{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:1996:L4KVB5ZIZVI43MIWLEDZ6HW5KJ","short_pith_number":"pith:L4KVB5ZI","schema_version":"1.0","canonical_sha256":"5f1550f728cd51cdb11659079f1edd52425bb3d6148f4caf59b793f602758e44","source":{"kind":"arxiv","id":"cs/9605103","version":1},"attestation_state":"computed","paper":{"title":"Reinforcement Learning: A Survey","license":"","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"A. W. Moore, L. P. Kaelbling, M. L. Littman","submitted_at":"1996-05-01T00:00:00Z","abstract_excerpt":"This paper surveys the field of reinforcement learning from a computer-science perspective. It is written to be accessible to researchers familiar with machine learning. Both the historical basis of the field and a broad selection of current work are summarized. Reinforcement learning is the problem faced by an agent that learns behavior through trial-and-error interactions with a dynamic environment. The work described here has a resemblance to work in psychology, but differs considerably in the details and in the use of the word ``reinforcement.'' The paper discusses central issues of reinfo"},"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":"cs/9605103","kind":"arxiv","version":1},"metadata":{"license":"","primary_cat":"cs.AI","submitted_at":"1996-05-01T00:00:00Z","cross_cats_sorted":[],"title_canon_sha256":"f942feb40a73b3c2e0e5083214a82edb8f49d32cc0210bd5ef33783cb779681f","abstract_canon_sha256":"5faeaecbe6b5a10bffa3fcc84a3b790dbd8942b6b725720ac6a59ad63241f261"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:37:36.690960Z","signature_b64":"r3Mq+N1Vof3a+UfkiGqxzMjffNRFZBdvWO/FRmdtXXIa/+LYjBL8gaqeWnO5zmCluqt07jo2KKDtDRFYN+FrDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5f1550f728cd51cdb11659079f1edd52425bb3d6148f4caf59b793f602758e44","last_reissued_at":"2026-05-18T02:37:36.690550Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:37:36.690550Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reinforcement Learning: A Survey","license":"","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"A. W. Moore, L. P. Kaelbling, M. L. Littman","submitted_at":"1996-05-01T00:00:00Z","abstract_excerpt":"This paper surveys the field of reinforcement learning from a computer-science perspective. It is written to be accessible to researchers familiar with machine learning. Both the historical basis of the field and a broad selection of current work are summarized. Reinforcement learning is the problem faced by an agent that learns behavior through trial-and-error interactions with a dynamic environment. The work described here has a resemblance to work in psychology, but differs considerably in the details and in the use of the word ``reinforcement.'' The paper discusses central issues of reinfo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"cs/9605103","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":"cs/9605103","created_at":"2026-05-18T02:37:36.690607+00:00"},{"alias_kind":"arxiv_version","alias_value":"cs/9605103v1","created_at":"2026-05-18T02:37:36.690607+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.cs/9605103","created_at":"2026-05-18T02:37:36.690607+00:00"},{"alias_kind":"pith_short_12","alias_value":"L4KVB5ZIZVI4","created_at":"2026-05-18T12:25:48.327863+00:00"},{"alias_kind":"pith_short_16","alias_value":"L4KVB5ZIZVI43MIW","created_at":"2026-05-18T12:25:48.327863+00:00"},{"alias_kind":"pith_short_8","alias_value":"L4KVB5ZI","created_at":"2026-05-18T12:25:48.327863+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/L4KVB5ZIZVI43MIWLEDZ6HW5KJ","json":"https://pith.science/pith/L4KVB5ZIZVI43MIWLEDZ6HW5KJ.json","graph_json":"https://pith.science/api/pith-number/L4KVB5ZIZVI43MIWLEDZ6HW5KJ/graph.json","events_json":"https://pith.science/api/pith-number/L4KVB5ZIZVI43MIWLEDZ6HW5KJ/events.json","paper":"https://pith.science/paper/L4KVB5ZI"},"agent_actions":{"view_html":"https://pith.science/pith/L4KVB5ZIZVI43MIWLEDZ6HW5KJ","download_json":"https://pith.science/pith/L4KVB5ZIZVI43MIWLEDZ6HW5KJ.json","view_paper":"https://pith.science/paper/L4KVB5ZI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=cs/9605103&json=true","fetch_graph":"https://pith.science/api/pith-number/L4KVB5ZIZVI43MIWLEDZ6HW5KJ/graph.json","fetch_events":"https://pith.science/api/pith-number/L4KVB5ZIZVI43MIWLEDZ6HW5KJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/L4KVB5ZIZVI43MIWLEDZ6HW5KJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/L4KVB5ZIZVI43MIWLEDZ6HW5KJ/action/storage_attestation","attest_author":"https://pith.science/pith/L4KVB5ZIZVI43MIWLEDZ6HW5KJ/action/author_attestation","sign_citation":"https://pith.science/pith/L4KVB5ZIZVI43MIWLEDZ6HW5KJ/action/citation_signature","submit_replication":"https://pith.science/pith/L4KVB5ZIZVI43MIWLEDZ6HW5KJ/action/replication_record"}},"created_at":"2026-05-18T02:37:36.690607+00:00","updated_at":"2026-05-18T02:37:36.690607+00:00"}