{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:4AAY4RFROTCEZ57JQ2LINJPLWR","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":"9c8927dca16f4b1118fdbe3a58e8b6511d1f2d5f9cd51aa6fd94520f7fbf8413","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-03-03T20:19:08Z","title_canon_sha256":"b48f1fd13340b3b1c4b3394b46e674918616be1165b723f00d0f7c6253435c77"},"schema_version":"1.0","source":{"id":"1703.01327","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1703.01327","created_at":"2026-05-18T00:13:37Z"},{"alias_kind":"arxiv_version","alias_value":"1703.01327v2","created_at":"2026-05-18T00:13:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.01327","created_at":"2026-05-18T00:13:37Z"},{"alias_kind":"pith_short_12","alias_value":"4AAY4RFROTCE","created_at":"2026-05-18T12:30:58Z"},{"alias_kind":"pith_short_16","alias_value":"4AAY4RFROTCEZ57J","created_at":"2026-05-18T12:30:58Z"},{"alias_kind":"pith_short_8","alias_value":"4AAY4RFR","created_at":"2026-05-18T12:30:58Z"}],"graph_snapshots":[{"event_id":"sha256:eba7b44374003408d2839133df6e9855b66c10764c0fa8f1df5aaefbad67578e","target":"graph","created_at":"2026-05-18T00:13:37Z","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":"Unifying seemingly disparate algorithmic ideas to produce better performing algorithms has been a longstanding goal in reinforcement learning. As a primary example, TD($\\lambda$) elegantly unifies one-step TD prediction with Monte Carlo methods through the use of eligibility traces and the trace-decay parameter $\\lambda$. Currently, there are a multitude of algorithms that can be used to perform TD control, including Sarsa, $Q$-learning, and Expected Sarsa. These methods are often studied in the one-step case, but they can be extended across multiple time steps to achieve better performance. E","authors_text":"G. Zacharias Holland, J. Fernando Hernandez-Garcia, Kristopher De Asis, Richard S. Sutton","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-03-03T20:19:08Z","title":"Multi-step Reinforcement Learning: A Unifying Algorithm"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.01327","kind":"arxiv","version":2},"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:e946293350b7ad7f4507410a42efac9f7eb6a41c52e3294b0c84e246b743bb91","target":"record","created_at":"2026-05-18T00:13:37Z","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":"9c8927dca16f4b1118fdbe3a58e8b6511d1f2d5f9cd51aa6fd94520f7fbf8413","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-03-03T20:19:08Z","title_canon_sha256":"b48f1fd13340b3b1c4b3394b46e674918616be1165b723f00d0f7c6253435c77"},"schema_version":"1.0","source":{"id":"1703.01327","kind":"arxiv","version":2}},"canonical_sha256":"e0018e44b174c44cf7e9869686a5ebb4518bd39cf319c7215bec60567a3d2dbc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e0018e44b174c44cf7e9869686a5ebb4518bd39cf319c7215bec60567a3d2dbc","first_computed_at":"2026-05-18T00:13:37.926843Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:13:37.926843Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BCfTDEohXLtQYu2riVtFbhy3nMoJXVZOoWzyILDM6C9xkuAQNOM0RLo1NaAxMrpl8P3ItA1ejtYOsOcWtEd9AQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:13:37.927458Z","signed_message":"canonical_sha256_bytes"},"source_id":"1703.01327","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e946293350b7ad7f4507410a42efac9f7eb6a41c52e3294b0c84e246b743bb91","sha256:eba7b44374003408d2839133df6e9855b66c10764c0fa8f1df5aaefbad67578e"],"state_sha256":"19cdcefd60e7a511e1b2b01b2f19119f9dbb112db09e041818e3cc640e4f9954"}