{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:JDYAJTFSNC6AOIIIMVEM52FDSB","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"087ec504a17ebc9b1996e3f5147b2298efd2ac04610e1b4002b6d09507462bd7","cross_cats_sorted":["cs.AI","cs.RO","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-06-15T13:18:30Z","title_canon_sha256":"c24719c215c66532e5900e6ac6825ff194fb874fe432c4e641b6eb2de30df30a"},"schema_version":"1.0","source":{"id":"1606.04753","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1606.04753","created_at":"2026-05-18T00:52:02Z"},{"alias_kind":"arxiv_version","alias_value":"1606.04753v2","created_at":"2026-05-18T00:52:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1606.04753","created_at":"2026-05-18T00:52:02Z"},{"alias_kind":"pith_short_12","alias_value":"JDYAJTFSNC6A","created_at":"2026-05-18T12:30:25Z"},{"alias_kind":"pith_short_16","alias_value":"JDYAJTFSNC6AOIII","created_at":"2026-05-18T12:30:25Z"},{"alias_kind":"pith_short_8","alias_value":"JDYAJTFS","created_at":"2026-05-18T12:30:25Z"}],"graph_snapshots":[{"event_id":"sha256:2cf494956f9d875196a7ea90ba25d7fcd20fd9c4e2a7595852f86087c736d497","target":"graph","created_at":"2026-05-18T00:52:02Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"In classical reinforcement learning, when exploring an environment, agents accept arbitrary short term loss for long term gain. This is infeasible for safety critical applications, such as robotics, where even a single unsafe action may cause system failure. In this paper, we address the problem of safely exploring finite Markov decision processes (MDP). We define safety in terms of an, a priori unknown, safety constraint that depends on states and actions. We aim to explore the MDP under this constraint, assuming that the unknown function satisfies regularity conditions expressed via a Gaussi","authors_text":"Andreas Krause, Felix Berkenkamp, Matteo Turchetta","cross_cats":["cs.AI","cs.RO","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-06-15T13:18:30Z","title":"Safe Exploration in Finite Markov Decision Processes with Gaussian Processes"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1606.04753","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:34b447db2a8e151e796f98668ad49b289e26de00e46316dd59c14424ecd94b13","target":"record","created_at":"2026-05-18T00:52:02Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"087ec504a17ebc9b1996e3f5147b2298efd2ac04610e1b4002b6d09507462bd7","cross_cats_sorted":["cs.AI","cs.RO","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-06-15T13:18:30Z","title_canon_sha256":"c24719c215c66532e5900e6ac6825ff194fb874fe432c4e641b6eb2de30df30a"},"schema_version":"1.0","source":{"id":"1606.04753","kind":"arxiv","version":2}},"canonical_sha256":"48f004ccb268bc0721086548cee8a3906c9944a3f72b69164cd911e6cdd43b6e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"48f004ccb268bc0721086548cee8a3906c9944a3f72b69164cd911e6cdd43b6e","first_computed_at":"2026-05-18T00:52:02.021566Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:52:02.021566Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3O6RE6cEdHLAk0giwA9UjepX5eDTSrXlHgro1RspYg+YZtfJ3QuPlmXOIQswSCRnlgMmLEKaWFeIQxcxpVDXDg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:52:02.022101Z","signed_message":"canonical_sha256_bytes"},"source_id":"1606.04753","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:34b447db2a8e151e796f98668ad49b289e26de00e46316dd59c14424ecd94b13","sha256:2cf494956f9d875196a7ea90ba25d7fcd20fd9c4e2a7595852f86087c736d497"],"state_sha256":"194e9639f4c38d8b01e2f846d95795bd3ccd104763c03c0335e25f5fd0ded48d"}