{"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/deep-reinforcement-learning/papers/14","list_of":"/task/deep-reinforcement-learning","task":"Deep 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":14,"pages_in_order":59,"rows_per_page":100,"rows":[1301,1400],"of":5822,"counts":{"archive_papers_tagged":5822,"with_a_code_link":1739,"where_syntology_ran_a_sample":398,"not_listed_spam_title":0,"listed":5822,"listed_where_code_ran":398,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":340,"every_run_a_failure_of_syntologys_instrument":58,"listed_with_a_run_with_no_instrument_failure":340,"listed_every_run_a_failure_of_syntologys_instrument":58,"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/deep-reinforcement-learning","prev":"/task/deep-reinforcement-learning/papers/13","next":"/task/deep-reinforcement-learning/papers/15","papers":[{"url":"/paper/symbolic-relational-deep-reinforcement","slug":"symbolic-relational-deep-reinforcement","title":"Symbolic Relational Deep Reinforcement Learning based on Graph Neural Networks and Autoregressive Policy Decomposition","date":"2020-09-25","arxiv_id":"2009.12462","repositories_listed":1,"syntology":null},{"url":"/paper/a-centralised-soft-actor-critic-deep","slug":"a-centralised-soft-actor-critic-deep","title":"A Centralised Soft Actor Critic Deep Reinforcement Learning Approach to District Demand Side Management through CityLearn","date":"2020-09-22","arxiv_id":"2009.10562","repositories_listed":1,"syntology":null},{"url":"/paper/structure-guided-processing-path-optimization","slug":"structure-guided-processing-path-optimization","title":"Deep Reinforcement Learning Methods for Structure-Guided Processing Path Optimization","date":"2020-09-21","arxiv_id":"2009.09706","repositories_listed":1,"syntology":null},{"url":"/paper/grac-self-guided-and-self-regularized-actor","slug":"grac-self-guided-and-self-regularized-actor","title":"GRAC: Self-Guided and Self-Regularized Actor-Critic","date":"2020-09-18","arxiv_id":"2009.08973","repositories_listed":1,"syntology":null},{"url":"/paper/rlzoo-a-comprehensive-and-adaptive","slug":"rlzoo-a-comprehensive-and-adaptive","title":"Efficient Reinforcement Learning Development with RLzoo","date":"2020-09-18","arxiv_id":"2009.08644","repositories_listed":1,"syntology":null},{"url":"/paper/srec-proactive-self-remedy-of-energy","slug":"srec-proactive-self-remedy-of-energy","title":"SREC: Proactive Self-Remedy of Energy-Constrained UAV-Based Networks via Deep Reinforcement Learning","date":"2020-09-17","arxiv_id":"2009.08528","repositories_listed":1,"syntology":null},{"url":"/paper/meta-aad-active-anomaly-detection-with-deep","slug":"meta-aad-active-anomaly-detection-with-deep","title":"Meta-AAD: Active Anomaly Detection with Deep Reinforcement Learning","date":"2020-09-16","arxiv_id":"2009.07415","repositories_listed":1,"syntology":null},{"url":"/paper/deep-actor-critic-learning-for-distributed","slug":"deep-actor-critic-learning-for-distributed","title":"Deep Actor-Critic Learning for Distributed Power Control in Wireless Mobile Networks","date":"2020-09-14","arxiv_id":"2009.06681","repositories_listed":1,"syntology":null},{"url":"/paper/vacsim-learning-effective-strategies-for","slug":"vacsim-learning-effective-strategies-for","title":"VacSIM: Learning Effective Strategies for COVID-19 Vaccine Distribution using Reinforcement Learning","date":"2020-09-14","arxiv_id":"2009.06602","repositories_listed":1,"syntology":null},{"url":"/paper/physically-embedded-planning-problems-new","slug":"physically-embedded-planning-problems-new","title":"Physically Embedded Planning Problems: New Challenges for Reinforcement Learning","date":"2020-09-11","arxiv_id":"2009.05524","repositories_listed":1,"syntology":null},{"url":"/paper/tripletree-a-versatile-interpretable","slug":"tripletree-a-versatile-interpretable","title":"TripleTree: A Versatile Interpretable Representation of Black Box Agents and their Environments","date":"2020-09-10","arxiv_id":"2009.04743","repositories_listed":1,"syntology":null},{"url":"/paper/deep-active-inference-for-partially","slug":"deep-active-inference-for-partially","title":"Deep Active Inference for Partially Observable MDPs","date":"2020-09-08","arxiv_id":"2009.03622","repositories_listed":1,"syntology":null},{"url":"/paper/dexterous-robotic-grasping-with-object","slug":"dexterous-robotic-grasping-with-object","title":"Learning Dexterous