-smoothness-for-rl-in-metric","title":"Coarse-Grained Smoothness for RL in Metric Spaces","date":"2021-10-23","arxiv_id":"2110.12276","repositories_listed":0,"syntology":null},{"url":null,"slug":"mechanistic-interpretation-of-machine","title":"Mechanistic Interpretation of Machine Learning Inference: A Fuzzy Feature Importance Fusion Approach","date":"2021-10-22","arxiv_id":"2110.11713","repositories_listed":0,"syntology":null},{"url":null,"slug":"predictive-machine-learning-for-prescriptive","title":"Predictive machine learning for prescriptive applications: a coupled training-validating approach","date":"2021-10-22","arxiv_id":"2110.11826","repositories_listed":0,"syntology":null},{"url":null,"slug":"anti-concentrated-confidence-bonuses-for-1","title":"Anti-Concentrated Confidence Bonuses for Scalable Exploration","date":"2021-10-21","arxiv_id":"2110.11202","repositories_listed":0,"syntology":null},{"url":null,"slug":"aware-adoption-of-ai-from-potential-to","title":"Representations of epistemic uncertainty and awareness in data-driven strategies","date":"2021-10-21","arxiv_id":"2110.11482","repositories_listed":0,"syntology":null},{"url":null,"slug":"can-q-learning-solve-multi-armed-bantids","title":"Can Q-learning solve Multi Armed Bantids?","date":"2021-10-21","arxiv_id":"2110.10934","repositories_listed":0,"syntology":null},{"url":null,"slug":"evaluation-of-various-open-set-medical","title":"Evaluation of Various Open-Set Medical Imaging Tasks with Deep Neural Networks","date":"2021-10-21","arxiv_id":"2110.10888","repositories_listed":0,"syntology":null},{"url":null,"slug":"individualized-decision-making-under-partial","title":"Individualized Decision-Making Under Partial Identification: Three Perspectives, Two Optimality Results, and One Paradox","date":"2021-10-21","arxiv_id":"2110.10961","repositories_listed":0,"syntology":null},{"url":null,"slug":"statistical-discrimination-in-learning-agents","title":"Statistical discrimination in learning agents","date":"2021-10-21","arxiv_id":"2110.11404","repositories_listed":0,"syntology":null},{"url":null,"slug":"survival-oriented-embeddings-for-improving","title":"Survival-oriented embeddings for improving accessibility to complex data structures","date":"2021-10-21","arxiv_id":"2110.11303","repositories_listed":0,"syntology":null},{"url":null,"slug":"estimating-optimal-infinite-horizon-dynamic","title":"Estimating Optimal Infinite Horizon Dynamic Treatment Regimes via pT-Learning","date":"2021-10-20","arxiv_id":"2110.10719","repositories_listed":0,"syntology":null},{"url":null,"slug":"advanced-statistical-learning-on-short-term","title":"Advanced Statistical Learning on Short Term Load Process Forecasting","date":"2021-10-19","arxiv_id":"2110.09920","repositories_listed":0,"syntology":null},{"url":null,"slug":"information-efficient-learning-of-complexly","title":"Information efficient learning of complexly structured preferences: Elicitation procedures and their application to decision making under uncertainty","date":"2021-10-19","arxiv_id":"2110.12879","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-robotic-manipulation-skills-using-an","title":"Learning Robotic Manipulation Skills Using an Adaptive Force-Impedance Action Space","date":"2021-10-19","arxiv_id":"2110.09904","repositories_listed":0,"syntology":null},{"url":null,"slug":"don-t-judge-me-by-my-face-an-indirect","title":"Don't Judge Me by My Face : An Indirect Adversarial Approach to Remove Sensitive Information From Multimodal Neural Representation in Asynchronous Job Video Interviews","date":"2021-10-18","arxiv_id":"2110.09424","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-robustness-of-reinforcement","title":"Improving Robustness of Reinforcement Learning for Power System Control with Adversarial Training","date":"2021-10-18","arxiv_id":"2110.08956","repositories_listed":0,"syntology":null},{"url":null,"slug":"ss-mail-self-supervised-multi-agent-imitation-1","title":"SS-MAIL: Self-Supervised