{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:743LAUG37E7HHNC2RBZE3O6MSM","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":"e62a8d374ef885a8dff29411f2645715adf57c173f8a3ddc02750eb15610a52f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-01-03T23:29:04Z","title_canon_sha256":"b10e6638d94725ce41ca9c3c69eeefb68c4c0e63e0036b17d6d6a8e6dc63184b"},"schema_version":"1.0","source":{"id":"1701.00867","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1701.00867","created_at":"2026-05-18T00:53:22Z"},{"alias_kind":"arxiv_version","alias_value":"1701.00867v1","created_at":"2026-05-18T00:53:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1701.00867","created_at":"2026-05-18T00:53:22Z"},{"alias_kind":"pith_short_12","alias_value":"743LAUG37E7H","created_at":"2026-05-18T12:31:03Z"},{"alias_kind":"pith_short_16","alias_value":"743LAUG37E7HHNC2","created_at":"2026-05-18T12:31:03Z"},{"alias_kind":"pith_short_8","alias_value":"743LAUG3","created_at":"2026-05-18T12:31:03Z"}],"graph_snapshots":[{"event_id":"sha256:49313a6c19ce4b67f28fbca59c14baf33bb8d970612537ce889b7d82fd1dfb5f","target":"graph","created_at":"2026-05-18T00:53:22Z","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":"The high variance issue in unbiased policy-gradient methods such as VPG and REINFORCE is typically mitigated by adding a baseline. However, the baseline fitting itself suffers from the underfitting or the overfitting problem. In this paper, we develop a K-fold method for baseline estimation in policy gradient algorithms. The parameter K is the baseline estimation hyperparameter that can adjust the bias-variance trade-off in the baseline estimates. We demonstrate the usefulness of our approach via two state-of-the-art policy gradient algorithms on three MuJoCo locomotive control tasks.","authors_text":"Abhishek Mishra, Nithyanand Kota, Pieter Abbeel, Sunil Srinivasa, Xi (Peter) Chen","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-01-03T23:29:04Z","title":"A K-fold Method for Baseline Estimation in Policy Gradient Algorithms"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1701.00867","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:de338314d97fcd1f7b19056c5e04621e733789e2219ade1a0a93f78ca6fa39f3","target":"record","created_at":"2026-05-18T00:53:22Z","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":"e62a8d374ef885a8dff29411f2645715adf57c173f8a3ddc02750eb15610a52f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-01-03T23:29:04Z","title_canon_sha256":"b10e6638d94725ce41ca9c3c69eeefb68c4c0e63e0036b17d6d6a8e6dc63184b"},"schema_version":"1.0","source":{"id":"1701.00867","kind":"arxiv","version":1}},"canonical_sha256":"ff36b050dbf93e73b45a88724dbbcc9321c4d1ed8a95611a82886a22b2c82984","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ff36b050dbf93e73b45a88724dbbcc9321c4d1ed8a95611a82886a22b2c82984","first_computed_at":"2026-05-18T00:53:22.028051Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:53:22.028051Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cr2mvW/HrVuypL5BhWTGGg/Vb9PVBO/PQ3oQHaS4PxS2sfiu0UOadxha2ZTPJ43k81T6vnITYjCYE4PObhIwAA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:53:22.028651Z","signed_message":"canonical_sha256_bytes"},"source_id":"1701.00867","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:de338314d97fcd1f7b19056c5e04621e733789e2219ade1a0a93f78ca6fa39f3","sha256:49313a6c19ce4b67f28fbca59c14baf33bb8d970612537ce889b7d82fd1dfb5f"],"state_sha256":"a05fe0b23fe0e1f439b2fa68c10012e765f929cd0f34e802dfbdae28bfb3dde8"}