Grasping with Object-Centric Visual Affordances","date":"2020-09-03","arxiv_id":"2009.01439","repositories_listed":1,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":6,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":1,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/dexterous-robotic-grasping-with-object#ran","syntology_url":"https://syntology.ai/paper/2009.01439","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2009.01439"}},"official":{"repos":["priyankamandikal/graff"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/sample-efficient-automated-deep-reinforcement","slug":"sample-efficient-automated-deep-reinforcement","title":"Sample-Efficient Automated Deep Reinforcement Learning","date":"2020-09-03","arxiv_id":"2009.01555","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/sample-efficient-automated-deep-reinforcement#ran","syntology_url":"https://syntology.ai/paper/2009.01555","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2009.01555"}},"official":{"repos":["automl/SEARL"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/allenact-a-framework-for-embodied-ai-research","slug":"allenact-a-framework-for-embodied-ai-research","title":"AllenAct: A Framework for Embodied AI Research","date":"2020-08-28","arxiv_id":"2008.12760","repositories_listed":1,"syntology":null},{"url":"/paper/learning-off-policy-with-online-planning","slug":"learning-off-policy-with-online-planning","title":"Learning Off-Policy with Online Planning","date":"2020-08-23","arxiv_id":"2008.10066","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/learning-off-policy-with-online-planning#ran","syntology_url":"https://syntology.ai/paper/2008.10066","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2008.10066"}},"official":null}},{"url":"/paper/social-aware-incentive-mechanism-for","slug":"social-aware-incentive-mechanism-for","title":"Social-Aware Incentive Mechanism for VehicularCrowdsensing by Deep Reinforcement Learning","date":"2020-08-21","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/optimization-of-operation-parameters-towards","slug":"optimization-of-operation-parameters-towards","title":"Optimal control towards sustainable wastewater treatment plants based on multi-agent reinforcement learning","date":"2020-08-19","arxiv_id":"2008.10417","repositories_listed":1,"syntology":null},{"url":"/paper/learning-fair-policies-in-multiobjective-deep","slug":"learning-fair-policies-in-multiobjective-deep","title":"Learning Fair Policies in Multiobjective (Deep) Reinforcement Learning with Average and Discounted Rewards","date":"2020-08-18","arxiv_id":"2008.07773","repositories_listed":1,"syntology":null},{"url":"/paper/towards-closing-the-sim-to-real-gap-in","slug":"towards-closing-the-sim-to-real-gap-in","title":"Towards Closing the Sim-to-Real Gap in Collaborative Multi-Robot Deep Reinforcement Learning","date":"2020-08-18","arxiv_id":"2008.07875","repositories_listed":1,"syntology":null},{"url":"/paper/towards-sample-efficient-agents-through","slug":"towards-sample-efficient-agents-through","title":"Towards Sample Efficient Agents through Algorithmic Alignment","date":"2020-08-07","arxiv_id":"2008.03229","repositories_listed":1,"syntology":null},{"url":"/paper/contrastive-variational-model-based","slug":"contrastive-variational-model-based","title":"Contrastive Variational Reinforcement Learning for Complex Observations","date":"2020-08-06","arxiv_id":"2008.02430","repositories_listed":1,"syntology":null},{"url":"/paper/deep-reinforcement-learning-for-tactile","slug":"deep-reinforcement-learning-for-tactile","title":"Deep Reinforcement Learning for Tactile Robotics: Learning to Type on a Braille Keyboard","date":"2020-08-06","arxiv_id":"2008.02646","repositories_listed":1,"syntology":null},{"url":"/paper/fast-adaptive-task-offloading-in-edge","slug":"fast-adaptive-task-offloading-in-edge","title":"Fast Adaptive Task Offloading in Edge Computing based on Meta Reinforcement Learning","date":"2020-08-05","arxiv_id":"2008.02033","repositories_listed":1,"syntology":null},{"url":"/paper/queueing-network-controls-via-deep","slug":"queueing-network-controls-via-deep","title":"Queueing Network Controls via Deep Reinforcement Learning","date":"2020-07-31","arxiv_id":"2008.01644","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/queueing-network-controls-via-deep#ran","syntology_url":"https://syntology.ai/paper/2008.01644","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2008.01644"}},"official":null}},{"url":"/paper/combining-deep-reinforcement-learning-and-1","slug":"combining-deep-reinforcement-learning-and-1","title":"Combining