{"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/safe-exploration","name":"Safe Exploration","slug":"safe-exploration","description_markdown":"**Safe Exploration** is an approach to collect ground truth data by safely interacting with the environment.\n\n\n<span class=\"description-source\">Source: [Chance-Constrained Trajectory Optimization for Safe Exploration and Learning of Nonlinear Systems ](https://arxiv.org/abs/2005.04374)</span>","categories":[{"name":"Robots","url":"/area/robots"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"derived"},"counts":{"papers_tagged":135,"papers_with_code":43,"benchmarks":0,"benchmark_tables_in_archive":0,"benchmark_tables_shown":0,"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":0,"subtasks":0,"parent_tasks":0},"benchmarks":[],"datasets":[],"subtasks":[],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":2,"rows_per_page":100,"shown":100,"of":135,"of_with_code":43,"tagged_in_all":135,"counts":{"archive_papers_tagged":135,"with_a_code_link":43,"where_syntology_ran_a_sample":12,"not_listed_spam_title":0,"listed":135,"listed_where_code_ran":12,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":11,"every_run_a_failure_of_syntologys_instrument":1,"listed_with_a_run_with_no_instrument_failure":11,"listed_every_run_a_failure_of_syntologys_instrument":1,"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"},"items":[{"url":"/paper/safe-exploration-in-continuous-action-spaces","slug":"safe-exploration-in-continuous-action-spaces","title":"Safe Exploration in Continuous Action Spaces","date":"2018-01-26","arxiv_id":"1801.08757","repositories_listed":6,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"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) · 0 unverified","sample_list":"/paper/safe-exploration-in-continuous-action-spaces#ran","syntology_url":"https://syntology.ai/paper/1801.08757","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1801.08757"}},"official":null}},{"url":"/paper/feasible-actor-critic-constrained","slug":"feasible-actor-critic-constrained","title":"Feasible Actor-Critic: Constrained Reinforcement Learning for Ensuring Statewise Safety","date":"2021-05-22","arxiv_id":"2105.10682","repositories_listed":3,"syntology":{"n":6,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":3,"n_honours":1,"n_violates":0,"n_no_contract":2,"n_pointer_only":1,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/feasible-actor-critic-constrained#ran","syntology_url":"https://syntology.ai/paper/2105.10682","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.10682"}},"official":{"repos":["mahaitongdae/Feasible-Actor-Critic"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/metadrive-composing-diverse-driving-scenarios","slug":"metadrive-composing-diverse-driving-scenarios","title":"MetaDrive: Composing Diverse Driving Scenarios for Generalizable Reinforcement Learning","date":"2021-09-26","arxiv_id":"2109.12674","repositories_listed":2,"syntology":null},{"url":"/paper/safeml-safety-monitoring-of-machine-learning","slug":"safeml-safety-monitoring-of-machine-learning","title":"SafeML: Safety Monitoring of Machine Learning Classifiers through Statistical Difference Measure","date":"2020-05-27","arxiv_id":"2005.13166","repositories_listed":2,"syntology":null},{"url":"/paper/ai-safety-gridworlds","slug":"ai-safety-gridworlds","title":"AI Safety Gridworlds","date":"2017-11-27","arxiv_id":"1711.09883","repositories_listed":2,"syntology":null},{"url":"/paper/confidence-guided-human-ai-collaboration","slug":"confidence-guided-human-ai-collaboration","title":"Confidence-Guided Human-AI Collaboration: Reinforcement Learning with Distributional Proxy Value Propagation for Autonomous Driving","date":"2025-06-04","arxiv_id":"2506.03568","repositories_listed":1,"syntology":null},{"url":"/paper/conrft-a-reinforced-fine-tuning-method-for","slug":"conrft-a-reinforced-fine-tuning-method-for","title":"ConRFT: A Reinforced Fine-tuning Method for VLA Models via Consistency Policy","date":"2025-02-08","arxiv_id":"2502.05450","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":0,"n_honours":3,"n_violates":0,"n_no_contract":2,"n_pointer_only":4,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 