{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:1996:L4KVB5ZIZVI43MIWLEDZ6HW5KJ","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":"5faeaecbe6b5a10bffa3fcc84a3b790dbd8942b6b725720ac6a59ad63241f261","cross_cats_sorted":[],"license":"","primary_cat":"cs.AI","submitted_at":"1996-05-01T00:00:00Z","title_canon_sha256":"f942feb40a73b3c2e0e5083214a82edb8f49d32cc0210bd5ef33783cb779681f"},"schema_version":"1.0","source":{"id":"cs/9605103","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"cs/9605103","created_at":"2026-05-18T02:37:36Z"},{"alias_kind":"arxiv_version","alias_value":"cs/9605103v1","created_at":"2026-05-18T02:37:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.cs/9605103","created_at":"2026-05-18T02:37:36Z"},{"alias_kind":"pith_short_12","alias_value":"L4KVB5ZIZVI4","created_at":"2026-05-18T12:25:48Z"},{"alias_kind":"pith_short_16","alias_value":"L4KVB5ZIZVI43MIW","created_at":"2026-05-18T12:25:48Z"},{"alias_kind":"pith_short_8","alias_value":"L4KVB5ZI","created_at":"2026-05-18T12:25:48Z"}],"graph_snapshots":[{"event_id":"sha256:e47420951f5b4aca48016f1ebcff202876d4d73fa55034802806060d6ae2f048","target":"graph","created_at":"2026-05-18T02:37:36Z","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":"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","authors_text":"A. W. Moore, L. P. Kaelbling, M. L. Littman","cross_cats":[],"headline":"","license":"","primary_cat":"cs.AI","submitted_at":"1996-05-01T00:00:00Z","title":"Reinforcement Learning: A Survey"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"cs/9605103","kind":"arxiv","version":1},"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":"sha256:658137b9006e477694ced6cd03ce1140a9f11fd8ba95313bc95b22e69a621137","target":"record","created_at":"2026-05-18T02:37:36Z","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":"5faeaecbe6b5a10bffa3fcc84a3b790dbd8942b6b725720ac6a59ad63241f261","cross_cats_sorted":[],"license":"","primary_cat":"cs.AI","submitted_at":"1996-05-01T00:00:00Z","title_canon_sha256":"f942feb40a73b3c2e0e5083214a82edb8f49d32cc0210bd5ef33783cb779681f"},"schema_version":"1.0","source":{"id":"cs/9605103","kind":"arxiv","version":1}},"canonical_sha256":"5f1550f728cd51cdb11659079f1edd52425bb3d6148f4caf59b793f602758e44","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5f1550f728cd51cdb11659079f1edd52425bb3d6148f4caf59b793f602758e44","first_computed_at":"2026-05-18T02:37:36.690550Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T02:37:36.690550Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"r3Mq+N1Vof3a+UfkiGqxzMjffNRFZBdvWO/FRmdtXXIa/+LYjBL8gaqeWnO5zmCluqt07jo2KKDtDRFYN+FrDw==","signature_status":"signed_v1","signed_at":"2026-05-18T02:37:36.690960Z","signed_message":"canonical_sha256_bytes"},"source_id":"cs/9605103","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:658137b9006e477694ced6cd03ce1140a9f11fd8ba95313bc95b22e69a621137","sha256:e47420951f5b4aca48016f1ebcff202876d4d73fa55034802806060d6ae2f048"],"state_sha256":"7ae4687063314e31af23b303b75091da9f6f2dbd533c7bffae41e15440cd6810"}