{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:RD5Z6YTJIO3VPEG4HOYDWGXPXO","short_pith_number":"pith:RD5Z6YTJ","canonical_record":{"source":{"id":"1705.09322","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-05-25T18:37:55Z","cross_cats_sorted":[],"title_canon_sha256":"818216b1858be12da8991dde629608451b19dfc67ddcf9cd4eb0d351dd4eaa01","abstract_canon_sha256":"ebbd32ea4d972a66bf07fef5c94042b3ff86b574d6b9f9d231b71ed62641149c"},"schema_version":"1.0"},"canonical_sha256":"88fb9f626943b75790dc3bb03b1aefbb843dc7b2c6feadd5db8c42e85b883e5f","source":{"kind":"arxiv","id":"1705.09322","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1705.09322","created_at":"2026-05-17T23:57:03Z"},{"alias_kind":"arxiv_version","alias_value":"1705.09322v4","created_at":"2026-05-17T23:57:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.09322","created_at":"2026-05-17T23:57:03Z"},{"alias_kind":"pith_short_12","alias_value":"RD5Z6YTJIO3V","created_at":"2026-05-18T12:31:39Z"},{"alias_kind":"pith_short_16","alias_value":"RD5Z6YTJIO3VPEG4","created_at":"2026-05-18T12:31:39Z"},{"alias_kind":"pith_short_8","alias_value":"RD5Z6YTJ","created_at":"2026-05-18T12:31:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:RD5Z6YTJIO3VPEG4HOYDWGXPXO","target":"record","payload":{"canonical_record":{"source":{"id":"1705.09322","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-05-25T18:37:55Z","cross_cats_sorted":[],"title_canon_sha256":"818216b1858be12da8991dde629608451b19dfc67ddcf9cd4eb0d351dd4eaa01","abstract_canon_sha256":"ebbd32ea4d972a66bf07fef5c94042b3ff86b574d6b9f9d231b71ed62641149c"},"schema_version":"1.0"},"canonical_sha256":"88fb9f626943b75790dc3bb03b1aefbb843dc7b2c6feadd5db8c42e85b883e5f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:57:03.366234Z","signature_b64":"0gUQ2AAA8QfDcnfyKfTsKfBT0PbRcPC0RZgGDigsD5nzVIyWMIosQ2stkKK7kGkmhRy9PNZsfYTgQw8ol28pDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"88fb9f626943b75790dc3bb03b1aefbb843dc7b2c6feadd5db8c42e85b883e5f","last_reissued_at":"2026-05-17T23:57:03.365582Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:57:03.365582Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1705.09322","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:57:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"V8PO4OaNEXB8agRbcKNlW/2Y2+Anc/D0uT7fMMDCsADfJFeTYnK8rifYWwLlW5dBJcvgbFJ4SRDdnyU3cdVVCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T16:31:36.299925Z"},"content_sha256":"7593f141a3a814c56ddb1eb925c0e38d2bf5d747de3c4b4c88b6825f1c4ecda2","schema_version":"1.0","event_id":"sha256:7593f141a3a814c56ddb1eb925c0e38d2bf5d747de3c4b4c88b6825f1c4ecda2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:RD5Z6YTJIO3VPEG4HOYDWGXPXO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Convergent Tree Backup and Retrace with Function Approximation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ahmed Touati, Doina Precup, Pascal Vincent, Pierre-Luc Bacon","submitted_at":"2017-05-25T18:37:55Z","abstract_excerpt":"Off-policy learning is key to scaling up reinforcement learning as it allows to learn about a target policy from the experience generated by a different behavior policy. Unfortunately, it has been challenging to combine off-policy learning with function approximation and multi-step bootstrapping in a way that leads to both stable and efficient algorithms. In this work, we show that the \\textsc{Tree Backup} and \\textsc{Retrace} algorithms are unstable with linear function approximation, both in theory and in practice with specific examples. Based on our analysis, we then derive stable and effic"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.09322","kind":"arxiv","version":4},"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":"2026-05-17T23:57:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aynOSuiOOdS9/s1Rklv3yJ9/AGWLYiO4vumtT84nFX9SkYl5KN7LXwUPOOOiOdVZDowmcAeVTDKetbwYjgmwCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T16:31:36.300275Z"},"content_sha256":"08fd883dedc1e506538caa6cbf1f65bd309bc671b57bc487478655525d69b1b1","schema_version":"1.0","event_id":"sha256:08fd883dedc1e506538caa6cbf1f65bd309bc671b57bc487478655525d69b1b1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RD5Z6YTJIO3VPEG4HOYDWGXPXO/bundle.json","state_url":"https://pith.science/pith/RD