3 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/conrft-a-reinforced-fine-tuning-method-for#ran","syntology_url":"https://syntology.ai/paper/2502.05450","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.05450"}},"official":{"repos":["cccedric/conrft"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/handling-long-term-safety-and-uncertainty-in","slug":"handling-long-term-safety-and-uncertainty-in","title":"Handling Long-Term Safety and Uncertainty in Safe Reinforcement Learning","date":"2024-09-18","arxiv_id":"2409.12045","repositories_listed":1,"syntology":null},{"url":"/paper/exterior-penalty-policy-optimization-with","slug":"exterior-penalty-policy-optimization-with","title":"Exterior Penalty Policy Optimization with Penalty Metric Network under Constraints","date":"2024-07-22","arxiv_id":"2407.15537","repositories_listed":1,"syntology":null},{"url":"/paper/transductive-active-learning-with-application","slug":"transductive-active-learning-with-application","title":"Transductive Active Learning with Application to Safe Bayesian Optimization","date":"2024-07-12","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/safe-reinforcement-learning-in-black-box","slug":"safe-reinforcement-learning-in-black-box","title":"Safe Reinforcement Learning in Black-Box Environments via Adaptive Shielding","date":"2024-05-28","arxiv_id":"2405.18180","repositories_listed":1,"syntology":null},{"url":"/paper/a-comparison-of-rl-based-and-pid-controllers","slug":"a-comparison-of-rl-based-and-pid-controllers","title":"A comparison of RL-based and PID controllers for 6-DOF swimming robots: hybrid underwater object tracking","date":"2024-01-29","arxiv_id":"2401.16618","repositories_listed":1,"syntology":null},{"url":"/paper/state-wise-safe-reinforcement-learning-with","slug":"state-wise-safe-reinforcement-learning-with","title":"State-Wise Safe Reinforcement Learning With Pixel Observations","date":"2023-11-03","arxiv_id":"2311.02227","repositories_listed":1,"syntology":{"n":14,"n_ran":12,"n_constructed":0,"n_ran_checked":12,"n_instrument":0,"n_unverified":2,"n_honours":1,"n_violates":1,"n_no_contract":10,"n_pointer_only":14,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 1 honoured, 1 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/state-wise-safe-reinforcement-learning-with#ran","syntology_url":"https://syntology.ai/paper/2311.02227","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.02227"}},"official":{"repos":["simonzhan-code/step-wise_saferl_pixel"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/probabilistic-counterexample-guidance-for","slug":"probabilistic-counterexample-guidance-for","title":"Probabilistic Counterexample Guidance for Safer Reinforcement Learning (Extended Version)","date":"2023-07-10","arxiv_id":"2307.04927","repositories_listed":1,"syntology":null},{"url":"/paper/safe-and-sample-efficient-reinforcement","slug":"safe-and-sample-efficient-reinforcement","title":"Safe and Sample-efficient Reinforcement Learning for Clustered Dynamic Environments","date":"2023-03-24","arxiv_id":"2303.14265","repositories_listed":1,"syntology":null},{"url":"/paper/information-theoretic-safe-exploration-with","slug":"information-theoretic-safe-exploration-with","title":"Information-Theoretic Safe Exploration with Gaussian Processes","date":"2022-12-09","arxiv_id":"2212.04914","repositories_listed":1,"syntology":{"n":9,"n_ran":6,"n_constructed":2,"n_ran_checked":5,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":1,"n_no_contract":4,"n_pointer_only":8,"phrase":"6 ran (of which 2 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 1 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/information-theoretic-safe-exploration-with#ran","syntology_url":"https://syntology.ai/paper/2212.04914","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.04914"}},"official":{"repos":["boschresearch/information-theoretic-safe-exploration"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":2,"n_ran_no_instrument_failure":4,"n_unverified":3,"ran_from_kinds":["found_in_text","official"]}}},{"url":"/paper/benefits-of-monotonicity-in-safe-exploration","slug":"benefits-of-monotonicity-in-safe-exploration","title":"Benefits