{"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-reinforcement-learning/papers/4","list_of":"/task/safe-reinforcement-learning","task":"Safe 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":4,"pages_in_order":4,"rows_per_page":100,"rows":[301,306],"of":306,"counts":{"archive_papers_tagged":306,"with_a_code_link":100,"where_syntology_ran_a_sample":34,"not_listed_spam_title":0,"listed":306,"listed_where_code_ran":34,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":29,"every_run_a_failure_of_syntologys_instrument":5,"listed_with_a_run_with_no_instrument_failure":29,"listed_every_run_a_failure_of_syntologys_instrument":5,"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/safe-reinforcement-learning","prev":"/task/safe-reinforcement-learning/papers/3","next":null,"papers":[{"url":null,"slug":"directed-policy-gradient-for-safe","title":"Directed Policy Gradient for Safe Reinforcement Learning with Human Advice","date":"2018-08-13","arxiv_id":"1808.04096","repositories_listed":0,"syntology":null},{"url":null,"slug":"shielded-decision-making-in-mdps","title":"Safe Reinforcement Learning via Probabilistic Shields","date":"2018-07-16","arxiv_id":"1807.06096","repositories_listed":0,"syntology":null},{"url":null,"slug":"measuring-and-avoiding-side-effects-using","title":"Penalizing side effects using stepwise relative reachability","date":"2018-06-04","arxiv_id":"1806.01186","repositories_listed":0,"syntology":null},{"url":null,"slug":"virtuously-safe-reinforcement-learning","title":"Virtuously Safe Reinforcement Learning","date":"2018-05-29","arxiv_id":"1805.11447","repositories_listed":0,"syntology":null},{"url":null,"slug":"accelerated-primal-dual-policy-optimization","title":"Accelerated Primal-Dual Policy Optimization for Safe Reinforcement Learning","date":"2018-02-19","arxiv_id":"1802.06480","repositories_listed":0,"syntology":null},{"url":null,"slug":"uncertainty-decomposition-in-bayesian-neural","title":"Uncertainty Decomposition in Bayesian Neural Networks with Latent Variables","date":"2017-06-26","arxiv_id":"1706.08495","repositories_listed":0,"syntology":null}],"record_sha256":"39da727970378a8b8b7e55b8f6673713b82f1b8f3eb624663ff535ec9657dd4d","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}