Multi-Agent Imitation Learning","date":"2021-10-18","arxiv_id":"2110.08963","repositories_listed":0,"syntology":null},{"url":null,"slug":"when-are-linear-stochastic-bandits-attackable","title":"When Are Linear Stochastic Bandits Attackable?","date":"2021-10-18","arxiv_id":"2110.09008","repositories_listed":0,"syntology":null},{"url":null,"slug":"auto-discern-autonomous-driving-using-common","title":"AUTO-DISCERN: Autonomous Driving Using Common Sense Reasoning","date":"2021-10-17","arxiv_id":"2110.13606","repositories_listed":0,"syntology":null},{"url":null,"slug":"measuring-total-transverse-reference-free","title":"Measuring Total Transverse Reference-free Displacements of Railroad Bridges using 2 Degrees of Freedom (2DOF): Experimental Validation","date":"2021-10-17","arxiv_id":"2110.08701","repositories_listed":0,"syntology":null},{"url":null,"slug":"tip-task-informed-motion-prediction-for","title":"TIP: Task-Informed Motion Prediction for Intelligent Vehicles","date":"2021-10-17","arxiv_id":"2110.08750","repositories_listed":0,"syntology":null},{"url":null,"slug":"decomposing-natural-logic-inferences-in","title":"Decomposing Natural Logic Inferences in Neural NLI","date":"2021-10-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-cooperation-and-online-planning","title":"Learning Cooperation and Online Planning Through Simulation and Graph Convolutional Network","date":"2021-10-16","arxiv_id":"2110.08480","repositories_listed":0,"syntology":null},{"url":null,"slug":"mapping-illegal-waste-dumping-sites-with","title":"Mapping illegal waste dumping sites with neural-network classification of satellite imagery","date":"2021-10-16","arxiv_id":"2110.08599","repositories_listed":0,"syntology":null},{"url":null,"slug":"neuroview-explainable-deep-network-decision","title":"NeuroView: Explainable Deep Network Decision Making","date":"2021-10-15","arxiv_id":"2110.07778","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-identity-preserving-normal-to","title":"Towards Identity Preserving Normal to Dysarthric Voice Conversion","date":"2021-10-15","arxiv_id":"2110.08213","repositories_listed":0,"syntology":null},{"url":null,"slug":"distribution-free-federated-learning-with","title":"Distribution-Free Federated Learning with Conformal Predictions","date":"2021-10-14","arxiv_id":"2110.07661","repositories_listed":0,"syntology":null},{"url":null,"slug":"fair-data-pipeline-provenance-driven-data","title":"FAIR Data Pipeline: provenance-driven data management for traceable scientific workflows","date":"2021-10-14","arxiv_id":"2110.07117","repositories_listed":0,"syntology":null},{"url":null,"slug":"federated-learning-and-next-generation","title":"Federated learning and next generation wireless communications: A survey on bidirectional relationship","date":"2021-10-14","arxiv_id":"2110.07649","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-when-and-what-to-ask-a-hierarchical-1","title":"A Framework for Learning to Request Rich and Contextually Useful Information from Humans","date":"2021-10-14","arxiv_id":"2110.08258","repositories_listed":0,"syntology":null},{"url":null,"slug":"looper-an-end-to-end-ml-platform-for-product","title":"Looper: An end-to-end ML platform for product decisions","date":"2021-10-14","arxiv_id":"2110.07554","repositories_listed":0,"syntology":null},{"url":null,"slug":"action-sufficient-state-representation-1","title":"Action-Sufficient State Representation Learning for Control with Structural Constraints","date":"2021-10-12","arxiv_id":"2110.05721","repositories_listed":0,"syntology":null},{"url":null,"slug":"fourier-based-video-prediction-through","title":"Fourier-based Video Prediction through Relational Object Motion","date":"2021-10-12","arxiv_id":"2110.05881","repositories_listed":0,"syntology":null},{"url":null,"slug":"power-and-accountability-in-rl-driven","title":"Power and Accountability in RL-driven Environmental