of Monotonicity in Safe Exploration with Gaussian Processes","date":"2022-11-03","arxiv_id":"2211.01561","repositories_listed":1,"syntology":null},{"url":"/paper/atlas-automate-online-service-configuration","slug":"atlas-automate-online-service-configuration","title":"Atlas: Automate Online Service Configuration in Network Slicing","date":"2022-10-30","arxiv_id":"2210.16902","repositories_listed":1,"syntology":null},{"url":"/paper/the-pump-scheduling-problem-a-real-world","slug":"the-pump-scheduling-problem-a-real-world","title":"The Pump Scheduling Problem: A Real-World Scenario for Reinforcement Learning","date":"2022-10-20","arxiv_id":"2210.11111","repositories_listed":1,"syntology":null},{"url":"/paper/model-based-safe-deep-reinforcement-learning","slug":"model-based-safe-deep-reinforcement-learning","title":"Model-based Safe Deep Reinforcement Learning via a Constrained Proximal Policy Optimization Algorithm","date":"2022-10-14","arxiv_id":"2210.07573","repositories_listed":1,"syntology":{"n":13,"n_ran":9,"n_constructed":0,"n_ran_checked":6,"n_instrument":3,"n_unverified":4,"n_honours":2,"n_violates":0,"n_no_contract":4,"n_pointer_only":8,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 2 honoured, 0 violated, 4 with no contract checked; 3 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/model-based-safe-deep-reinforcement-learning#ran","syntology_url":"https://syntology.ai/paper/2210.07573","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.07573"}},"official":{"repos":["akjayant/mbppol"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/near-optimal-multi-agent-learning-for-safe","slug":"near-optimal-multi-agent-learning-for-safe","title":"Near-Optimal Multi-Agent Learning for Safe Coverage Control","date":"2022-10-12","arxiv_id":"2210.06380","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"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) · 1 unverified","sample_list":"/paper/near-optimal-multi-agent-learning-for-safe#ran","syntology_url":"https://syntology.ai/paper/2210.06380","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.06380"}},"official":{"repos":["manish-pra/safemac"],"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/safe-exploration-method-for-reinforcement","slug":"safe-exploration-method-for-reinforcement","title":"Safe Exploration Method for Reinforcement Learning under Existence of Disturbance","date":"2022-09-30","arxiv_id":"2209.15452","repositories_listed":1,"syntology":null},{"url":"/paper/toward-safe-and-accelerated-deep","slug":"toward-safe-and-accelerated-deep","title":"Toward Safe and Accelerated Deep Reinforcement Learning for Next-Generation Wireless Networks","date":"2022-09-16","arxiv_id":"2209.13532","repositories_listed":1,"syntology":null},{"url":"/paper/enhancing-safe-exploration-using-safety-state","slug":"enhancing-safe-exploration-using-safety-state","title":"Effects of Safety State Augmentation on Safe Exploration","date":"2022-06-06","arxiv_id":"2206.02675","repositories_listed":1,"syntology":null},{"url":"/paper/cup-a-conservative-update-policy-algorithm-1","slug":"cup-a-conservative-update-policy-algorithm-1","title":"CUP: A Conservative Update Policy Algorithm for Safe Reinforcement Learning","date":"2022-02-15","arxiv_id":"2202.07565","repositories_listed":1,"syntology":null},{"url":"/paper/scalable-safe-exploration-for-global","slug":"scalable-safe-exploration-for-global","title":"GoSafeOpt: Scalable Safe Exploration for Global Optimization of Dynamical Systems","date":"2022-01-24","arxiv_id":"2201.09562","repositories_listed":1,"syntology":null},{"url":"/paper/safe-exploration-for-constrained","slug":"safe-exploration-for-constrained","title":"DOPE: Doubly Optimistic and Pessimistic Exploration for Safe Reinforcement Learning","date":"2021-12-01","arxiv_id":"2112.00885","repositories_listed":1,"syntology":null},{"url":"/paper/safe-policy-optimization-with-local","slug":"safe-policy-optimization-with-local","title":"Safe