Deep Reinforcement Learning and Search for Imperfect-Information Games","date":"2020-07-27","arxiv_id":"2007.13544","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/combining-deep-reinforcement-learning-and-1#ran","syntology_url":"https://syntology.ai/paper/2007.13544","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.13544"}},"official":{"repos":["facebookresearch/rebel"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/human-preference-scaling-with-demonstrations","slug":"human-preference-scaling-with-demonstrations","title":"Weak Human Preference Supervision For Deep Reinforcement Learning","date":"2020-07-25","arxiv_id":"2007.12904","repositories_listed":1,"syntology":null},{"url":"/paper/autonomous-exploration-under-uncertainty-via","slug":"autonomous-exploration-under-uncertainty-via","title":"Autonomous Exploration Under Uncertainty via Deep Reinforcement Learning on Graphs","date":"2020-07-24","arxiv_id":"2007.12640","repositories_listed":1,"syntology":null},{"url":"/paper/integrating-deep-reinforcement-learning","slug":"integrating-deep-reinforcement-learning","title":"Integrating Deep Reinforcement Learning Networks with Health System Simulations","date":"2020-07-21","arxiv_id":"2008.07434","repositories_listed":1,"syntology":null},{"url":"/paper/joint-trajectory-and-passive-beamforming","slug":"joint-trajectory-and-passive-beamforming","title":"Joint Trajectory and Passive Beamforming Design for Intelligent Reflecting Surface-Aided UAV Communications: A Deep Reinforcement Learning Approach","date":"2020-07-16","arxiv_id":"2007.08380","repositories_listed":1,"syntology":null},{"url":"/paper/weighing-counts-sequential-crowd-counting-by","slug":"weighing-counts-sequential-crowd-counting-by","title":"Weighing Counts: Sequential Crowd Counting by Reinforcement Learning","date":"2020-07-16","arxiv_id":"2007.08260","repositories_listed":1,"syntology":null},{"url":"/paper/reinforcement-learning-of-musculoskeletal","slug":"reinforcement-learning-of-musculoskeletal","title":"Reinforcement Learning of Musculoskeletal Control from Functional Simulations","date":"2020-07-13","arxiv_id":"2007.06669","repositories_listed":1,"syntology":null},{"url":"/paper/data-efficient-reinforcement-learning-with-1","slug":"data-efficient-reinforcement-learning-with-1","title":"Data-Efficient Reinforcement Learning with Self-Predictive Representations","date":"2020-07-12","arxiv_id":"2007.05929","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/data-efficient-reinforcement-learning-with-1#ran","syntology_url":"https://syntology.ai/paper/2007.05929","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.05929"}},"official":{"repos":["mila-iqia/spr"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/long-term-planning-with-deep-reinforcement","slug":"long-term-planning-with-deep-reinforcement","title":"Long-Term Planning with Deep Reinforcement Learning on Autonomous Drones","date":"2020-07-11","arxiv_id":"2007.05694","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/long-term-planning-with-deep-reinforcement#ran","syntology_url":"https://syntology.ai/paper/2007.05694","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.05694"}},"official":{"repos":["ugurkanates/NeurIRS2019DroneChallengeRL"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/sunrise-a-simple-unified-framework-for","slug":"sunrise-a-simple-unified-framework-for","title":"SUNRISE: A Simple Unified Framework for Ensemble Learning in Deep Reinforcement Learning","date":"2020-07-09","arxiv_id":"2007.04938","repositories_listed":1,"syntology":null},{"url":"/paper/guided-exploration-with-proximal-policy","slug":"guided-exploration-with-proximal-policy","title":"Guided Exploration with Proximal Policy Optimization using a Single Demonstration","date":"2020-07-07","arxiv_id":"2007.03328","repositories_listed":1,"syntology":null},{"url":"/paper/lfq-online-learning-of-per-flow-queuing","slug":"lfq-online-learning-of-per-flow-queuing","title":"LFQ: Online Learning of Per-flow Queuing Policies using Deep Reinforcement Learning","date":"2020-07-06","arxiv_id":"2007.02735","repositories_listed":1,"syntology":null},{"url":"/paper/verifiably-safe-exploration-for-end-to-end","slug":"verifiably-safe-exploration-for-end-to-end","title":"Verifiably