{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:4AAY4RFROTCEZ57JQ2LINJPLWR","short_pith_number":"pith:4AAY4RFR","schema_version":"1.0","canonical_sha256":"e0018e44b174c44cf7e9869686a5ebb4518bd39cf319c7215bec60567a3d2dbc","source":{"kind":"arxiv","id":"1703.01327","version":2},"attestation_state":"computed","paper":{"title":"Multi-step Reinforcement Learning: A Unifying Algorithm","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"G. Zacharias Holland, J. Fernando Hernandez-Garcia, Kristopher De Asis, Richard S. Sutton","submitted_at":"2017-03-03T20:19:08Z","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"},"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":"1703.01327","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-03-03T20:19:08Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"b48f1fd13340b3b1c4b3394b46e674918616be1165b723f00d0f7c6253435c77","abstract_canon_sha256":"9c8927dca16f4b1118fdbe3a58e8b6511d1f2d5f9cd51aa6fd94520f7fbf8413"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:13:37.927458Z","signature_b64":"BCfTDEohXLtQYu2riVtFbhy3nMoJXVZOoWzyILDM6C9xkuAQNOM0RLo1NaAxMrpl8P3ItA1ejtYOsOcWtEd9AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e0018e44b174c44cf7e9869686a5ebb4518bd39cf319c7215bec60567a3d2dbc","last_reissued_at":"2026-05-18T00:13:37.926843Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:13:37.926843Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-step Reinforcement Learning: A Unifying Algorithm","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"G. Zacharias Holland, J. Fernando Hernandez-Garcia, Kristopher De Asis, Richard S. Sutton","submitted_at":"2017-03-03T20:19:08Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.01327","kind":"arxiv","version":2},"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":"1703.01327","created_at":"2026-05-18T00:13:37.926940+00:00"},{"alias_kind":"arxiv_version","alias_value":"1703.01327v2","created_at":"2026-05-18T00:13:37.926940+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.01327","created_at":"2026-05-18T00:13:37.926940+00:00"},{"alias_kind":"pith_short_12","alias_value":"4AAY4RFROTCE","created_at":"2026-05-18T12:30:58.224056+00:00"},{"alias_kind":"pith_short_16","alias_value":"4AAY4RFROTCEZ57J","created_at":"2026-05-18T12:30:58.224056+00:00"},{"alias_kind":"pith_short_8","alias_value":"4AAY4RFR","created_at":"2026-05-18T12:30:58.224056+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.05812","citing_title":"Long-Horizon Q-Learning: Accurate Value Learning via n-Step Inequalities","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05812","citing_title":"Long-Horizon Q-Learning: Accurate Value Learning via n-Step Inequalities","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4AAY4RFROTCEZ57JQ2LINJPLWR","json":"https://pith.science/pith/4AAY4RFROTCEZ57JQ2LINJPLWR.json","graph_json":"https://pith.science/api/pith-number/4AAY4RFROTCEZ57JQ2LINJPLWR/graph.json","events_json":"https://pith.science/api/pith-number/4AAY4RFROTCEZ57JQ2LINJPLWR/events.json","paper":"https://pith.science/paper/4AAY4RFR"},"agent_actions":{"view_html":"https://pith.science/pith/4AAY4RFROTCEZ57JQ2LINJPLWR","download_json":"https://pith.science/pith/4AAY4RFROTCEZ57JQ2LINJPLWR.json","view_paper":"https://pith.science/paper/4AAY4RFR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1703.01327&json=true","fetch_graph":"https://pith.science/api/pith-number/4AAY4RFROTCEZ57JQ2LINJPLWR/graph.json","fetch_events":"https://pith.science/api/pith-number/4AAY4RFROTCEZ57JQ2LINJPLWR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4AAY4RFROTCEZ57JQ2LINJPLWR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4AAY4RFROTCEZ57JQ2LINJPLWR/action/storage_attestation","attest_author":"https://pith.science/pith/4AAY4RFROTCEZ57JQ2LINJPLWR/action/author_attestation","sign_citation":"https://pith.science/pith/4AAY4RFROTCEZ57JQ2LINJPLWR/action/citation_signature","submit_replication":"https://pith.science/pith/4AAY4RFROTCEZ57JQ2LINJPLWR/action/replication_record"}},"created_at":"2026-05-18T00:13:37.926940+00:00","updated_at":"2026-05-18T00:13:37.926940+00:00"}