Policy Optimization with Local Generalized Linear Function Approximations","date":"2021-11-09","arxiv_id":"2111.04894","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":5,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/safe-policy-optimization-with-local#ran","syntology_url":"https://syntology.ai/paper/2111.04894","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.04894"}},"official":{"repos":["akifumi-wachi-4/spolf"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/infinite-time-horizon-safety-of-bayesian","slug":"infinite-time-horizon-safety-of-bayesian","title":"Infinite Time Horizon Safety of Bayesian Neural Networks","date":"2021-11-04","arxiv_id":"2111.03165","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"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; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/infinite-time-horizon-safety-of-bayesian#ran","syntology_url":"https://syntology.ai/paper/2111.03165","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.03165"}},"official":{"repos":["mlech26l/bayesian_nn_safety"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/safe-continuous-control-with-constrained","slug":"safe-continuous-control-with-constrained","title":"Safe Continuous Control with Constrained Model-Based Policy Optimization","date":"2021-04-14","arxiv_id":"2104.06922","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":4,"n_pointer_only":1,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 1 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/safe-continuous-control-with-constrained#ran","syntology_url":"https://syntology.ai/paper/2104.06922","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.06922"}},"official":null}},{"url":"/paper/autonomous-uav-exploration-of-dynamic","slug":"autonomous-uav-exploration-of-dynamic","title":"Autonomous UAV Exploration of Dynamic Environments via Incremental Sampling and Probabilistic Roadmap","date":"2020-10-14","arxiv_id":"2010.07429","repositories_listed":1,"syntology":null},{"url":"/paper/align-rudder-learning-from-few-demonstrations","slug":"align-rudder-learning-from-few-demonstrations","title":"Align-RUDDER: Learning From Few Demonstrations by Reward Redistribution","date":"2020-09-29","arxiv_id":"2009.14108","repositories_listed":1,"syntology":{"n":3,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 3 unverified","sample_list":"/paper/align-rudder-learning-from-few-demonstrations#ran","syntology_url":"https://syntology.ai/paper/2009.14108","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2009.14108"}},"official":{"repos":["ml-jku/align-rudder"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":[]}}},{"url":"/paper/neurosymbolic-reinforcement-learning-with","slug":"neurosymbolic-reinforcement-learning-with","title":"Neurosymbolic Reinforcement Learning with Formally Verified Exploration","date":"2020-09-26","arxiv_id":"2009.12612","repositories_listed":1,"syntology":null},{"url":"/paper/provably-safe-pac-mdp-exploration-using","slug":"provably-safe-pac-mdp-exploration-using","title":"Provably Safe PAC-MDP Exploration Using Analogies","date":"2020-07-07","arxiv_id":"2007.03574","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/enforcing-almost-sure-reachability-in-pomdps","slug":"enforcing-almost-sure-reachability-in-pomdps","title":"Enforcing Almost-Sure Reachability in POMDPs","date":"2020-06-30","arxiv_id":"2007.00085","repositories_listed":1,"syntology":null},{"url":"/paper/curiosity-killed-the-cat-and-the","slug":"curiosity-killed-the-cat-and-the","title":"Curiosity Killed or Incapacitated the Cat and the Asymptotically Optimal Agent","date":"2020-06-05","arxiv_id":"2006.03357","repositories_listed":1,"syntology":null},{"url":"/paper/safe-reinforcement-learning-for-probabilistic","slug":"safe-reinforcement-learning-for-probabilistic","title":"Safe reinforcement learning for probabilistic reachability and safety specifications: A Lyapunov-based approach","date":"2020-02-24","arxiv_id":"2002.10126","repositories_listed":1,"syntology":null},{"url":"/paper/safe-exploration-for-optimizing-contextual","slug":"safe-exploration-for-optimizing-contextual","title":"Safe