Safe Exploration for End-to-End Reinforcement Learning","date":"2020-07-02","arxiv_id":"2007.01223","repositories_listed":1,"syntology":null},{"url":"/paper/group-equivariant-deep-reinforcement-learning","slug":"group-equivariant-deep-reinforcement-learning","title":"Group Equivariant Deep Reinforcement Learning","date":"2020-07-01","arxiv_id":"2007.03437","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"0 ran · 1 unverified","sample_list":"/paper/group-equivariant-deep-reinforcement-learning#ran","syntology_url":"https://syntology.ai/paper/2007.03437","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.03437"}},"official":{"repos":["arnab39/EquivariantDQN"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/deep-feature-space-a-geometrical-perspective","slug":"deep-feature-space-a-geometrical-perspective","title":"Deep Feature Space: A Geometrical Perspective","date":"2020-06-30","arxiv_id":"2007.00062","repositories_listed":1,"syntology":null},{"url":"/paper/explanation-augmented-feedback-in-human-in","slug":"explanation-augmented-feedback-in-human-in","title":"Widening the Pipeline in Human-Guided Reinforcement Learning with Explanation and Context-Aware Data Augmentation","date":"2020-06-26","arxiv_id":"2006.14804","repositories_listed":1,"syntology":null},{"url":"/paper/online-3d-bin-packing-with-constrained-deep","slug":"online-3d-bin-packing-with-constrained-deep","title":"Online 3D Bin Packing with Constrained Deep Reinforcement Learning","date":"2020-06-26","arxiv_id":"2006.14978","repositories_listed":1,"syntology":null},{"url":"/paper/policy-gnn-aggregation-optimization-for-graph","slug":"policy-gnn-aggregation-optimization-for-graph","title":"Policy-GNN: Aggregation Optimization for Graph Neural Networks","date":"2020-06-26","arxiv_id":"2006.15097","repositories_listed":1,"syntology":null},{"url":"/paper/automatic-data-augmentation-for","slug":"automatic-data-augmentation-for","title":"Automatic Data Augmentation for Generalization in Deep Reinforcement Learning","date":"2020-06-23","arxiv_id":"2006.12862","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/automatic-data-augmentation-for#ran","syntology_url":"https://syntology.ai/paper/2006.12862","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.12862"}},"official":{"repos":["rraileanu/auto-drac"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/experience-replay-with-likelihood-free","slug":"experience-replay-with-likelihood-free","title":"Experience Replay with Likelihood-free Importance Weights","date":"2020-06-23","arxiv_id":"2006.13169","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/experience-replay-with-likelihood-free#ran","syntology_url":"https://syntology.ai/paper/2006.13169","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.13169"}},"official":null}},{"url":"/paper/automated-optical-multi-layer-design-via-deep","slug":"automated-optical-multi-layer-design-via-deep","title":"Automated Optical Multi-layer Design via Deep Reinforcement Learning","date":"2020-06-21","arxiv_id":"2006.11940","repositories_listed":1,"syntology":null},{"url":"/paper/dream-deep-regret-minimization-with-advantage","slug":"dream-deep-regret-minimization-with-advantage","title":"DREAM: Deep Regret minimization with Advantage baselines and Model-free learning","date":"2020-06-18","arxiv_id":"2006.10410","repositories_listed":1,"syntology":null},{"url":"/paper/forgetful-experience-replay-in-hierarchical","slug":"forgetful-experience-replay-in-hierarchical","title":"Forgetful Experience Replay in Hierarchical Reinforcement Learning from Demonstrations","date":"2020-06-17","arxiv_id":"2006.09939","repositories_listed":1,"syntology":null},{"url":"/paper/learning-to-track-dynamic-targets-in","slug":"learning-to-track-dynamic-targets-in","title":"Learning to Track Dynamic Targets in Partially Known Environments","date":"2020-06-17","arxiv_id":"2006.10190","repositories_listed":1,"syntology":null},{"url":"/paper/learning-what-to-defer-for-maximum","slug":"learning-what-to-defer-for-maximum","title":"Learning What to Defer for Maximum Independent Sets","date":"2020-06-17","arxiv_id":"2006.09607","repositories_listed":1,"syntology":null},{"url":"/paper/nnc-neural-network-control-of-dynamical","slug":"nnc-neural-network-control-of-dynamical","title":"Neural Ordinary Differential Equation Control of Dynamics on