Policy","date":"2021-10-12","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"explainable-fact-checking-through-question","title":"Explainable Fact-checking through Question Answering","date":"2021-10-11","arxiv_id":"2110.05369","repositories_listed":0,"syntology":null},{"url":null,"slug":"human-aware-robot-navigation-via","title":"Human-Aware Robot Navigation via Reinforcement Learning with Hindsight Experience Replay and Curriculum Learning","date":"2021-10-09","arxiv_id":"2110.04564","repositories_listed":0,"syntology":null},{"url":null,"slug":"predicting-decision-making-in-the-future","title":"Predicting decision-making in the future: Human versus Machine","date":"2021-10-09","arxiv_id":"2110.04465","repositories_listed":0,"syntology":null},{"url":null,"slug":"predicting-the-spread-of-covid-19-in-delhi","title":"Predicting the spread of COVID-19 in Delhi, India using Deep Residual Recurrent Neural Networks","date":"2021-10-09","arxiv_id":"2110.05477","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-uncertainty-informed-framework-for","title":"An Uncertainty-Informed Framework for Trustworthy Fault Diagnosis in Safety-Critical Applications","date":"2021-10-08","arxiv_id":"2111.00874","repositories_listed":0,"syntology":null},{"url":null,"slug":"governance-and-communication-of-algorithmic","title":"Governance and Communication of Algorithmic Decision Making: A Case Study on Public Sector","date":"2021-10-08","arxiv_id":"2110.09226","repositories_listed":0,"syntology":null},{"url":null,"slug":"showing-your-offline-reinforcement-learning","title":"Showing Your Offline Reinforcement Learning Work: Online Evaluation Budget Matters","date":"2021-10-08","arxiv_id":"2110.04156","repositories_listed":0,"syntology":null},{"url":null,"slug":"uncertainty-quantification-in-lv-state","title":"Uncertainty Quantification in LV State Estimation Under High Shares of Flexible Resources","date":"2021-10-08","arxiv_id":"2110.04174","repositories_listed":0,"syntology":null},{"url":null,"slug":"when-to-call-your-neighbor-strategic","title":"When to Call Your Neighbor? Strategic Communication in Cooperative Stochastic Bandits","date":"2021-10-08","arxiv_id":"2110.04396","repositories_listed":0,"syntology":null},{"url":null,"slug":"explaining-deep-reinforcement-learning-agents","title":"Explaining Deep Reinforcement Learning Agents In The Atari Domain through a Surrogate Model","date":"2021-10-07","arxiv_id":"2110.03184","repositories_listed":0,"syntology":null},{"url":null,"slug":"highly-accurate-and-reliable-wireless-network","title":"Highly Accurate and Reliable Wireless Network Slicing in 5th Generation Networks: A Hybrid Deep Learning Approach","date":"2021-10-07","arxiv_id":"2111.09416","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-prediction-confidence-in-learning","title":"Improving Prediction Confidence in Learning-Enabled Autonomous Systems","date":"2021-10-07","arxiv_id":"2110.03123","repositories_listed":0,"syntology":null},{"url":null,"slug":"inferring-substitutable-and-complementary","title":"Inferring Substitutable and Complementary Products with Knowledge-Aware Path Reasoning based on Dynamic Policy Network","date":"2021-10-07","arxiv_id":"2110.03276","repositories_listed":0,"syntology":null},{"url":null,"slug":"optimizing-oil-and-gas-acquisitions-using","title":"Optimizing Oil and Gas Acquisitions Using Recommender Systems","date":"2021-10-07","arxiv_id":"2110.03748","repositories_listed":0,"syntology":null},{"url":null,"slug":"shift-bnn-highly-efficient-probabilistic","title":"Shift-BNN: Highly-Efficient Probabilistic Bayesian Neural Network Training via Memory-Friendly Pattern Retrieving","date":"2021-10-07","arxiv_id":"2110.03553","repositories_listed":0,"syntology":null},{"url":null,"slug":"can-an-ai-agent-hit-a-moving-target","title":"Can an AI agent hit a moving target?","date":"2021-10-06","arxiv_id":"2110.02474","repositories_listed":0,"syntology":null},{"url":null,"slug":"metastable-dynamics-of-neural-circuits-and","title":"Metastable dynamics of neural