Exploration for Optimizing Contextual Bandits","date":"2020-02-02","arxiv_id":"2002.00467","repositories_listed":1,"syntology":null},{"url":"/paper/learning-based-model-predictive-control-for-1","slug":"learning-based-model-predictive-control-for-1","title":"Learning-based Model Predictive Control for Safe Exploration and Reinforcement Learning","date":"2019-06-27","arxiv_id":"1906.12189","repositories_listed":1,"syntology":null},{"url":"/paper/learning-based-model-predictive-control-for","slug":"learning-based-model-predictive-control-for","title":"Learning-based Model Predictive Control for Safe Exploration","date":"2018-03-22","arxiv_id":"1803.08287","repositories_listed":1,"syntology":{"n":4,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 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; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/learning-based-model-predictive-control-for#ran","syntology_url":"https://syntology.ai/paper/1803.08287","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1803.08287"}},"official":null}},{"url":"/paper/concrete-problems-in-ai-safety","slug":"concrete-problems-in-ai-safety","title":"Concrete Problems in AI Safety","date":"2016-06-21","arxiv_id":"1606.06565","repositories_listed":1,"syntology":null},{"url":"/paper/safe-exploration-in-finite-markov-decision","slug":"safe-exploration-in-finite-markov-decision","title":"Safe Exploration in Finite Markov Decision Processes with Gaussian Processes","date":"2016-06-15","arxiv_id":"1606.04753","repositories_listed":1,"syntology":{"n":2,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 2 unverified","sample_list":"/paper/safe-exploration-in-finite-markov-decision#ran","syntology_url":"https://syntology.ai/paper/1606.04753","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1606.04753"}},"official":{"repos":["befelix/SafeMDP"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":[]}}},{"url":null,"slug":"slac-simulation-pretrained-latent-action","title":"SLAC: Simulation-Pretrained Latent Action Space for Whole-Body Real-World RL","date":"2025-06-04","arxiv_id":"2506.04147","repositories_listed":0,"syntology":null},{"url":null,"slug":"bresa-bio-inspired-reflexive-safe","title":"Bresa: Bio-inspired Reflexive Safe Reinforcement Learning for Contact-Rich Robotic Tasks","date":"2025-03-27","arxiv_id":"2503.21989","repositories_listed":0,"syntology":null},{"url":null,"slug":"safe-exploration-in-reproducing-kernel","title":"Safe exploration in reproducing kernel Hilbert spaces","date":"2025-03-13","arxiv_id":"2503.10352","repositories_listed":0,"syntology":null},{"url":null,"slug":"safety-representations-for-safer-policy","title":"Safety Representations for Safer Policy Learning","date":"2025-02-27","arxiv_id":"2502.20341","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-to-explore-when-mistakes-are-not","title":"Learning to explore when mistakes are not allowed","date":"2025-02-19","arxiv_id":"2502.13801","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-enhanced-safeguard-control-for-high","title":"Learning-Enhanced Safeguard Control for High-Relative-Degree Systems: Robust Optimization under Disturbances and Faults","date":"2025-01-26","arxiv_id":"2501.15373","repositories_listed":0,"syntology":null},{"url":null,"slug":"safe-bayesian-optimization-for-the-control-of","title":"Safe Bayesian Optimization for the Control of High-Dimensional Embodied Systems","date":"2024-12-29","arxiv_id":"2412.20350","repositories_listed":0,"syntology":null},{"url":null,"slug":"actsafe-active-exploration-with-safety","title":"ActSafe: Active Exploration with Safety Constraints for Reinforcement Learning","date":"2024-10-12","arxiv_id":"2410.09486","repositories_listed":0,"syntology":null},{"url":null,"slug":"robust-deep-reinforcement-learning-for-volt","title":"Robust Deep Reinforcement Learning for Volt-VAR Optimization in Active Distribution System under Uncertainty","date":"2024-09-27","arxiv_id":"2409.18937","repositories_listed":0,"syntology":null},{"url":null,"slug":"revisiting-safe-exploration-in-safe","title":"Revisiting