Graphs","date":"2020-06-17","arxiv_id":"2006.09773","repositories_listed":1,"syntology":{"n":18,"n_ran":18,"n_constructed":0,"n_ran_checked":18,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":18,"n_pointer_only":0,"phrase":"18 ran (of which 0 constructed an object rather than computing a result; 18 with no instrument failure: 0 honoured, 0 violated, 18 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/nnc-neural-network-control-of-dynamical#ran","syntology_url":"https://syntology.ai/paper/2006.09773","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.09773"}},"official":{"repos":["asikist/nnc"],"state":"official (archive's flag): 18 ran","n_ran":18,"n_constructed":0,"n_ran_no_instrument_failure":18,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/opponent-modelling-with-local-information","slug":"opponent-modelling-with-local-information","title":"Agent Modelling under Partial Observability for Deep Reinforcement Learning","date":"2020-06-16","arxiv_id":"2006.09447","repositories_listed":1,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":3,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":1,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/opponent-modelling-with-local-information#ran","syntology_url":"https://syntology.ai/paper/2006.09447","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.09447"}},"official":{"repos":["uoe-agents/LIAM"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/mutual-information-based-knowledge-transfer","slug":"mutual-information-based-knowledge-transfer","title":"Mutual Information Based Knowledge Transfer Under State-Action Dimension Mismatch","date":"2020-06-12","arxiv_id":"2006.07041","repositories_listed":1,"syntology":null},{"url":"/paper/deep-reinforcement-learning-for-human-like","slug":"deep-reinforcement-learning-for-human-like","title":"Deep Reinforcement Learning for Human-Like Driving Policies in Collision Avoidance Tasks of Self-Driving Cars","date":"2020-06-07","arxiv_id":"2006.04218","repositories_listed":1,"syntology":null},{"url":"/paper/dual-policy-distillation","slug":"dual-policy-distillation","title":"Dual Policy Distillation","date":"2020-06-07","arxiv_id":"2006.04061","repositories_listed":1,"syntology":{"n":17,"n_ran":11,"n_constructed":0,"n_ran_checked":11,"n_instrument":0,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":11,"n_pointer_only":17,"phrase":"11 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; 0 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/dual-policy-distillation#ran","syntology_url":"https://syntology.ai/paper/2006.04061","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.04061"}},"official":null}},{"url":"/paper/optimization-and-passive-flow-control-using","slug":"optimization-and-passive-flow-control-using","title":"Single-step deep reinforcement learning for open-loop control of laminar and turbulent flows","date":"2020-06-04","arxiv_id":"2006.02979","repositories_listed":1,"syntology":null},{"url":"/paper/solving-hard-ai-planning-instances-using","slug":"solving-hard-ai-planning-instances-using","title":"Solving Hard AI Planning Instances Using Curriculum-Driven Deep Reinforcement Learning","date":"2020-06-04","arxiv_id":"2006.02689","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/solving-hard-ai-planning-instances-using#ran","syntology_url":"https://syntology.ai/paper/2006.02689","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.02689"}},"official":null}},{"url":"/paper/interferobot-aligning-an-optical","slug":"interferobot-aligning-an-optical","title":"Interferobot: aligning an optical interferometer by a reinforcement learning agent","date":"2020-06-03","arxiv_id":"2006.02252","repositories_listed":1,"syntology":null},{"url":"/paper/combining-reinforcement-learning-and-1","slug":"combining-reinforcement-learning-and-1","title":"Combining Reinforcement Learning and Constraint Programming for Combinatorial Optimization","date":"2020-06-02","arxiv_id":"2006.01610","repositories_listed":1,"syntology":null},{"url":"/paper/learning-optimal-environments-using-projected","slug":"learning-optimal-environments-using-projected","title":"Jointly Learning Environments and Control Policies with Projected Stochastic Gradient Ascent","date":"2020-06-02","arxiv_id":"2006.01738","repositories_listed":1,"syntology":null},{"url":"/paper/sim2real-for-peg-hole-insertion-with-eye-in","slug":"sim2real-for-peg-hole-insertion-with-eye-in","title":"Sim2Real