circuits and networks","date":"2021-10-06","arxiv_id":"2110.03025","repositories_listed":0,"syntology":null},{"url":null,"slug":"nested-policy-reinforcement-learning","title":"Compositional Q-learning for electrolyte repletion with imbalanced patient sub-populations","date":"2021-10-06","arxiv_id":"2110.02879","repositories_listed":0,"syntology":null},{"url":null,"slug":"bi-rads-net-an-explainable-multitask-learning","title":"BI-RADS-Net: An Explainable Multitask Learning Approach for Cancer Diagnosis in Breast Ultrasound Images","date":"2021-10-05","arxiv_id":"2110.04069","repositories_listed":0,"syntology":null},{"url":null,"slug":"fake-news-noise-and-tenacious-bayesians","title":"Noise, fake news, and tenacious Bayesians","date":"2021-10-05","arxiv_id":"2110.03432","repositories_listed":0,"syntology":null},{"url":null,"slug":"gambits-theory-and-evidence","title":"Gambits: Theory and Evidence","date":"2021-10-05","arxiv_id":"2110.02755","repositories_listed":0,"syntology":null},{"url":null,"slug":"investigating-health-aware-smart-nudging-with","title":"Investigating Health-Aware Smart-Nudging with Machine Learning to Help People Pursue Healthier Eating-Habits","date":"2021-10-05","arxiv_id":"2110.07045","repositories_listed":0,"syntology":null},{"url":null,"slug":"procedure-planning-in-instructional-videosvia","title":"Procedure Planning in Instructional Videos via Contextual Modeling and Model-based Policy Learning","date":"2021-10-05","arxiv_id":"2110.01770","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-effects-of-temperature-on-economic","title":"Heat and Economic Preferences","date":"2021-10-05","arxiv_id":"2110.05611","repositories_listed":0,"syntology":null},{"url":null,"slug":"estimating-potential-outcome-distributions","title":"Estimating Potential Outcome Distributions with Collaborating Causal Networks","date":"2021-10-04","arxiv_id":"2110.01664","repositories_listed":0,"syntology":null},{"url":null,"slug":"skill-induction-and-planning-with-latent","title":"Skill Induction and Planning with Latent Language","date":"2021-10-04","arxiv_id":"2110.01517","repositories_listed":0,"syntology":null},{"url":null,"slug":"fairfed-enabling-group-fairness-in-federated","title":"FairFed: Enabling Group Fairness in Federated Learning","date":"2021-10-02","arxiv_id":"2110.00857","repositories_listed":0,"syntology":null},{"url":null,"slug":"making-things-explainable-vs-explaining","title":"Making Things Explainable vs Explaining: Requirements and Challenges under the GDPR","date":"2021-10-02","arxiv_id":"2110.00758","repositories_listed":0,"syntology":null},{"url":null,"slug":"partner-aware-algorithms-in-decentralized","title":"Partner-Aware Algorithms in Decentralized Cooperative Bandit Teams","date":"2021-10-02","arxiv_id":"2110.00751","repositories_listed":0,"syntology":null},{"url":null,"slug":"probabilistic-prediction-for-binary-treatment","title":"Probabilistic Prediction for Binary Treatment Choice: with focus on personalized medicine","date":"2021-10-02","arxiv_id":"2110.00864","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-ensemble-based-multi-criteria-decision","title":"An Ensemble-based Multi-Criteria Decision Making Method for COVID-19 Cough Classification","date":"2021-10-01","arxiv_id":"2110.00508","repositories_listed":0,"syntology":null},{"url":null,"slug":"cognitive-control-as-a-multivariate","title":"Cognitive control as a multivariate optimization problem","date":"2021-10-01","arxiv_id":"2110.00668","repositories_listed":0,"syntology":null},{"url":null,"slug":"from-slam-to-situational-awareness-challenges","title":"From SLAM to Situational Awareness: Challenges and Survey","date":"2021-10-01","arxiv_id":"2110.00273","repositories_listed":0,"syntology":null},{"url":null,"slug":"how-to-not-drive-learning-driving-constraints","title":"How To Not Drive: Learning Driving Constraints from Demonstration","date":"2021-10-01","arxiv_id":"2110.00645","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-agent-algorithmic-recourse","title":"Multi-Agent