{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:MSQ7FDF5HATA47DUZG5Y5HWS2O","short_pith_number":"pith:MSQ7FDF5","canonical_record":{"source":{"id":"1809.08926","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-21T06:09:21Z","cross_cats_sorted":["cs.AI","math.OC","stat.ML"],"title_canon_sha256":"a0f89356f045ec9643134ea4789142a48bf3731108710b39621265f2d70f8f05","abstract_canon_sha256":"5d3f58fdcb6eb64593bd8bf3463b847fac84c5332ecedde399c7945fda4c13d1"},"schema_version":"1.0"},"canonical_sha256":"64a1f28cbd38260e7c74c9bb8e9ed2d3a73713eb20dbd5f387b72fda3e7b898d","source":{"kind":"arxiv","id":"1809.08926","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1809.08926","created_at":"2026-05-18T00:05:03Z"},{"alias_kind":"arxiv_version","alias_value":"1809.08926v1","created_at":"2026-05-18T00:05:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.08926","created_at":"2026-05-18T00:05:03Z"},{"alias_kind":"pith_short_12","alias_value":"MSQ7FDF5HATA","created_at":"2026-05-18T12:32:40Z"},{"alias_kind":"pith_short_16","alias_value":"MSQ7FDF5HATA47DU","created_at":"2026-05-18T12:32:40Z"},{"alias_kind":"pith_short_8","alias_value":"MSQ7FDF5","created_at":"2026-05-18T12:32:40Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:MSQ7FDF5HATA47DUZG5Y5HWS2O","target":"record","payload":{"canonical_record":{"source":{"id":"1809.08926","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-21T06:09:21Z","cross_cats_sorted":["cs.AI","math.OC","stat.ML"],"title_canon_sha256":"a0f89356f045ec9643134ea4789142a48bf3731108710b39621265f2d70f8f05","abstract_canon_sha256":"5d3f58fdcb6eb64593bd8bf3463b847fac84c5332ecedde399c7945fda4c13d1"},"schema_version":"1.0"},"canonical_sha256":"64a1f28cbd38260e7c74c9bb8e9ed2d3a73713eb20dbd5f387b72fda3e7b898d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:05:03.147470Z","signature_b64":"hDT5W1efiGPdOzZZeGexfM0Q6KpX1WRhfkZT7W1VfE1dJrQ9HjKn1vv2iLLcMvBYzbtOKtVZtObiFKARggP6Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"64a1f28cbd38260e7c74c9bb8e9ed2d3a73713eb20dbd5f387b72fda3e7b898d","last_reissued_at":"2026-05-18T00:05:03.147040Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:05:03.147040Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1809.08926","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":"2026-05-18T00:05:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6dysOw9TGWxL6RgR/i3feSNfHTcnwc6e+8ZL6/Ued0XO+9OcpaN7vWhO6kN/AaRVqg4fVnOUXj4J0x/Ef93RAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T13:52:52.878246Z"},"content_sha256":"7dc0edaeee54d599eb371eb055edb0f0449bf6ba84e58d333ec01d02543770d4","schema_version":"1.0","event_id":"sha256:7dc0edaeee54d599eb371eb055edb0f0449bf6ba84e58d333ec01d02543770d4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:MSQ7FDF5HATA47DUZG5Y5HWS2O","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Finite Sample Analysis of the GTD Policy Evaluation Algorithms in Markov Setting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Tie-Yan Liu, Wei Chen, Yue Wang, Yuting Liu, Zhi-Ming Ma","submitted_at":"2018-09-21T06:09:21Z","abstract_excerpt":"In reinforcement learning (RL) , one of the key components is policy evaluation, which aims to estimate the value function (i.e., expected long-term accumulated reward) of a policy. With a good policy evaluation method, the RL algorithms will estimate the value function more accurately and find a better policy. When the state space is large or continuous \\emph{Gradient-based Temporal Difference(GTD)} policy evaluation algorithms with linear function approximation are widely used. Considering that the collection of the evaluation data is both time and reward consuming, a clear understanding of "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.08926","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":"2026-05-18T00:05:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yKS44nkLN/FKaD/FdwQXKTKkNgn/hgW+/mnabpg1MjMORi6XeBY81q9O8akh3hTHfCWOpMNY1r4TOSLPO4GcCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T13:52:52.878902Z"},"content_sha256":"f11a59d0d73b8eeb504183ec8144e01a4169b7ab8be8529ca1cdc0a17d73df6f","schema_version":"1.0","event_id":"sha256:f11a59d0d73b8eeb504183ec8144e01a4169b7ab8be8529ca1cdc0a17d73df6f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MSQ7FDF5HATA47DUZG5Y5HWS2O/bundle.json","state_url":"https://pith.science/pith/MSQ7FDF5HATA47