for Peg-Hole Insertion with Eye-in-Hand Camera","date":"2020-05-29","arxiv_id":"2005.14401","repositories_listed":1,"syntology":null},{"url":"/paper/parameter-sharing-is-surprisingly-useful-for","slug":"parameter-sharing-is-surprisingly-useful-for","title":"Revisiting Parameter Sharing in Multi-Agent Deep Reinforcement Learning","date":"2020-05-27","arxiv_id":"2005.13625","repositories_listed":1,"syntology":null},{"url":"/paper/decentralized-deep-reinforcement-learning-for","slug":"decentralized-deep-reinforcement-learning-for","title":"Decentralized Deep Reinforcement Learning for a Distributed and Adaptive Locomotion Controller of a Hexapod Robot","date":"2020-05-21","arxiv_id":"2005.11164","repositories_listed":1,"syntology":null},{"url":"/paper/ultrasound-video-summarization-using-deep","slug":"ultrasound-video-summarization-using-deep","title":"Ultrasound Video Summarization using Deep Reinforcement Learning","date":"2020-05-19","arxiv_id":"2005.09531","repositories_listed":1,"syntology":null},{"url":"/paper/deepsocs-a-neural-scheduler-for-heterogeneous","slug":"deepsocs-a-neural-scheduler-for-heterogeneous","title":"DeepSoCS: A Neural Scheduler for Heterogeneous System-on-Chip (SoC) Resource Scheduling","date":"2020-05-15","arxiv_id":"2005.07666","repositories_listed":1,"syntology":null},{"url":"/paper/delay-aware-multi-agent-reinforcement","slug":"delay-aware-multi-agent-reinforcement","title":"Delay-Aware Multi-Agent Reinforcement Learning for Cooperative and Competitive Environments","date":"2020-05-11","arxiv_id":"2005.05441","repositories_listed":1,"syntology":null},{"url":"/paper/carl-controllable-agent-with-reinforcement","slug":"carl-controllable-agent-with-reinforcement","title":"CARL: Controllable Agent with Reinforcement Learning for Quadruped Locomotion","date":"2020-05-07","arxiv_id":"2005.03288","repositories_listed":1,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/carl-controllable-agent-with-reinforcement#ran","syntology_url":"https://syntology.ai/paper/2005.03288","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.03288"}},"official":{"repos":["inventec-ai-center/carl-siggraph2020"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/explain-your-move-understanding-agent-actions","slug":"explain-your-move-understanding-agent-actions","title":"Explain Your Move: Understanding Agent Actions Using Focused Feature Saliency","date":"2020-05-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/logic-and-the-2-simplicial-transformer-1","slug":"logic-and-the-2-simplicial-transformer-1","title":"Logic and the 2-Simplicial Transformer","date":"2020-05-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/deep-reinforcement-learning-with-graph-based","slug":"deep-reinforcement-learning-with-graph-based","title":"Graph-based State Representation for Deep Reinforcement Learning","date":"2020-04-29","arxiv_id":"2004.13965","repositories_listed":1,"syntology":null},{"url":"/paper/the-ai-economist-improving-equality-and","slug":"the-ai-economist-improving-equality-and","title":"The AI Economist: Improving Equality and Productivity with AI-Driven Tax Policies","date":"2020-04-28","arxiv_id":"2004.13332","repositories_listed":1,"syntology":null},{"url":"/paper/reinforcement-learning-generalization-with","slug":"reinforcement-learning-generalization-with","title":"Reinforcement Learning Generalization with Surprise Minimization","date":"2020-04-26","arxiv_id":"2004.12399","repositories_listed":1,"syntology":null},{"url":"/paper/curiosity-driven-energy-efficient-worker","slug":"curiosity-driven-energy-efficient-worker","title":"Curiosity-Driven Energy-Efficient Worker Scheduling in Vehicular Crowdsourcing: A Deep Reinforcement Learning Approach","date":"2020-04-24","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/self-paced-deep-reinforcement-learning","slug":"self-paced-deep-reinforcement-learning","title":"Self-Paced Deep Reinforcement Learning","date":"2020-04-24","arxiv_id":"2004.11812","repositories_listed":1,"syntology":null},{"url":"/paper/a-text-based-deep-reinforcement-learning","slug":"a-text-based-deep-reinforcement-learning","title":"A Text-based Deep Reinforcement Learning Framework for Interactive Recommendation","date":"2020-04-14","arxiv_id":"2004.06651","repositories_listed":1,"syntology":null},{"url":"/paper/self-punishment-and-reward-backfill-for-deep","slug":"self-punishment-and-reward-backfill-for-deep","title":"Self