{"url":"/task/decision-making","name":"Decision Making","slug":"decision-making","description_markdown":null,"categories":[{"name":"Methodology","url":"/area/methodology"},{"name":"Reasoning","url":"/area/reasoning"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":12311,"papers_with_code":2946,"benchmarks":2,"benchmark_tables_in_archive":2,"benchmark_tables_shown":2,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":40,"subtasks":1,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/decision-making-on-01-01-1967","slug":"decision-making-on-01-01-1967","dataset":"./01/01/1967","dataset_url":null,"rows_in_archive":1,"metrics":["0..5sec"],"first_row_in_archive_order":{"model":"topais","paper_title":"Strategic Evaluation in Optimizing the Internal Supply Chain Using TOPSIS: Evidence In A Coil Winding Machine Manufacturer","paper_url":"/paper/strategic-evaluation-in-optimizing-the","paper_date":"2020-07-08","arxiv_id":"2007.10121","code_links":[{"title":"hcshipra/researchpublication","url":"https://github.com/hcshipra/researchpublication"}],"syntology":null}},{"leaderboard":"/sota/decision-making-on-nasa-c-mapss","slug":"decision-making-on-nasa-c-mapss","dataset":"NASA C-MAPSS","dataset_url":"/dataset/nasa-c-mapss","rows_in_archive":1,"metrics":["Average Remaining Cycles"],"first_row_in_archive_order":{"model":"SRLA","paper_title":"Hierarchical Framework for Interpretable and Probabilistic Model-Based Safe Reinforcement Learning","paper_url":"/paper/hierarchical-framework-for-interpretable-and","paper_date":"2023-10-28","arxiv_id":"2310.18811","code_links":[{"title":"ammar-n-abbas/Predictive-Maintenance-BC-IOHMM-DRL","url":"https://github.com/ammar-n-abbas/Predictive-Maintenance-BC-IOHMM-DRL"}],"syntology":null}}],"datasets":[{"url":"/dataset/d4rl","name":"D4RL","full_name":"D4RL","num_papers_in_archive":538},{"url":"/dataset/charades-sta","name":"Charades-STA","full_name":"","num_papers_in_archive":236},{"url":"/dataset/fairface","name":"FairFace","full_name":"","num_papers_in_archive":208},{"url":"/dataset/vizdoom","name":"VizDoom","full_name":"VizDoom","num_papers_in_archive":156},{"url":"/dataset/logiqa","name":"LogiQA","full_name":"","num_papers_in_archive":127},{"url":"/dataset/torcs","name":"TORCS","full_name":"The Open Racing Car Simulator","num_papers_in_archive":96},{"url":"/dataset/mura","name":"MURA","full_name":"","num_papers_in_archive":43},{"url":"/dataset/sharc","name":"ShARC","full_name":"Shaping Answers with Rules through Conversation","num_papers_in_archive":43},{"url":"/dataset/peerread","name":"PeerRead","full_name":"","num_papers_in_archive":42},{"url":"/dataset/coaid","name":"CoAID","full_name":"","num_papers_in_archive":41},{"url":"/dataset/gazefollow","name":"GazeFollow","full_name":"GazeFollow","num_papers_in_archive":38},{"url":"/dataset/robonet","name":"RoboNet","full_name":"","num_papers_in_archive":28},{"url":"/dataset/evidence-inference","name":"Evidence Inference","full_name":"","num_papers_in_archive":27},{"url":"/dataset/road","name":"ROAD","full_name":"ROAD: The ROad event Awareness Dataset for Autonomous Driving","num_papers_in_archive":27},{"url":"/dataset/senticap","name":"SentiCap","full_name":"","num_papers_in_archive":26},{"url":"/dataset/ropes","name":"ROPES","full_name":"Reasoning Over Paragraph Effects in Situations","num_papers_in_archive":24},{"url":"/dataset/obstacle-tower","name":"Obstacle Tower","full_name":"","num_papers_in_archive":20},{"url":"/dataset/industrial-benchmark","name":"Industrial