Safe Exploration in Safe Reinforcement learning","date":"2024-09-02","arxiv_id":"2409.01245","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-safe-self-evolution-algorithm-for","title":"A Safe Self-evolution Algorithm for Autonomous Driving Based on Data-Driven Risk Quantification Model","date":"2024-08-23","arxiv_id":"2408.12805","repositories_listed":0,"syntology":null},{"url":null,"slug":"meta-sac-lag-towards-deployable-safe","title":"Meta SAC-Lag: Towards Deployable Safe Reinforcement Learning via MetaGradient-based Hyperparameter Tuning","date":"2024-08-15","arxiv_id":"2408.07962","repositories_listed":0,"syntology":null},{"url":null,"slug":"2408-00997","title":"A Safe Exploration Strategy for Model-free Task Adaptation in Safety-constrained Grid Environments","date":"2024-08-02","arxiv_id":"2408.00997","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhanced-safety-in-autonomous-driving","title":"Enhanced Safety in Autonomous Driving: Integrating Latent State Diffusion Model for End-to-End Navigation","date":"2024-07-08","arxiv_id":"2407.06317","repositories_listed":0,"syntology":null},{"url":"/paper/highway-value-iteration-networks","slug":"highway-value-iteration-networks","title":"Highway Value Iteration Networks","date":"2024-06-05","arxiv_id":"2406.03485","repositories_listed":0,"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":6,"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/highway-value-iteration-networks#ran","syntology_url":"https://syntology.ai/paper/2406.03485","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.03485"}},"official":null}},{"url":null,"slug":"preparing-for-black-swans-the-antifragility","title":"Preparing for Black Swans: The Antifragility Imperative for Machine Learning","date":"2024-05-18","arxiv_id":"2405.11397","repositories_listed":0,"syntology":null},{"url":null,"slug":"contextual-affordances-for-safe-exploration","title":"Contextual Affordances for Safe Exploration in Robotic Scenarios","date":"2024-05-10","arxiv_id":"2405.06422","repositories_listed":0,"syntology":null},{"url":null,"slug":"safe-exploration-using-bayesian-world-models","title":"Safe Exploration Using Bayesian World Models and Log-Barrier Optimization","date":"2024-05-09","arxiv_id":"2405.05890","repositories_listed":0,"syntology":null},{"url":null,"slug":"information-theoretic-safe-bayesian","title":"Information-Theoretic Safe Bayesian Optimization","date":"2024-02-23","arxiv_id":"2402.15347","repositories_listed":0,"syntology":null},{"url":null,"slug":"trajectory-wise-iterative-reinforcement","title":"Trajectory-wise Iterative Reinforcement Learning Framework for Auto-bidding","date":"2024-02-23","arxiv_id":"2402.15102","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-socially-and-morally-aware-rl-agent","title":"Towards Socially and Morally Aware RL agent: Reward Design With LLM","date":"2024-01-23","arxiv_id":"2401.12459","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-safe-load-balancing-based-on-control","title":"Towards Safe Load Balancing based on Control Barrier Functions and Deep Reinforcement Learning","date":"2024-01-10","arxiv_id":"2401.05525","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-human-like-representations-to-enable","title":"Learning Human-like Representations to Enable Learning Human Values","date":"2023-12-21","arxiv_id":"2312.14106","repositories_listed":0,"syntology":null},{"url":null,"slug":"safe-exploration-in-reinforcement-learning","title":"Safe Exploration in Reinforcement Learning: Training Backup Control Barrier Functions with Zero Training Time Safety Violations","date":"2023-12-13","arxiv_id":"2312.07828","repositories_listed":0,"syntology":null},{"url":null,"slug":"interior-point-constrained-reinforcement","title":"A safe exploration approach to constrained Markov decision processes","date":"2023-12-01","arxiv_id":"2312.00561","repositories_listed":0,"syntology":null},{"url":null,"slug":"safe-reinforcement-learning-in-a-simulated","title":"Safe Reinforcement Learning in a Simulated Robotic