{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:SSCMEC6EWU6DTYGKTZMZG6BGYM","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":"d84d188d4681a43c7cb957e03e58b7aa01c9eac48bd32f09e9fd737c4c009ad9","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-27T22:50:39Z","title_canon_sha256":"e381e25b0cb0bfe4b7d8041c9ec69eea3e161a597f50fd562069d67ca626a83a"},"schema_version":"1.0","source":{"id":"2010.14657","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2010.14657","created_at":"2026-07-05T01:47:17Z"},{"alias_kind":"arxiv_version","alias_value":"2010.14657v1","created_at":"2026-07-05T01:47:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.14657","created_at":"2026-07-05T01:47:17Z"},{"alias_kind":"pith_short_12","alias_value":"SSCMEC6EWU6D","created_at":"2026-07-05T01:47:17Z"},{"alias_kind":"pith_short_16","alias_value":"SSCMEC6EWU6DTYGK","created_at":"2026-07-05T01:47:17Z"},{"alias_kind":"pith_short_8","alias_value":"SSCMEC6E","created_at":"2026-07-05T01:47:17Z"}],"graph_snapshots":[{"event_id":"sha256:8f45025f06d44ebed6bdac00b14f09a08dfda773dd232280c14d415c1b0d21d5","target":"graph","created_at":"2026-07-05T01:47:17Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2010.14657/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Temporal difference learning with linear function approximation is a popular method to obtain a low-dimensional approximation of the value function of a policy in a Markov Decision Process. We give a new interpretation of this method in terms of a splitting of the gradient of an appropriately chosen function. As a consequence of this interpretation, convergence proofs for gradient descent can be applied almost verbatim to temporal difference learning. Beyond giving a new, fuller explanation of why temporal difference works, our interpretation also yields improved convergence times. We consider","authors_text":"Alex Olshevsky, Rui Liu","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-27T22:50:39Z","title":"Temporal Difference Learning as Gradient Splitting"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.14657","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":"sha256:17651e24c7faba9e812537967931a90c97dd5f1d988467780543674aa2b160b9","target":"record","created_at":"2026-07-05T01:47:17Z","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":"d84d188d4681a43c7cb957e03e58b7aa01c9eac48bd32f09e9fd737c4c009ad9","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-27T22:50:39Z","title_canon_sha256":"e381e25b0cb0bfe4b7d8041c9ec69eea3e161a597f50fd562069d67ca626a83a"},"schema_version":"1.0","source":{"id":"2010.14657","kind":"arxiv","version":1}},"canonical_sha256":"9484c20bc4b53c39e0ca9e59937826c3056c62154b4128ad7acab8c6de36ed0d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9484c20bc4b53c39e0ca9e59937826c3056c62154b4128ad7acab8c6de36ed0d","first_computed_at":"2026-07-05T01:47:17.299690Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:47:17.299690Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Q11aKx4xeKRPZXCjNh+qd3RF7H2XBQskT7Z5TmfDyChPlShaKmwRMRjSSLQSWtpKlAosHPO2eunPAdcwY8O9Aw==","signature_status":"signed_v1","signed_at":"2026-07-05T01:47:17.300099Z","signed_message":"canonical_sha256_bytes"},"source_id":"2010.14657","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:17651e24c7faba9e812537967931a90c97dd5f1d988467780543674aa2b160b9","sha256:8f45025f06d44ebed6bdac00b14f09a08dfda773dd232280c14d415c1b0d21d5"],"state_sha256":"48c86348ecf1551de423950f991d085c0b72791648f9bbaa72c23806e955dd40"}