{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:RDLG6OTT76EH7Y7N3K5ZTFBT6A","short_pith_number":"pith:RDLG6OTT","schema_version":"1.0","canonical_sha256":"88d66f3a73ff887fe3eddabb999433f0251c0160cc5b910b8be852e317c9994a","source":{"kind":"arxiv","id":"1802.03171","version":1},"attestation_state":"computed","paper":{"title":"A Unified Approach for Multi-step Temporal-Difference Learning with Eligibility Traces in Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.AI","authors_text":"Gang Pan, Long Yang, Minhao Shi, Qian Zheng, Wenjia Meng","submitted_at":"2018-02-09T08:46:21Z","abstract_excerpt":"Recently, a new multi-step temporal learning algorithm, called $Q(\\sigma)$, unifies $n$-step Tree-Backup (when $\\sigma=0$) and $n$-step Sarsa (when $\\sigma=1$) by introducing a sampling parameter $\\sigma$. However, similar to other multi-step temporal-difference learning algorithms, $Q(\\sigma)$ needs much memory consumption and computation time. Eligibility trace is an important mechanism to transform the off-line updates into efficient on-line ones which consume less memory and computation time. In this paper, we further develop the original $Q(\\sigma)$, combine it with eligibility traces and"},"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":"1802.03171","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-02-09T08:46:21Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"668c01be78064b9abb433c2165a43fe676fbbc0e9fef3ef3226294c5026e9f3b","abstract_canon_sha256":"72dc557adf4cc4384c43c07a8b30e27ddb4ff72fd3924f52781e281ddaa3821a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:23:58.393234Z","signature_b64":"1Mc5SlrUhfKBKmjJ0QLcXkA9/IKMbo9a6OovlVoL+EOqTuQ3IxyQuxk3lZOcdJAt7GEYZRJbGSvoCXFiWj7rDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"88d66f3a73ff887fe3eddabb999433f0251c0160cc5b910b8be852e317c9994a","last_reissued_at":"2026-05-18T00:23:58.392751Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:23:58.392751Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Unified Approach for Multi-step Temporal-Difference Learning with Eligibility Traces in Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.AI","authors_text":"Gang Pan, Long Yang, Minhao Shi, Qian Zheng, Wenjia Meng","submitted_at":"2018-02-09T08:46:21Z","abstract_excerpt":"Recently, a new multi-step temporal learning algorithm, called $Q(\\sigma)$, unifies $n$-step Tree-Backup (when $\\sigma=0$) and $n$-step Sarsa (when $\\sigma=1$) by introducing a sampling parameter $\\sigma$. However, similar to other multi-step temporal-difference learning algorithms, $Q(\\sigma)$ needs much memory consumption and computation time. Eligibility trace is an important mechanism to transform the off-line updates into efficient on-line ones which consume less memory and computation time. In this paper, we further develop the original $Q(\\sigma)$, combine it with eligibility traces and"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.03171","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":"1802.03171","created_at":"2026-05-18T00:23:58.392821+00:00"},{"alias_kind":"arxiv_version","alias_value":"1802.03171v1","created_at":"2026-05-18T00:23:58.392821+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.03171","created_at":"2026-05-18T00:23:58.392821+00:00"},{"alias_kind":"pith_short_12","alias_value":"RDLG6OTT76EH","created_at":"2026-05-18T12:32:50.500415+00:00"},{"alias_kind":"pith_short_16","alias_value":"RDLG6OTT76EH7Y7N","created_at":"2026-05-18T12:32:50.500415+00:00"},{"alias_kind":"pith_short_8","alias_value":"RDLG6OTT","created_at":"2026-05-18T12:32:50.500415+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.11138","citing_title":"Safe Reinforcement Learning using Finite-Horizon Gradient-based Estimation","ref_index":61,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RDLG6OTT76EH7Y7N3K5ZTFBT6A","json":"https://pith.science/pith/RDLG6OTT76EH7Y7N3K5ZTFBT6A.json","graph_json":"https://pith.science/api/pith-number/RDLG6OTT76EH7Y7N3K5ZTFBT6A/graph.json","events_json":"https://pith.science/api/pith-number/RDLG6OTT76EH7Y7N3K5ZTFBT6A/events.json","paper":"https://pith.science/paper/RDLG6OTT"},"agent_actions":{"view_html":"https://pith.science/pith/RDLG6OTT76EH7Y7N3K5ZTFBT6A","download_json":"https://pith.science/pith/RDLG6OTT76EH7Y7N3K5ZTFBT6A.json","view_paper":"https://pith.science/paper/RDLG6OTT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1802.03171&json=true","fetch_graph":"https://pith.science/api/pith-number/RDLG6OTT76EH7Y7N3K5ZTFBT6A/graph.json","fetch_events":"https://pith.science/api/pith-number/RDLG6OTT76EH7Y7N3K5ZTFBT6A/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RDLG6OTT76EH7Y7N3K5ZTFBT6A/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RDLG6OTT76EH7Y7N3K5ZTFBT6A/action/storage_attestation","attest_author":"https://pith.science/pith/RDLG6OTT76EH7Y7N3K5ZTFBT6A/action/author_attestation","sign_citation":"https://pith.science/pith/RDLG6OTT76EH7Y7N3K5ZTFBT6A/action/citation_signature","submit_replication":"https://pith.science/pith/RDLG6OTT76EH7Y7N3K5ZTFBT6A/action/replication_record"}},"created_at":"2026-05-18T00:23:58.392821+00:00","updated_at":"2026-05-18T00:23:58.392821+00:00"}