Arm","date":"2023-11-28","arxiv_id":"2312.09468","repositories_listed":0,"syntology":null},{"url":null,"slug":"safe-exploration-in-reinforcement-learning-a","title":"Safe Exploration in Reinforcement Learning: A Generalized Formulation and Algorithms","date":"2023-10-05","arxiv_id":"2310.03225","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-by-guided-safe","title":"Reinforcement Learning by Guided Safe Exploration","date":"2023-07-26","arxiv_id":"2307.14316","repositories_listed":0,"syntology":null},{"url":null,"slug":"model-assisted-probabilistic-safe-adaptive","title":"Model-Assisted Probabilistic Safe Adaptive Control With Meta-Bayesian Learning","date":"2023-07-03","arxiv_id":"2307.00828","repositories_listed":0,"syntology":null},{"url":null,"slug":"safe-reinforcement-learning-with-dead-ends","title":"Safe Reinforcement Learning with Dead-Ends Avoidance and Recovery","date":"2023-06-24","arxiv_id":"2306.13944","repositories_listed":0,"syntology":null},{"url":null,"slug":"provably-learning-nash-policies-in","title":"Provably Learning Nash Policies in Constrained Markov Potential Games","date":"2023-06-13","arxiv_id":"2306.07749","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploration-of-unranked-items-in-safe-online","title":"Exploration of Unranked Items in Safe Online Learning to Re-Rank","date":"2023-05-02","arxiv_id":"2305.01202","repositories_listed":0,"syntology":null},{"url":null,"slug":"system-iii-learning-with-domain-knowledge-for","title":"System III: Learning with Domain Knowledge for Safety Constraints","date":"2023-04-23","arxiv_id":"2304.11593","repositories_listed":0,"syntology":null},{"url":null,"slug":"approximate-shielding-of-atari-agents-for","title":"Approximate Shielding of Atari Agents for Safe Exploration","date":"2023-04-21","arxiv_id":"2304.11104","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-human-centered-safe-robot-reinforcement","title":"A Human-Centered Safe Robot Reinforcement Learning Framework with Interactive Behaviors","date":"2023-02-25","arxiv_id":"2302.13137","repositories_listed":0,"syntology":null},{"url":null,"slug":"guiding-safe-exploration-with-weakest","title":"Guiding Safe Exploration with Weakest Preconditions","date":"2022-09-28","arxiv_id":"2209.14148","repositories_listed":0,"syntology":null},{"url":null,"slug":"safe-reinforcement-learning-of-dynamic-high","title":"Safe Reinforcement Learning of Dynamic High-Dimensional Robotic Tasks: Navigation, Manipulation, Interaction","date":"2022-09-27","arxiv_id":"2209.13308","repositories_listed":0,"syntology":null},{"url":null,"slug":"safe-reinforcement-learning-with-contrastive","title":"Safe Reinforcement Learning with Contrastive Risk Prediction","date":"2022-09-10","arxiv_id":"2209.09648","repositories_listed":0,"syntology":null},{"url":null,"slug":"probabilistic-safe-online-learning-with","title":"Recursively Feasible Probabilistic Safe Online Learning with Control Barrier Functions","date":"2022-08-23","arxiv_id":"2208.10733","repositories_listed":0,"syntology":null},{"url":null,"slug":"sample-efficient-safe-learning-for-online","title":"Sample-efficient Safe Learning for Online Nonlinear Control with Control Barrier Functions","date":"2022-07-29","arxiv_id":"2207.14419","repositories_listed":0,"syntology":null},{"url":null,"slug":"ablation-study-of-how-run-time-assurance","title":"Ablation Study of How Run Time Assurance Impacts the Training and Performance of Reinforcement Learning Agents","date":"2022-07-08","arxiv_id":"2207.04117","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-safe-semi-supervised-graph-convolution","title":"A Safe Semi-supervised Graph Convolution Network","date":"2022-07-05","arxiv_id":"2207.01960","repositories_listed":0,"syntology":null},{"url":null,"slug":"safe-exploration-incurs-nearly-no-additional","title":"Safe Exploration Incurs Nearly No Additional Sample Complexity for Reward-free RL","date":"2022-06-28","arxiv_id":"2206.14057","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-to-drive-using-sparse-imitation","title":"Learning to Drive Using Sparse Imitation Reinforcement Learning","date":"2022-05-24","arxiv_id":"2205.12128","repositories_listed":0,"syntology":null},{"url":null,"slug":"learn-to-race-challenge-2022-benchmarking","title":"Learn-to-Race