Benchmark","full_name":"","num_papers_in_archive":13},{"url":"/dataset/trajnet-1","name":"TrajNet","full_name":"","num_papers_in_archive":12},{"url":"/dataset/chalet","name":"CHALET","full_name":"Cornell House Agent Learning Environment","num_papers_in_archive":10},{"url":"/dataset/atari-head","name":"Atari-HEAD","full_name":null,"num_papers_in_archive":9},{"url":"/dataset/blvd","name":"BLVD","full_name":"","num_papers_in_archive":9},{"url":"/dataset/ukp","name":"UKP","full_name":"UKP Argument Annotated Essays","num_papers_in_archive":8},{"url":"/dataset/nasa-c-mapss","name":"NASA C-MAPSS","full_name":"Turbofan Engine Degradation Simulation Data Set","num_papers_in_archive":7},{"url":"/dataset/omics","name":"OMICS","full_name":"Open Mind Indoor Common Sense","num_papers_in_archive":6},{"url":"/dataset/demcare","name":"DemCare","full_name":"","num_papers_in_archive":5},{"url":"/dataset/flickr-cropping-dataset","name":"Flickr Cropping Dataset","full_name":null,"num_papers_in_archive":5},{"url":"/dataset/golfdb","name":"GolfDB","full_name":"","num_papers_in_archive":5},{"url":"/dataset/cuhk-image-cropping","name":"CUHK Image Cropping","full_name":"CUHK Image Cropping","num_papers_in_archive":3},{"url":"/dataset/packit","name":"PackIt","full_name":"","num_papers_in_archive":3},{"url":"/dataset/covid-hera","name":"Covid-HeRA","full_name":null,"num_papers_in_archive":2},{"url":"/dataset/negotiation-dialogues-dataset","name":"Negotiation Dialogues Dataset","full_name":"","num_papers_in_archive":2},{"url":"/dataset/pubmed-pico-element-detection-dataset","name":"PubMed PICO Element Detection Dataset","full_name":null,"num_papers_in_archive":2},{"url":"/dataset/a-view-from-somewhere-avfs","name":"A View From Somewhere (AVFS)","full_name":"","num_papers_in_archive":1},{"url":"/dataset/benyfits","name":"BeNYfits","full_name":"New York City Public Benefits Eligibility Dialog Agent Benchmark","num_papers_in_archive":1},{"url":"/dataset/car-price-prediction","name":"Car_Price_Prediction","full_name":"Second_Hand-Car_Price_Prediction","num_papers_in_archive":1},{"url":"/dataset/d2city","name":"D2City","full_name":"","num_papers_in_archive":1},{"url":"/dataset/industrial-benchmark-dataset-for-customer","name":"Industrial Benchmark Dataset for Customer Escalation Prediction","full_name":"","num_papers_in_archive":1},{"url":"/dataset/pursuitmw","name":"pursuitMW","full_name":"Multi-agent pursuit in matrix world","num_papers_in_archive":1},{"url":"/dataset/spaceship-dataset","name":"Spaceship Dataset","full_name":null,"num_papers_in_archive":1}],"subtasks":[{"url":"/task/imitation-learning","name":"Imitation Learning"}],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":30,"of":2946,"tagged_in_all":12311,"items":[{"url":"/paper/soft-actor-critic-off-policy-maximum-entropy","title":"Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor","date":"2018-01-04","arxiv_id":"1801.01290","repositories_listed":86,"syntology":{"n":148,"n_ran":91,"n_unverified":57,"n_pointer_only":66}},{"url":"/paper/soft-actor-critic-algorithms-and-applications","title":"Soft Actor-Critic Algorithms and Applications","date":"2018-12-13","arxiv_id":"1812.05905","repositories_listed":52,"syntology":{"n":40,"n_ran":10,"n_unverified":30,"n_pointer_only":1}},{"url":"/paper/relational-inductive-biases-deep-learning-and","title":"Relational inductive biases, deep learning, and graph networks","date":"2018-06-04","arxiv_id":"1806.01261","repositories_listed":31,"syntology":{"n":51,"n_ran":13,"n_unverified":38,"n_pointer_only":15}},{"url":"/paper/bayesian-segnet-model-uncertainty-in-deep","title":"Bayesian