DUZG5Y5HWS2O/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MSQ7FDF5HATA47DUZG5Y5HWS2O/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":"2026-05-27T13:52:52Z","links":{"resolver":"https://pith.science/pith/MSQ7FDF5HATA47DUZG5Y5HWS2O","bundle":"https://pith.science/pith/MSQ7FDF5HATA47DUZG5Y5HWS2O/bundle.json","state":"https://pith.science/pith/MSQ7FDF5HATA47DUZG5Y5HWS2O/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MSQ7FDF5HATA47DUZG5Y5HWS2O/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:MSQ7FDF5HATA47DUZG5Y5HWS2O","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":"5d3f58fdcb6eb64593bd8bf3463b847fac84c5332ecedde399c7945fda4c13d1","cross_cats_sorted":["cs.AI","math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-21T06:09:21Z","title_canon_sha256":"a0f89356f045ec9643134ea4789142a48bf3731108710b39621265f2d70f8f05"},"schema_version":"1.0","source":{"id":"1809.08926","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1809.08926","created_at":"2026-05-18T00:05:03Z"},{"alias_kind":"arxiv_version","alias_value":"1809.08926v1","created_at":"2026-05-18T00:05:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.08926","created_at":"2026-05-18T00:05:03Z"},{"alias_kind":"pith_short_12","alias_value":"MSQ7FDF5HATA","created_at":"2026-05-18T12:32:40Z"},{"alias_kind":"pith_short_16","alias_value":"MSQ7FDF5HATA47DU","created_at":"2026-05-18T12:32:40Z"},{"alias_kind":"pith_short_8","alias_value":"MSQ7FDF5","created_at":"2026-05-18T12:32:40Z"}],"graph_snapshots":[{"event_id":"sha256:f11a59d0d73b8eeb504183ec8144e01a4169b7ab8be8529ca1cdc0a17d73df6f","target":"graph","created_at":"2026-05-18T00:05:03Z","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 reinforcement learning (RL) , one of the key components is policy evaluation, which aims to estimate the value function (i.e., expected long-term accumulated reward) of a policy. With a good policy evaluation method, the RL algorithms will estimate the value function more accurately and find a better policy. When the state space is large or continuous \\emph{Gradient-based Temporal Difference(GTD)} policy evaluation algorithms with linear function approximation are widely used. Considering that the collection of the evaluation data is both time and reward consuming, a clear understanding of ","authors_text":"Tie-Yan Liu, Wei Chen, Yue Wang, Yuting Liu, Zhi-Ming Ma","cross_cats":["cs.AI","math.OC","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-21T06:09:21Z","title":"Finite Sample Analysis of the GTD Policy Evaluation Algorithms in Markov Setting"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.08926","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":"sha256:7dc0edaeee54d599eb371eb055edb0f0449bf6ba84e58d333ec01d02543770d4","target":"record","created_at":"2026-05-18T00:05:03Z","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":"5d3f58fdcb6eb64593bd8bf3463b847fac84c5332ecedde399c7945fda4c13d1","cross_cats_sorted":["cs.AI","math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-21T06:09:21Z","title_canon_sha256":"a0f89356f045ec9643134ea4789142a48bf3731108710b39621265f2d70f8f05"},"schema_version":"1.0","source":{"id":"1809.08926","kind":"arxiv","version":1}},"canonical_sha256":"64a1f28cbd38260e7c74c9bb8e9ed2d3a73713eb20dbd5f387b72fda3e7b898d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"64a1f28cbd38260e7c74c9bb8e9ed2d3a73713eb20dbd5f387b72fda3e7b898d","first_computed_at":"2026-05-18T00:05:03.147040Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:05:03.147040Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hDT5W1efiGPdOzZZeGexfM0Q6KpX1WRhfkZT7W1VfE1dJrQ9HjKn1vv2iLLcMvBYzbtOKtVZtObiFKARggP6Bw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:05:03.147470Z","signed_message":"canonical_sha256_bytes"},"source_id":"1809.08926","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7dc0edaeee54d599eb371eb055edb0f0449bf6ba84e58d333ec01d02543770d4","sha256:f11a59d0d73b8eeb504183ec8144e01a4169b7ab8be8529ca1cdc0a17d73df6f"],"state_sha256":"4b0dfd4be740ee6cc3d752f640f6abab540c9890e13aca8d3067f3c81a43db78"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DKDRzDAtG421G1Y6Y+VpJlLpnkEVGe6LDB5zLaL+NqVwr0SFf/FAogoQZmGV59pWU3oYW6WMviLV6xuFoTZnCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T13:52:52.882468Z","bundle_sha256":"944344c552a0c02cd4a1fbbaaa9ce43355fc7cb7ba0647cb414c50502032e040"}}