5Z6YTJIO3VPEG4HOYDWGXPXO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RD5Z6YTJIO3VPEG4HOYDWGXPXO/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":"2026-06-05T16:31:36Z","links":{"resolver":"https://pith.science/pith/RD5Z6YTJIO3VPEG4HOYDWGXPXO","bundle":"https://pith.science/pith/RD5Z6YTJIO3VPEG4HOYDWGXPXO/bundle.json","state":"https://pith.science/pith/RD5Z6YTJIO3VPEG4HOYDWGXPXO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RD5Z6YTJIO3VPEG4HOYDWGXPXO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:RD5Z6YTJIO3VPEG4HOYDWGXPXO","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":"ebbd32ea4d972a66bf07fef5c94042b3ff86b574d6b9f9d231b71ed62641149c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-05-25T18:37:55Z","title_canon_sha256":"818216b1858be12da8991dde629608451b19dfc67ddcf9cd4eb0d351dd4eaa01"},"schema_version":"1.0","source":{"id":"1705.09322","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1705.09322","created_at":"2026-05-17T23:57:03Z"},{"alias_kind":"arxiv_version","alias_value":"1705.09322v4","created_at":"2026-05-17T23:57:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.09322","created_at":"2026-05-17T23:57:03Z"},{"alias_kind":"pith_short_12","alias_value":"RD5Z6YTJIO3V","created_at":"2026-05-18T12:31:39Z"},{"alias_kind":"pith_short_16","alias_value":"RD5Z6YTJIO3VPEG4","created_at":"2026-05-18T12:31:39Z"},{"alias_kind":"pith_short_8","alias_value":"RD5Z6YTJ","created_at":"2026-05-18T12:31:39Z"}],"graph_snapshots":[{"event_id":"sha256:08fd883dedc1e506538caa6cbf1f65bd309bc671b57bc487478655525d69b1b1","target":"graph","created_at":"2026-05-17T23:57:03Z","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":"Off-policy learning is key to scaling up reinforcement learning as it allows to learn about a target policy from the experience generated by a different behavior policy. Unfortunately, it has been challenging to combine off-policy learning with function approximation and multi-step bootstrapping in a way that leads to both stable and efficient algorithms. In this work, we show that the \\textsc{Tree Backup} and \\textsc{Retrace} algorithms are unstable with linear function approximation, both in theory and in practice with specific examples. Based on our analysis, we then derive stable and effic","authors_text":"Ahmed Touati, Doina Precup, Pascal Vincent, Pierre-Luc Bacon","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-05-25T18:37:55Z","title":"Convergent Tree Backup and Retrace with Function Approximation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.09322","kind":"arxiv","version":4},"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":"sha256:7593f141a3a814c56ddb1eb925c0e38d2bf5d747de3c4b4c88b6825f1c4ecda2","target":"record","created_at":"2026-05-17T23:57:03Z","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":"ebbd32ea4d972a66bf07fef5c94042b3ff86b574d6b9f9d231b71ed62641149c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-05-25T18:37:55Z","title_canon_sha256":"818216b1858be12da8991dde629608451b19dfc67ddcf9cd4eb0d351dd4eaa01"},"schema_version":"1.0","source":{"id":"1705.09322","kind":"arxiv","version":4}},"canonical_sha256":"88fb9f626943b75790dc3bb03b1aefbb843dc7b2c6feadd5db8c42e85b883e5f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"88fb9f626943b75790dc3bb03b1aefbb843dc7b2c6feadd5db8c42e85b883e5f","first_computed_at":"2026-05-17T23:57:03.365582Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:57:03.365582Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0gUQ2AAA8QfDcnfyKfTsKfBT0PbRcPC0RZgGDigsD5nzVIyWMIosQ2stkKK7kGkmhRy9PNZsfYTgQw8ol28pDw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:57:03.366234Z","signed_message":"canonical_sha256_bytes"},"source_id":"1705.09322","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7593f141a3a814c56ddb1eb925c0e38d2bf5d747de3c4b4c88b6825f1c4ecda2","sha256:08fd883dedc1e506538caa6cbf1f65bd309bc671b57bc487478655525d69b1b1"],"state_sha256":"cf1b8e94a54da2433fd1ad4f04b32415a6ced6dc5887f0720ec73a08aaea7bc3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tTq7VrwbNocDEvIzS+wWto7HSieIKnRjpNvBJoKxLtCbJlERbSfCdhOmFMqgeWcuzltnP8uVLx0RO1vVhJ7FAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-05T16:31:36.302527Z","bundle_sha256":"b311914021953340b31fa28163bd052eefd62ba046eaeb60563006bf115f3cbd"}}