Algorithmic Recourse","date":"2021-10-01","arxiv_id":"2110.00673","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-automated-scanning-transmission-electron","title":"An Automated Scanning Transmission Electron Microscope Guided by Sparse Data Analytics","date":"2021-09-30","arxiv_id":"2109.14772","repositories_listed":0,"syntology":null},{"url":null,"slug":"crowdsourcing-through-cognitive-opportunistic","title":"Crowdsourcing through Cognitive Opportunistic Networks","date":"2021-09-30","arxiv_id":"2109.14946","repositories_listed":0,"syntology":null},{"url":null,"slug":"emergence-of-theory-of-mind-collaboration-in","title":"Emergence of Theory of Mind Collaboration in Multiagent Systems","date":"2021-09-30","arxiv_id":"2110.00121","repositories_listed":0,"syntology":null},{"url":null,"slug":"modeling-interactions-of-autonomous-vehicles","title":"Modeling Interactions of Autonomous Vehicles and Pedestrians with Deep Multi-Agent Reinforcement Learning for Collision Avoidance","date":"2021-09-30","arxiv_id":"2109.15266","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-risk-sensitive-policy-gradient-method","title":"A Risk-Sensitive Policy Gradient Method","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"an-attempt-to-model-human-trust-with","title":"An Attempt to Model Human Trust with Reinforcement Learning","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"asynchronous-multi-agent-actor-critic-with","title":"Asynchronous Multi-Agent Actor-Critic with Macro-Actions","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"auto-encoding-inverse-reinforcement-learning","title":"Auto-Encoding Inverse Reinforcement Learning","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"automatic-loss-function-search-for-predict","title":"Automatic Loss Function Search for Predict-Then-Optimize Problems with Strong Ranking Property","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"avoiding-overfitting-to-the-importance","title":"Avoiding Overfitting to the Importance Weights in Offline Policy Optimization","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"comparing-distributions-by-measuring","title":"Comparing Distributions by Measuring Differences that Affect Decision Making","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"crowdplay-crowdsourcing-human-demonstration","title":"CrowdPlay: Crowdsourcing human demonstration data for offline learning in Atari games","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"decentralized-cross-entropy-method-for-model","title":"Decentralized Cross-Entropy Method for Model-Based Reinforcement Learning","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"dl-based-prediction-of-optimal-actions-of","title":"DL-based prediction of optimal actions of human experts","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"fight-fire-with-fire-countering-bad-shortcuts","title":"Fight fire with fire: countering bad shortcuts in imitation learning with good shortcuts","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"generalizing-successor-features-to-continuous","title":"Generalizing Successor Features to continuous domains for Multi-task Learning","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"goal-randomization-for-playing-text-based","title":"Goal Randomization for Playing Text-based Games without a Reward Function","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"input-convex-graph-neural-networks-an","title":"Input Convex Graph Neural Networks: An Application to Optimal Control and Design Optimization","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"language-model-pre-training-improves","title":"Language Model Pre-training Improves Generalization in Policy Learning","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null}],"record_sha256":"d420e82f5d2bba8c34ace5f8dda7e9abdb792d2f61cc35bbb872ed3d4619769b","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}