Punishment and Reward Backfill for Deep Q-Learning","date":"2020-04-10","arxiv_id":"2004.05002","repositories_listed":1,"syntology":null},{"url":"/paper/topological-quantum-compiling-with","slug":"topological-quantum-compiling-with","title":"Topological Quantum Compiling with Reinforcement Learning","date":"2020-04-09","arxiv_id":"2004.04743","repositories_listed":1,"syntology":null},{"url":"/paper/an-application-of-deep-reinforcement-learning","slug":"an-application-of-deep-reinforcement-learning","title":"An Application of Deep Reinforcement Learning to Algorithmic Trading","date":"2020-04-07","arxiv_id":"2004.06627","repositories_listed":1,"syntology":null},{"url":"/paper/learning-2-opt-heuristics-for-the-traveling","slug":"learning-2-opt-heuristics-for-the-traveling","title":"Learning 2-opt Heuristics for the Traveling Salesman Problem via Deep Reinforcement Learning","date":"2020-04-03","arxiv_id":"2004.01608","repositories_listed":1,"syntology":null},{"url":"/paper/mri-reconstruction-with-interpretable-pixel","slug":"mri-reconstruction-with-interpretable-pixel","title":"MRI Reconstruction with Interpretable Pixel-Wise Operations Using Reinforcement Learning","date":"2020-04-03","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/action-space-shaping-in-deep-reinforcement","slug":"action-space-shaping-in-deep-reinforcement","title":"Action Space Shaping in Deep Reinforcement Learning","date":"2020-04-02","arxiv_id":"2004.00980","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/action-space-shaping-in-deep-reinforcement#ran","syntology_url":"https://syntology.ai/paper/2004.00980","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.00980"}},"official":{"repos":["Miffyli/rl-action-space-shaping"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/learning-sparse-rewarded-tasks-from-sub","slug":"learning-sparse-rewarded-tasks-from-sub","title":"Learning Sparse Rewarded Tasks from Sub-Optimal Demonstrations","date":"2020-04-01","arxiv_id":"2004.00530","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":2,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 2 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/learning-sparse-rewarded-tasks-from-sub#ran","syntology_url":"https://syntology.ai/paper/2004.00530","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.00530"}},"official":null}},{"url":"/paper/obstacle-tower-without-human-demonstrations","slug":"obstacle-tower-without-human-demonstrations","title":"Obstacle Tower Without Human Demonstrations: How Far a Deep Feed-Forward Network Goes with Reinforcement Learning","date":"2020-04-01","arxiv_id":"2004.00567","repositories_listed":1,"syntology":null},{"url":"/paper/augmented-q-imitation-learning-aqil","slug":"augmented-q-imitation-learning-aqil","title":"Augmented Q Imitation Learning (AQIL)","date":"2020-03-31","arxiv_id":"2004.00993","repositories_listed":1,"syntology":null},{"url":"/paper/optical-non-line-of-sight-physics-based-3d","slug":"optical-non-line-of-sight-physics-based-3d","title":"Optical Non-Line-of-Sight Physics-based 3D Human Pose Estimation","date":"2020-03-31","arxiv_id":"2003.14414","repositories_listed":1,"syntology":null},{"url":"/paper/deep-reinforcement-learning-for-large-scale","slug":"deep-reinforcement-learning-for-large-scale","title":"Deep reinforcement learning for large-scale epidemic control","date":"2020-03-30","arxiv_id":"2003.13676","repositories_listed":1,"syntology":null},{"url":"/paper/suphx-mastering-mahjong-with-deep","slug":"suphx-mastering-mahjong-with-deep","title":"Suphx: Mastering Mahjong with Deep Reinforcement Learning","date":"2020-03-30","arxiv_id":"2003.13590","repositories_listed":1,"syntology":null},{"url":"/paper/using-deep-reinforcement-learning-methods-for","slug":"using-deep-reinforcement-learning-methods-for","title":"Using Deep Reinforcement Learning Methods for Autonomous Vessels in 2D Environments","date":"2020-03-23","arxiv_id":"2003.10249","repositories_listed":1,"syntology":null},{"url":"/paper/l2b-learning-to-balance-the-safety-efficiency","slug":"l2b-learning-to-balance-the-safety-efficiency","title":"L2B: Learning to Balance the Safety-Efficiency Trade-off in Interactive Crowd-aware Robot Navigation","date":"2020-03-20","arxiv_id":"2003.09207","repositories_listed":1,"syntology":null},{"url":"/paper/social-navigation-with-human-empowerment","slug":"social-navigation-with-human-empowerment","title":"Social