SegNet: Model Uncertainty in Deep Convolutional Encoder-Decoder Architectures for Scene Understanding","date":"2015-11-09","arxiv_id":"1511.02680","repositories_listed":21,"syntology":{"n":18,"n_ran":0,"n_unverified":18,"n_pointer_only":0}},{"url":"/paper/tabnet-attentive-interpretable-tabular","title":"TabNet: Attentive Interpretable Tabular Learning","date":"2019-08-20","arxiv_id":"1908.07442","repositories_listed":19,"syntology":{"n":17,"n_ran":1,"n_unverified":16,"n_pointer_only":1}},{"url":"/paper/ai-fairness-360-an-extensible-toolkit-for","title":"AI Fairness 360: An Extensible Toolkit for Detecting, Understanding, and Mitigating Unwanted Algorithmic Bias","date":"2018-10-03","arxiv_id":"1810.01943","repositories_listed":13,"syntology":{"n":11,"n_ran":3,"n_unverified":8,"n_pointer_only":1}},{"url":"/paper/graphcast-learning-skillful-medium-range","title":"GraphCast: Learning skillful medium-range global weather forecasting","date":"2022-12-24","arxiv_id":"2212.12794","repositories_listed":11,"syntology":{"n":4,"n_ran":1,"n_unverified":3,"n_pointer_only":0}},{"url":"/paper/react-synergizing-reasoning-and-acting-in","title":"ReAct: Synergizing Reasoning and Acting in Language Models","date":"2022-10-06","arxiv_id":"2210.03629","repositories_listed":9,"syntology":{"n":34,"n_ran":15,"n_unverified":19,"n_pointer_only":5}},{"url":"/paper/score-camimproved-visual-explanations-via","title":"Score-CAM: Score-Weighted Visual Explanations for Convolutional Neural Networks","date":"2019-10-03","arxiv_id":"1910.01279","repositories_listed":9,"syntology":{"n":13,"n_ran":3,"n_unverified":10,"n_pointer_only":2}},{"url":"/paper/a-probabilistic-u-net-for-segmentation-of","title":"A Probabilistic U-Net for Segmentation of Ambiguous Images","date":"2018-06-13","arxiv_id":"1806.05034","repositories_listed":9,"syntology":{"n":9,"n_ran":5,"n_unverified":4,"n_pointer_only":0}},{"url":"/paper/neural-additive-models-interpretable-machine","title":"Neural Additive Models: Interpretable Machine Learning with Neural Nets","date":"2020-04-29","arxiv_id":"2004.13912","repositories_listed":8,"syntology":{"n":33,"n_ran":26,"n_unverified":7,"n_pointer_only":14}},{"url":"/paper/mastering-diverse-domains-through-world","title":"Mastering Diverse Domains through World Models","date":"2023-01-10","arxiv_id":"2301.04104","repositories_listed":7,"syntology":{"n":34,"n_ran":21,"n_unverified":13,"n_pointer_only":0}},{"url":"/paper/the-kits19-challenge-data-300-kidney-tumor","title":"The KiTS19 Challenge Data: 300 Kidney Tumor Cases with Clinical Context, CT Semantic Segmentations, and Surgical Outcomes","date":"2019-03-31","arxiv_id":"1904.00445","repositories_listed":7,"syntology":{"n":4,"n_ran":3,"n_unverified":1,"n_pointer_only":4}},{"url":"/paper/brain-tumor-segmentation-and-radiomics","title":"Brain Tumor Segmentation and Radiomics Survival Prediction: Contribution to the BRATS 2017 Challenge","date":"2018-02-28","arxiv_id":"1802.10508","repositories_listed":7,"syntology":{"n":3,"n_ran":1,"n_unverified":2,"n_pointer_only":0}},{"url":"/paper/learning-robust-rewards-with-adversarial","title":"Learning Robust Rewards with Adversarial Inverse Reinforcement Learning","date":"2017-10-30","arxiv_id":"1710.11248","repositories_listed":7,"syntology":{"n":5,"n_ran":0,"n_unverified":5,"n_pointer_only":5}},{"url":"/paper/tree-of-thoughts-deliberate-problem-solving-1","title":"Tree of Thoughts: Deliberate Problem Solving with Large Language