Challenge 2022: Benchmarking Safe Learning and Cross-domain Generalisation in Autonomous Racing","date":"2022-05-05","arxiv_id":"2205.02953","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploration-in-deep-reinforcement-learning-a-1","title":"Exploration in Deep Reinforcement Learning: A Survey","date":"2022-05-02","arxiv_id":"2205.00824","repositories_listed":0,"syntology":null},{"url":null,"slug":"scope-safe-exploration-for-dynamic-computer","title":"SCOPE: Safe Exploration for Dynamic Computer Systems Optimization","date":"2022-04-22","arxiv_id":"2204.10451","repositories_listed":0,"syntology":null},{"url":null,"slug":"saac-safe-reinforcement-learning-as-an","title":"SAAC: Safe Reinforcement Learning as an Adversarial Game of Actor-Critics","date":"2022-04-20","arxiv_id":"2204.09424","repositories_listed":0,"syntology":null},{"url":null,"slug":"training-and-evaluation-of-deep-policies","title":"Training and Evaluation of Deep Policies using Reinforcement Learning and Generative Models","date":"2022-04-18","arxiv_id":"2204.08573","repositories_listed":0,"syntology":null},{"url":null,"slug":"safe-reinforcement-learning-via-shielding-for","title":"Safe Reinforcement Learning via Shielding under Partial Observability","date":"2022-04-02","arxiv_id":"2204.00755","repositories_listed":0,"syntology":null},{"url":null,"slug":"safe-exploration-for-efficient-policy","title":"Safe Exploration for Efficient Policy Evaluation and Comparison","date":"2022-02-26","arxiv_id":"2202.13234","repositories_listed":0,"syntology":null},{"url":null,"slug":"model-based-offline-meta-reinforcement-1","title":"Model-Based Offline Meta-Reinforcement Learning with Regularization","date":"2022-02-07","arxiv_id":"2202.02929","repositories_listed":0,"syntology":null},{"url":null,"slug":"provably-efficient-primal-dual-reinforcement","title":"Provably Efficient Primal-Dual Reinforcement Learning for CMDPs with Non-stationary Objectives and Constraints","date":"2022-01-28","arxiv_id":"2201.11965","repositories_listed":0,"syntology":null},{"url":null,"slug":"mesa-offline-meta-rl-for-safe-adaptation-and","title":"MESA: Offline Meta-RL for Safe Adaptation and Fault Tolerance","date":"2021-12-07","arxiv_id":"2112.03575","repositories_listed":0,"syntology":null},{"url":null,"slug":"desta-a-framework-for-safe-reinforcement-1","title":"DESTA: A Framework for Safe Reinforcement Learning with Markov Games of Intervention","date":"2021-10-27","arxiv_id":"2110.14468","repositories_listed":0,"syntology":null},{"url":null,"slug":"dual-arm-adversarial-robot-learning","title":"Dual-Arm Adversarial Robot Learning","date":"2021-10-15","arxiv_id":"2110.08066","repositories_listed":0,"syntology":null},{"url":null,"slug":"safe-exploration-in-linear-equality","title":"Safe Exploration in Linear Equality Constraint","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null}],"syntology_records":14,"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"},"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)"},"since_archive_judged":{"papers":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[]},"papers_where_code_ran":12,"papers_where_code_ran_first_page":"/task/safe-exploration/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","pages":[{"order":"archive","page":2,"of":2,"url":"/task/safe-exploration/papers/2","json":"/task/safe-exploration/papers/2.json","rows":35},{"order":"ran","page":1,"of":1,"url":"/task/safe-exploration/papers/ran/1","json":"/task/safe-exploration/papers/ran/1.json","rows":12}],"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":"2026-10-05T00:36:11+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; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"row_route":"each syntology object on a benchmark's first row and on a paper carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers"},"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"},"record_sha256":"d28805795a39699465bf53d28f2775e135dfa35306f4350f0aa27128df7acbbc","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}