Navigation with Human Empowerment driven Deep Reinforcement Learning","date":"2020-03-18","arxiv_id":"2003.08158","repositories_listed":1,"syntology":null},{"url":"/paper/simultaneous-navigation-and-radio-mapping-for","slug":"simultaneous-navigation-and-radio-mapping-for","title":"Simultaneous Navigation and Radio Mapping for Cellular-Connected UAV with Deep Reinforcement Learning","date":"2020-03-17","arxiv_id":"2003.07574","repositories_listed":1,"syntology":null},{"url":"/paper/self-supervised-discovering-of-causal","slug":"self-supervised-discovering-of-causal","title":"Self-Supervised Discovering of Interpretable Features for Reinforcement Learning","date":"2020-03-16","arxiv_id":"2003.07069","repositories_listed":1,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":2,"n_instrument":4,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":2,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/self-supervised-discovering-of-causal#ran","syntology_url":"https://syntology.ai/paper/2003.07069","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.07069"}},"official":{"repos":["shiwj16/SSINet"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/deep-deterministic-portfolio-optimization","slug":"deep-deterministic-portfolio-optimization","title":"Deep Deterministic Portfolio Optimization","date":"2020-03-13","arxiv_id":"2003.06497","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/deep-deterministic-portfolio-optimization#ran","syntology_url":"https://syntology.ai/paper/2003.06497","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.06497"}},"official":{"repos":["CFMTech/Deep-RL-for-Portfolio-Optimization"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/explore-and-exploit-with-heterotic-line","slug":"explore-and-exploit-with-heterotic-line","title":"Explore and Exploit with Heterotic Line Bundle Models","date":"2020-03-10","arxiv_id":"2003.04817","repositories_listed":1,"syntology":null},{"url":"/paper/stable-policy-optimization-via-off-policy","slug":"stable-policy-optimization-via-off-policy","title":"Stable Policy Optimization via Off-Policy Divergence Regularization","date":"2020-03-09","arxiv_id":"2003.04108","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/stable-policy-optimization-via-off-policy#ran","syntology_url":"https://syntology.ai/paper/2003.04108","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.04108"}},"official":{"repos":["facebookresearch/ppo-dice"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/learning-view-and-target-invariant-visual","slug":"learning-view-and-target-invariant-visual","title":"Learning View and Target Invariant Visual Servoing for Navigation","date":"2020-03-04","arxiv_id":"2003.02327","repositories_listed":1,"syntology":null},{"url":"/paper/can-increasing-input-dimensionality-improve","slug":"can-increasing-input-dimensionality-improve","title":"Can Increasing Input Dimensionality Improve Deep Reinforcement Learning?","date":"2020-03-03","arxiv_id":"2003.01629","repositories_listed":1,"syntology":null},{"url":"/paper/contention-window-optimization-in-ieee","slug":"contention-window-optimization-in-ieee","title":"Contention Window Optimization in IEEE 802.11ax Networks with Deep Reinforcement Learning","date":"2020-03-03","arxiv_id":"2003.01492","repositories_listed":1,"syntology":null},{"url":"/paper/embodied-synaptic-plasticity-with-online","slug":"embodied-synaptic-plasticity-with-online","title":"Embodied Synaptic Plasticity with Online Reinforcement learning","date":"2020-03-03","arxiv_id":"2003.01431","repositories_listed":1,"syntology":null},{"url":"/paper/autophase-juggling-hls-phase-orderings-in","slug":"autophase-juggling-hls-phase-orderings-in","title":"AutoPhase: Juggling HLS Phase Orderings in Random Forests with Deep Reinforcement Learning","date":"2020-03-02","arxiv_id":"2003.00671","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"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) · 0 unverified","sample_list":"/paper/autophase-juggling-hls-phase-orderings-in#ran","syntology_url":"https://syntology.ai/paper/2003.00671","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.00671"}},"official":{"repos":["ucb-bar/autophase"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}}],"record_sha256":"45dc8db88aa6a504bd53ea94eaed20b1b4e99f0b713201df158d696a72d35907","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}