Models","date":"2023-05-17","arxiv_id":"2305.10601","repositories_listed":6,"syntology":{"n":24,"n_ran":7,"n_unverified":17,"n_pointer_only":0}},{"url":"/paper/a-comprehensive-analysis-of-ai-biases-in","title":"Analyzing Fairness in Deepfake Detection With Massively Annotated Databases","date":"2022-08-11","arxiv_id":"2208.05845","repositories_listed":6,"syntology":null},{"url":"/paper/qplex-duplex-dueling-multi-agent-q-learning","title":"QPLEX: Duplex Dueling Multi-Agent Q-Learning","date":"2020-08-03","arxiv_id":"2008.01062","repositories_listed":6,"syntology":{"n":4,"n_ran":2,"n_unverified":2,"n_pointer_only":0}},{"url":"/paper/motion-planning-among-dynamic-decision-making","title":"Motion Planning Among Dynamic, Decision-Making Agents with Deep Reinforcement Learning","date":"2018-05-04","arxiv_id":"1805.01956","repositories_listed":6,"syntology":{"n":6,"n_ran":0,"n_unverified":6,"n_pointer_only":0}},{"url":"/paper/quicknat-a-fully-convolutional-network-for","title":"QuickNAT: A Fully Convolutional Network for Quick and Accurate Segmentation of Neuroanatomy","date":"2018-01-12","arxiv_id":"1801.04161","repositories_listed":6,"syntology":null},{"url":"/paper/deep-reinforcement-learning-for-unsupervised","title":"Deep Reinforcement Learning for Unsupervised Video Summarization with Diversity-Representativeness Reward","date":"2017-12-29","arxiv_id":"1801.00054","repositories_listed":6,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/deep-q-learning-from-demonstrations","title":"Deep Q-learning from Demonstrations","date":"2017-04-12","arxiv_id":"1704.03732","repositories_listed":6,"syntology":null},{"url":"/paper/reflexion-language-agents-with-verbal","title":"Reflexion: Language Agents with Verbal Reinforcement Learning","date":"2023-03-20","arxiv_id":"2303.11366","repositories_listed":5,"syntology":{"n":9,"n_ran":2,"n_unverified":7,"n_pointer_only":0}},{"url":"/paper/neur2sp-neural-two-stage-stochastic","title":"Neur2SP: Neural Two-Stage Stochastic Programming","date":"2022-05-20","arxiv_id":"2205.12006","repositories_listed":5,"syntology":{"n":10,"n_ran":5,"n_unverified":5,"n_pointer_only":10}},{"url":"/paper/safe-learning-in-robotics-from-learning-based","title":"Safe Learning in Robotics: From Learning-Based Control to Safe Reinforcement Learning","date":"2021-08-13","arxiv_id":"2108.06266","repositories_listed":5,"syntology":null},{"url":"/paper/iq-learn-inverse-soft-q-learning-for","title":"IQ-Learn: Inverse soft-Q Learning for Imitation","date":"2021-06-23","arxiv_id":"2106.12142","repositories_listed":5,"syntology":{"n":3,"n_ran":2,"n_unverified":1,"n_pointer_only":3}},{"url":"/paper/an-introduction-to-deep-reinforcement","title":"An Introduction to Deep Reinforcement Learning","date":"2018-11-30","arxiv_id":"1811.12560","repositories_listed":5,"syntology":null},{"url":"/paper/deep-reinforcement-learning-based","title":"Deep Reinforcement Learning based Recommendation with Explicit User-Item Interactions Modeling","date":"2018-10-29","arxiv_id":"1810.12027","repositories_listed":5,"syntology":null},{"url":"/paper/medsts-a-resource-for-clinical-semantic","title":"MedSTS: A Resource for Clinical Semantic Textual Similarity","date":"2018-08-28","arxiv_id":"1808.09397","repositories_listed":5,"syntology":null},{"url":"/paper/txagent-an-ai-agent-for-therapeutic-reasoning","title":"TxAgent: An AI Agent for Therapeutic Reasoning Across a Universe of Tools","date":"2025-03-14","arxiv_id":"2503.10970","repositories_listed":4,"syntology":{"n":4,"n_ran":0,"n_unverified":4,"n_pointer_only":0}}],"syntology_records":23,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}