{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:XZZLJ7VHFMFLUCACEQKQH3YTW4","short_pith_number":"pith:XZZLJ7VH","schema_version":"1.0","canonical_sha256":"be72b4fea72b0aba0802241503ef13b7149f8d1846fb622ae57cf1e8c3f1426e","source":{"kind":"arxiv","id":"1809.04232","version":1},"attestation_state":"computed","paper":{"title":"Safe Exploration in Markov Decision Processes with Time-Variant Safety using Spatio-Temporal Gaussian Process","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Akifumi Wachi, Asim Munawar, Hiroshi Kajino","submitted_at":"2018-09-12T02:43:19Z","abstract_excerpt":"In many real-world applications (e.g., planetary exploration, robot navigation), an autonomous agent must be able to explore a space with guaranteed safety. Most safe exploration algorithms in the field of reinforcement learning and robotics have been based on the assumption that the safety features are a priori known and time-invariant. This paper presents a learning algorithm called ST-SafeMDP for exploring Markov decision processes (MDPs) that is based on the assumption that the safety features are a priori unknown and time-variant. In this setting, the agent explores MDPs while constrainin"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1809.04232","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-09-12T02:43:19Z","cross_cats_sorted":[],"title_canon_sha256":"5ef29bfc8eb72179e70180ce1d978164a38fe04bafad2fd3a8c4d2394efd5a62","abstract_canon_sha256":"7e70c414f669bed4c91c48ed893f44738a02a33a209b174441bd41792d6b06fa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:05:53.076091Z","signature_b64":"3IblvA41X5tcUfNJWMuXWOghPxHihbN14GBmzXmQXeredUjP4uvZfI4ZzAdUiLTOi6RpfZ6uO3ZpAAbgslCZBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"be72b4fea72b0aba0802241503ef13b7149f8d1846fb622ae57cf1e8c3f1426e","last_reissued_at":"2026-05-18T00:05:53.075447Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:05:53.075447Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Safe Exploration in Markov Decision Processes with Time-Variant Safety using Spatio-Temporal Gaussian Process","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Akifumi Wachi, Asim Munawar, Hiroshi Kajino","submitted_at":"2018-09-12T02:43:19Z","abstract_excerpt":"In many real-world applications (e.g., planetary exploration, robot navigation), an autonomous agent must be able to explore a space with guaranteed safety. Most safe exploration algorithms in the field of reinforcement learning and robotics have been based on the assumption that the safety features are a priori known and time-invariant. This paper presents a learning algorithm called ST-SafeMDP for exploring Markov decision processes (MDPs) that is based on the assumption that the safety features are a priori unknown and time-variant. In this setting, the agent explores MDPs while constrainin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.04232","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"1809.04232","created_at":"2026-05-18T00:05:53.075557+00:00"},{"alias_kind":"arxiv_version","alias_value":"1809.04232v1","created_at":"2026-05-18T00:05:53.075557+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.04232","created_at":"2026-05-18T00:05:53.075557+00:00"},{"alias_kind":"pith_short_12","alias_value":"XZZLJ7VHFMFL","created_at":"2026-05-18T12:33:04.347982+00:00"},{"alias_kind":"pith_short_16","alias_value":"XZZLJ7VHFMFLUCAC","created_at":"2026-05-18T12:33:04.347982+00:00"},{"alias_kind":"pith_short_8","alias_value":"XZZLJ7VH","created_at":"2026-05-18T12:33:04.347982+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XZZLJ7VHFMFLUCACEQKQH3YTW4","json":"https://pith.science/pith/XZZLJ7VHFMFLUCACEQKQH3YTW4.json","graph_json":"https://pith.science/api/pith-number/XZZLJ7VHFMFLUCACEQKQH3YTW4/graph.json","events_json":"https://pith.science/api/pith-number/XZZLJ7VHFMFLUCACEQKQH3YTW4/events.json","paper":"https://pith.science/paper/XZZLJ7VH"},"agent_actions":{"view_html":"https://pith.science/pith/XZZLJ7VHFMFLUCACEQKQH3YTW4","download_json":"https://pith.science/pith/XZZLJ7VHFMFLUCACEQKQH3YTW4.json","view_paper":"https://pith.science/paper/XZZLJ7VH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1809.04232&json=true","fetch_graph":"https://pith.science/api/pith-number/XZZLJ7VHFMFLUCACEQKQH3YTW4/graph.json","fetch_events":"https://pith.science/api/pith-number/XZZLJ7VHFMFLUCACEQKQH3YTW4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XZZLJ7VHFMFLUCACEQKQH3YTW4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XZZLJ7VHFMFLUCACEQKQH3YTW4/action/storage_attestation","attest_author":"https://pith.science/pith/XZZLJ7VHFMFLUCACEQKQH3YTW4/action/author_attestation","sign_citation":"https://pith.science/pith/XZZLJ7VHFMFLUCACEQKQH3YTW4/action/citation_signature","submit_replication":"https://pith.science/pith/XZZLJ7VHFMFLUCACEQKQH3YTW4/action/replication_record"}},"created_at":"2026-05-18T00:05:53.075557+00:00","updated_at":"2026-05-18T00:05:53.075557+00:00"}