{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2013:Q523XFRBFIODRFHJUHAFBUNUAY","short_pith_number":"pith:Q523XFRB","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"},"canonical_sha256":"8775bb96212a1c3894e9a1c050d1b406397d2556a465507daa7d7da1d0bdfc16","source":{"kind":"arxiv","id":"1304.3999","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1304.3999","created_at":"2026-05-18T03:28:03Z"},{"alias_kind":"arxiv_version","alias_value":"1304.3999v1","created_at":"2026-05-18T03:28:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1304.3999","created_at":"2026-05-18T03:28:03Z"},{"alias_kind":"pith_short_12","alias_value":"Q523XFRBFIOD","created_at":"2026-05-18T12:27:57Z"},{"alias_kind":"pith_short_16","alias_value":"Q523XFRBFIODRFHJ","created_at":"2026-05-18T12:27:57Z"},{"alias_kind":"pith_short_8","alias_value":"Q523XFRB","created_at":"2026-05-18T12:27:57Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2013:Q523XFRBFIODRFHJUHAFBUNUAY","target":"record","payload":{"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"},"canonical_sha256":"8775bb96212a1c3894e9a1c050d1b406397d2556a465507daa7d7da1d0bdfc16","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"},"source_kind":"arxiv","source_id":"1304.3999","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T03:28:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cgUVYJYcIanyuKyfhYs001bZyZ3x8+OteIgw134qQt71sTMnkyIvdeMs4m7cYqg4dXzQhz0q2CSS3LMyzZuMDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T00:43:56.302712Z"},"content_sha256":"431bdce5bcf2ee818906119eb9a951daa0dadcd5e20c5b093139fe5023b50ba4","schema_version":"1.0","event_id":"sha256:431bdce5bcf2ee818906119eb9a951daa0dadcd5e20c5b093139fe5023b50ba4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2013:Q523XFRBFIODRFHJUHAFBUNUAY","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T03:28:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"p6EC8wbanvsB7kD+sKN/PlFWKYLD4qYDRLb/I5S08DJgm+lCvN8V6Z1OiTpAildAduiD+KsqdZIAC21jnjvNAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T00:43:56.303488Z"},"content_sha256":"6db91938093f81013a198d2a20c899e26c1ae30030848c5196d6449187adc3aa","schema_version":"1.0","event_id":"sha256:6db91938093f81013a198d2a20c899e26c1ae30030848c5196d6449187adc3aa"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Q523XFRBFIODRFHJUHAFBUNUAY/bundle.json","state_url":"https://pith.science/pith/Q523XFRBFIODRFHJUHAFBUNUAY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Q523XFRBFIODRFHJUHAFBUNUAY/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-01T00:43:56Z","links":{"resolver":"https://pith.science/pith/Q523XFRBFIODRFHJUHAFBUNUAY","bundle":"https://pith.science/pith/Q523XFRBFIODRFHJUHAFBUNUAY/bundle.json","state":"https://pith.science/pith/Q523XFRBFIODRFHJUHAFBUNUAY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Q523XFRBFIODRFHJUHAFBUNUAY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2013:Q523XFRBFIODRFHJUHAFBUNUAY","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":"b804b78c1239e384583c275c6f93640b84796c9f27f156f3e68dcac649bc9677","cross_cats_sorted":["cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2013-04-15T06:51:33Z","title_canon_sha256":"642d9ecd076e5003e798e83b419e5b51312e36c972b26bea5caf910c87933848"},"schema_version":"1.0","source":{"id":"1304.3999","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1304.3999","created_at":"2026-05-18T03:28:03Z"},{"alias_kind":"arxiv_version","alias_value":"1304.3999v1","created_at":"2026-05-18T03:28:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1304.3999","created_at":"2026-05-18T03:28:03Z"},{"alias_kind":"pith_short_12","alias_value":"Q523XFRBFIOD","created_at":"2026-05-18T12:27:57Z"},{"alias_kind":"pith_short_16","alias_value":"Q523XFRBFIODRFHJ","created_at":"2026-05-18T12:27:57Z"},{"alias_kind":"pith_short_8","alias_value":"Q523XFRB","created_at":"2026-05-18T12:27:57Z"}],"graph_snapshots":[{"event_id":"sha256:6db91938093f81013a198d2a20c899e26c1ae30030848c5196d6449187adc3aa","target":"graph","created_at":"2026-05-18T03:28:03Z","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":"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","authors_text":"Bruno Scherrer (INRIA Lorraine - LORIA), Matthieu Geist","cross_cats":["cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2013-04-15T06:51:33Z","title":"Off-policy Learning with Eligibility Traces: A Survey"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1304.3999","kind":"arxiv","version":1},"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":"sha256:431bdce5bcf2ee818906119eb9a951daa0dadcd5e20c5b093139fe5023b50ba4","target":"record","created_at":"2026-05-18T03:28:03Z","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":"b804b78c1239e384583c275c6f93640b84796c9f27f156f3e68dcac649bc9677","cross_cats_sorted":["cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2013-04-15T06:51:33Z","title_canon_sha256":"642d9ecd076e5003e798e83b419e5b51312e36c972b26bea5caf910c87933848"},"schema_version":"1.0","source":{"id":"1304.3999","kind":"arxiv","version":1}},"canonical_sha256":"8775bb96212a1c3894e9a1c050d1b406397d2556a465507daa7d7da1d0bdfc16","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8775bb96212a1c3894e9a1c050d1b406397d2556a465507daa7d7da1d0bdfc16","first_computed_at":"2026-05-18T03:28:03.590492Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:28:03.590492Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3eSaZAbe4YDW7mMy5nXC8TKbNbIJcAnkZkxxtheJxFt1C28nplcADZ3U6zprG0KLfKaxd6LJ15CTnwCNopk5CA==","signature_status":"signed_v1","signed_at":"2026-05-18T03:28:03.591226Z","signed_message":"canonical_sha256_bytes"},"source_id":"1304.3999","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:431bdce5bcf2ee818906119eb9a951daa0dadcd5e20c5b093139fe5023b50ba4","sha256:6db91938093f81013a198d2a20c899e26c1ae30030848c5196d6449187adc3aa"],"state_sha256":"ced29d88b5ac5a900be88e3ba6dc2d82d45dbb1857d7acdc8397804f1d340b37"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"scd3/ZmOnif2rWrCMufoBH+5+B2b6L9M/PEaRvxFrypEVlHkdCVuNI2N5cnQbENc8HADwpccAcWST+IkSKMKCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T00:43:56.307266Z","bundle_sha256":"3b1b4a0ed5e014973d0d89a08345a01ac34aa064438a28af320f9a66c5a49a30"}}