{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2011:EUKYQP6ROKH6GXS7JJWYG5MFJN","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":"e035c8c2c89145420e9e4b6f07ede8c4640a68fead5775d25ba7805d4b7236d5","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2011-01-02T20:20:27Z","title_canon_sha256":"290763cccc2332f1644a43e6bc1352cfcfeb2c381b9a65c9041d1061572f2055"},"schema_version":"1.0","source":{"id":"1101.0428","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1101.0428","created_at":"2026-05-18T04:32:10Z"},{"alias_kind":"arxiv_version","alias_value":"1101.0428v1","created_at":"2026-05-18T04:32:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1101.0428","created_at":"2026-05-18T04:32:10Z"},{"alias_kind":"pith_short_12","alias_value":"EUKYQP6ROKH6","created_at":"2026-05-18T12:26:28Z"},{"alias_kind":"pith_short_16","alias_value":"EUKYQP6ROKH6GXS7","created_at":"2026-05-18T12:26:28Z"},{"alias_kind":"pith_short_8","alias_value":"EUKYQP6R","created_at":"2026-05-18T12:26:28Z"}],"graph_snapshots":[{"event_id":"sha256:746151a57f065825fb99c5474d5af945afecf8f1dc5f8ffc2956954bc129ba79","target":"graph","created_at":"2026-05-18T04:32:10Z","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 this theoretical paper we are concerned with the problem of learning a value function by a smooth general function approximator, to solve a deterministic episodic control problem in a large continuous state space. It is shown that learning the gradient of the value-function at every point along a trajectory generated by a greedy policy is a sufficient condition for the trajectory to be locally extremal, and often locally optimal, and we argue that this brings greater efficiency to value-function learning. This contrasts to traditional value-function learning in which the value-function must","authors_text":"Eduardo Alonso, Michael Fairbank","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2011-01-02T20:20:27Z","title":"The Local Optimality of Reinforcement Learning by Value Gradients, and its Relationship to Policy Gradient Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1101.0428","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":"sha256:615f03b66b5d78c40a17debd302a8585454876ee4dcf59e2cdc5b6b64c45be8e","target":"record","created_at":"2026-05-18T04:32:10Z","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":"e035c8c2c89145420e9e4b6f07ede8c4640a68fead5775d25ba7805d4b7236d5","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2011-01-02T20:20:27Z","title_canon_sha256":"290763cccc2332f1644a43e6bc1352cfcfeb2c381b9a65c9041d1061572f2055"},"schema_version":"1.0","source":{"id":"1101.0428","kind":"arxiv","version":1}},"canonical_sha256":"2515883fd1728fe35e5f4a6d8375854b64ef8db1d76134685da2120fdfef18a3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2515883fd1728fe35e5f4a6d8375854b64ef8db1d76134685da2120fdfef18a3","first_computed_at":"2026-05-18T04:32:10.383430Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T04:32:10.383430Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bX8s4Ndq8INdUdieCQUq5ijS+yJU380GRCB5L1jfC33jZ1gcnGQlUpJAv86U9gLK/cKMM9RR2jhNzXJML68/Dg==","signature_status":"signed_v1","signed_at":"2026-05-18T04:32:10.383858Z","signed_message":"canonical_sha256_bytes"},"source_id":"1101.0428","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:615f03b66b5d78c40a17debd302a8585454876ee4dcf59e2cdc5b6b64c45be8e","sha256:746151a57f065825fb99c5474d5af945afecf8f1dc5f8ffc2956954bc129ba79"],"state_sha256":"77048814a08adc856e6c5b8897a59c816140db1bb527df1cf102f324bbb8d9f8"}