{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:7DJ2F2SE3TW2QIZXKOTNDBPPPP","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":"d3a1b0a891cd2aed5109a4c61cb9d0d771fc3d5b3c9e56460254e6f2ddedf48e","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-07-05T02:34:40Z","title_canon_sha256":"c21d3429b15320ae0117abfa2a53bc225a56eb6002506f12016cf7dc8b78b2ec"},"schema_version":"1.0","source":{"id":"1807.01830","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1807.01830","created_at":"2026-05-18T00:06:20Z"},{"alias_kind":"arxiv_version","alias_value":"1807.01830v1","created_at":"2026-05-18T00:06:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.01830","created_at":"2026-05-18T00:06:20Z"},{"alias_kind":"pith_short_12","alias_value":"7DJ2F2SE3TW2","created_at":"2026-05-18T12:32:11Z"},{"alias_kind":"pith_short_16","alias_value":"7DJ2F2SE3TW2QIZX","created_at":"2026-05-18T12:32:11Z"},{"alias_kind":"pith_short_8","alias_value":"7DJ2F2SE","created_at":"2026-05-18T12:32:11Z"}],"graph_snapshots":[{"event_id":"sha256:2c59f2062208c49f29c683f8a8b391bde7b88d89174de8ce417ce285b6bf1b5e","target":"graph","created_at":"2026-05-18T00:06:20Z","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":"Multi-step temporal difference (TD) learning is an important approach in reinforcement learning, as it unifies one-step TD learning with Monte Carlo methods in a way where intermediate algorithms can outperform either extreme. They address a bias-variance trade off between reliance on current estimates, which could be poor, and incorporating longer sampled reward sequences into the updates. Especially in the off-policy setting, where the agent aims to learn about a policy different from the one generating its behaviour, the variance in the updates can cause learning to diverge as the number of","authors_text":"Kristopher De Asis, Richard S. Sutton","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-07-05T02:34:40Z","title":"Per-decision Multi-step Temporal Difference Learning with Control Variates"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.01830","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":"sha256:5575ecf178d9364d7776a16cb5acc3b0ebde98703fae4c7de2ccb2edf778f087","target":"record","created_at":"2026-05-18T00:06:20Z","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":"d3a1b0a891cd2aed5109a4c61cb9d0d771fc3d5b3c9e56460254e6f2ddedf48e","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-07-05T02:34:40Z","title_canon_sha256":"c21d3429b15320ae0117abfa2a53bc225a56eb6002506f12016cf7dc8b78b2ec"},"schema_version":"1.0","source":{"id":"1807.01830","kind":"arxiv","version":1}},"canonical_sha256":"f8d3a2ea44dceda8233753a6d185ef7bc9c6a9b22daa5c5772da7e15fe69971d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f8d3a2ea44dceda8233753a6d185ef7bc9c6a9b22daa5c5772da7e15fe69971d","first_computed_at":"2026-05-18T00:06:20.067108Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:06:20.067108Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BET6md4L2Lyc1ZeFm5GCdcII6Pc3AqF458QQ8nxbwFMsvpUSuyQERvCp7+Zjmh+r2rvz+gQoB8+M82YNzAqyAw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:06:20.067567Z","signed_message":"canonical_sha256_bytes"},"source_id":"1807.01830","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5575ecf178d9364d7776a16cb5acc3b0ebde98703fae4c7de2ccb2edf778f087","sha256:2c59f2062208c49f29c683f8a8b391bde7b88d89174de8ce417ce285b6bf1b5e"],"state_sha256":"59625270f7064be789fd0222d8523b720524924bea05ea501a41b6f2dcc619a9"}