{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2013:Q523XFRBFIODRFHJUHAFBUNUAY","short_pith_number":"pith:Q523XFRB","schema_version":"1.0","canonical_sha256":"8775bb96212a1c3894e9a1c050d1b406397d2556a465507daa7d7da1d0bdfc16","source":{"kind":"arxiv","id":"1304.3999","version":1},"attestation_state":"computed","paper":{"title":"Off-policy Learning with Eligibility Traces: A Survey","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.AI","authors_text":"Bruno Scherrer (INRIA Lorraine - LORIA), Matthieu Geist","submitted_at":"2013-04-15T06:51:33Z","abstract_excerpt":"In the framework of Markov Decision Processes, off-policy learning, that is the problem of learning a linear approximation of the value function of some fixed policy from one trajectory possibly generated by some other policy. We briefly review on-policy learning algorithms of the literature (gradient-based and least-squares-based), adopting a unified algorithmic view. Then, we highlight a systematic approach for adapting them to off-policy learning with eligibility traces. This leads to some known algorithms - off-policy LSTD(\\lambda), LSPE(\\lambda), TD(\\lambda), TDC/GQ(\\lambda) - and suggest"},"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":"1304.3999","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2013-04-15T06:51:33Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"642d9ecd076e5003e798e83b419e5b51312e36c972b26bea5caf910c87933848","abstract_canon_sha256":"b804b78c1239e384583c275c6f93640b84796c9f27f156f3e68dcac649bc9677"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:28:03.591226Z","signature_b64":"3eSaZAbe4YDW7mMy5nXC8TKbNbIJcAnkZkxxtheJxFt1C28nplcADZ3U6zprG0KLfKaxd6LJ15CTnwCNopk5CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8775bb96212a1c3894e9a1c050d1b406397d2556a465507daa7d7da1d0bdfc16","last_reissued_at":"2026-05-18T03:28:03.590492Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:28:03.590492Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Off-policy Learning with Eligibility Traces: A Survey","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.AI","authors_text":"Bruno Scherrer (INRIA Lorraine - LORIA), Matthieu Geist","submitted_at":"2013-04-15T06:51:33Z","abstract_excerpt":"In the framework of Markov Decision Processes, off-policy learning, that is the problem of learning a linear approximation of the value function of some fixed policy from one trajectory possibly generated by some other policy. We briefly review on-policy learning algorithms of the literature (gradient-based and least-squares-based), adopting a unified algorithmic view. Then, we highlight a systematic approach for adapting them to off-policy learning with eligibility traces. This leads to some known algorithms - off-policy LSTD(\\lambda), LSPE(\\lambda), TD(\\lambda), TDC/GQ(\\lambda) - and suggest"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1304.3999","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":"1304.3999","created_at":"2026-05-18T03:28:03.590588+00:00"},{"alias_kind":"arxiv_version","alias_value":"1304.3999v1","created_at":"2026-05-18T03:28:03.590588+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1304.3999","created_at":"2026-05-18T03:28:03.590588+00:00"},{"alias_kind":"pith_short_12","alias_value":"Q523XFRBFIOD","created_at":"2026-05-18T12:27:57.521954+00:00"},{"alias_kind":"pith_short_16","alias_value":"Q523XFRBFIODRFHJ","created_at":"2026-05-18T12:27:57.521954+00:00"},{"alias_kind":"pith_short_8","alias_value":"Q523XFRB","created_at":"2026-05-18T12:27:57.521954+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/Q523XFRBFIODRFHJUHAFBUNUAY","json":"https://pith.science/pith/Q523XFRBFIODRFHJUHAFBUNUAY.json","graph_json":"https://pith.science/api/pith-number/Q523XFRBFIODRFHJUHAFBUNUAY/graph.json","events_json":"https://pith.science/api/pith-number/Q523XFRBFIODRFHJUHAFBUNUAY/events.json","paper":"https://pith.science/paper/Q523XFRB"},"agent_actions":{"view_html":"https://pith.science/pith/Q523XFRBFIODRFHJUHAFBUNUAY","download_json":"https://pith.science/pith/Q523XFRBFIODRFHJUHAFBUNUAY.json","view_paper":"https://pith.science/paper/Q523XFRB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1304.3999&json=true","fetch_graph":"https://pith.science/api/pith-number/Q523XFRBFIODRFHJUHAFBUNUAY/graph.json","fetch_events":"https://pith.science/api/pith-number/Q523XFRBFIODRFHJUHAFBUNUAY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Q523XFRBFIODRFHJUHAFBUNUAY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Q523XFRBFIODRFHJUHAFBUNUAY/action/storage_attestation","attest_author":"https://pith.science/pith/Q523XFRBFIODRFHJUHAFBUNUAY/action/author_attestation","sign_citation":"https://pith.science/pith/Q523XFRBFIODRFHJUHAFBUNUAY/action/citation_signature","submit_replication":"https://pith.science/pith/Q523XFRBFIODRFHJUHAFBUNUAY/action/replication_record"}},"created_at":"2026-05-18T03:28:03.590588+00:00","updated_at":"2026-05-18T03:28:03.590588+00:00"}