{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:HIQEE3PXZKTADUBFN3VIL35OBV","short_pith_number":"pith:HIQEE3PX","schema_version":"1.0","canonical_sha256":"3a20426df7caa601d0256eea85efae0d61f77985710a03c5c7216a501bc5780f","source":{"kind":"arxiv","id":"1507.00353","version":1},"attestation_state":"computed","paper":{"title":"An Empirical Evaluation of True Online TD({\\lambda})","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.AI","authors_text":"A. Rupam Mahmood, Harm van Seijen, Patrick M. Pilarski, Richard S. Sutton","submitted_at":"2015-07-01T20:03:49Z","abstract_excerpt":"The true online TD({\\lambda}) algorithm has recently been proposed (van Seijen and Sutton, 2014) as a universal replacement for the popular TD({\\lambda}) algorithm, in temporal-difference learning and reinforcement learning. True online TD({\\lambda}) has better theoretical properties than conventional TD({\\lambda}), and the expectation is that it also results in faster learning. In this paper, we put this hypothesis to the test. Specifically, we compare the performance of true online TD({\\lambda}) with that of TD({\\lambda}) on challenging examples, random Markov reward processes, and a real-wo"},"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":"1507.00353","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2015-07-01T20:03:49Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"c10e74ac2069bca1f39e9db11f550deba43cfed30ed976358879cee51e003abd","abstract_canon_sha256":"7b47c9264b62ef5aa5c528c1bc06d33cbe015153904ca913f71c0a432437e19e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:37:26.832414Z","signature_b64":"ZKRIfgFYyeIKwt2LXoIJVDgPU5W7gINaTh3umF7PsIjYHRIS8X5heRdP75lj7qgWFCGhGImdEy/3rJwIF0R0DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3a20426df7caa601d0256eea85efae0d61f77985710a03c5c7216a501bc5780f","last_reissued_at":"2026-05-18T01:37:26.831775Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:37:26.831775Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An Empirical Evaluation of True Online TD({\\lambda})","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.AI","authors_text":"A. Rupam Mahmood, Harm van Seijen, Patrick M. Pilarski, Richard S. Sutton","submitted_at":"2015-07-01T20:03:49Z","abstract_excerpt":"The true online TD({\\lambda}) algorithm has recently been proposed (van Seijen and Sutton, 2014) as a universal replacement for the popular TD({\\lambda}) algorithm, in temporal-difference learning and reinforcement learning. True online TD({\\lambda}) has better theoretical properties than conventional TD({\\lambda}), and the expectation is that it also results in faster learning. In this paper, we put this hypothesis to the test. Specifically, we compare the performance of true online TD({\\lambda}) with that of TD({\\lambda}) on challenging examples, random Markov reward processes, and a real-wo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1507.00353","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":"1507.00353","created_at":"2026-05-18T01:37:26.831868+00:00"},{"alias_kind":"arxiv_version","alias_value":"1507.00353v1","created_at":"2026-05-18T01:37:26.831868+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1507.00353","created_at":"2026-05-18T01:37:26.831868+00:00"},{"alias_kind":"pith_short_12","alias_value":"HIQEE3PXZKTA","created_at":"2026-05-18T12:29:25.134429+00:00"},{"alias_kind":"pith_short_16","alias_value":"HIQEE3PXZKTADUBF","created_at":"2026-05-18T12:29:25.134429+00:00"},{"alias_kind":"pith_short_8","alias_value":"HIQEE3PX","created_at":"2026-05-18T12:29:25.134429+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/HIQEE3PXZKTADUBFN3VIL35OBV","json":"https://pith.science/pith/HIQEE3PXZKTADUBFN3VIL35OBV.json","graph_json":"https://pith.science/api/pith-number/HIQEE3PXZKTADUBFN3VIL35OBV/graph.json","events_json":"https://pith.science/api/pith-number/HIQEE3PXZKTADUBFN3VIL35OBV/events.json","paper":"https://pith.science/paper/HIQEE3PX"},"agent_actions":{"view_html":"https://pith.science/pith/HIQEE3PXZKTADUBFN3VIL35OBV","download_json":"https://pith.science/pith/HIQEE3PXZKTADUBFN3VIL35OBV.json","view_paper":"https://pith.science/paper/HIQEE3PX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1507.00353&json=true","fetch_graph":"https://pith.science/api/pith-number/HIQEE3PXZKTADUBFN3VIL35OBV/graph.json","fetch_events":"https://pith.science/api/pith-number/HIQEE3PXZKTADUBFN3VIL35OBV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HIQEE3PXZKTADUBFN3VIL35OBV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HIQEE3PXZKTADUBFN3VIL35OBV/action/storage_attestation","attest_author":"https://pith.science/pith/HIQEE3PXZKTADUBFN3VIL35OBV/action/author_attestation","sign_citation":"https://pith.science/pith/HIQEE3PXZKTADUBFN3VIL35OBV/action/citation_signature","submit_replication":"https://pith.science/pith/HIQEE3PXZKTADUBFN3VIL35OBV/action/replication_record"}},"created_at":"2026-05-18T01:37:26.831868+00:00","updated_at":"2026-05-18T01:37:26.831868+00:00"}