{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:743LAUG37E7HHNC2RBZE3O6MSM","short_pith_number":"pith:743LAUG3","canonical_record":{"source":{"id":"1701.00867","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-01-03T23:29:04Z","cross_cats_sorted":[],"title_canon_sha256":"b10e6638d94725ce41ca9c3c69eeefb68c4c0e63e0036b17d6d6a8e6dc63184b","abstract_canon_sha256":"e62a8d374ef885a8dff29411f2645715adf57c173f8a3ddc02750eb15610a52f"},"schema_version":"1.0"},"canonical_sha256":"ff36b050dbf93e73b45a88724dbbcc9321c4d1ed8a95611a82886a22b2c82984","source":{"kind":"arxiv","id":"1701.00867","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:743LAUG37E7HHNC2RBZE3O6MSM","target":"record","payload":{"canonical_record":{"source":{"id":"1701.00867","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-01-03T23:29:04Z","cross_cats_sorted":[],"title_canon_sha256":"b10e6638d94725ce41ca9c3c69eeefb68c4c0e63e0036b17d6d6a8e6dc63184b","abstract_canon_sha256":"e62a8d374ef885a8dff29411f2645715adf57c173f8a3ddc02750eb15610a52f"},"schema_version":"1.0"},"canonical_sha256":"ff36b050dbf93e73b45a88724dbbcc9321c4d1ed8a95611a82886a22b2c82984","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:53:22.028651Z","signature_b64":"cr2mvW/HrVuypL5BhWTGGg/Vb9PVBO/PQ3oQHaS4PxS2sfiu0UOadxha2ZTPJ43k81T6vnITYjCYE4PObhIwAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ff36b050dbf93e73b45a88724dbbcc9321c4d1ed8a95611a82886a22b2c82984","last_reissued_at":"2026-05-18T00:53:22.028051Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:53:22.028051Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1701.00867","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":"2026-05-18T00:53:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OanKQX5W43Kem3ukxCpV3UdEg6SfdlB+1eFyoCnA7HV3Xp9DjGYssXKRKQbVM8jO8oaYOJ974bsh8kP/g0bzBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-11T22:59:11.734050Z"},"content_sha256":"de338314d97fcd1f7b19056c5e04621e733789e2219ade1a0a93f78ca6fa39f3","schema_version":"1.0","event_id":"sha256:de338314d97fcd1f7b19056c5e04621e733789e2219ade1a0a93f78ca6fa39f3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:743LAUG37E7HHNC2RBZE3O6MSM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A K-fold Method for Baseline Estimation in Policy Gradient Algorithms","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Abhishek Mishra, Nithyanand Kota, Pieter Abbeel, Sunil Srinivasa, Xi (Peter) Chen","submitted_at":"2017-01-03T23:29:04Z","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."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1701.00867","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":"2026-05-18T00:53:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8vnRf1p24sUKYrRAO9lj2Y5pyZm8h0Yte77emRmPBLNLHJYmQpy8or6js3pT39qjlyLJWck4XeJaPwSAzH3cCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-11T22:59:11.734742Z"},"content_sha256":"49313a6c19ce4b67f28fbca59c14baf33bb8d970612537ce889b7d82fd1dfb5f","schema_version":"1.0","event_id":"sha256:49313a6c19ce4b67f28fbca59c14baf33bb8d970612537ce889b7d82fd1dfb5f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/743LAUG37E7HHNC2RBZE3O6MSM/bundle.json","state_url":"https://pith.science/pith/743LAUG37E7HHNC2RBZE3O6MSM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/743LAUG37E7HHNC2RBZE3O6MSM/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":"2026-06-11T22:59:11Z","links":{"resolver":"https://pith.science/pith/743LAUG37E7HHNC2RBZE3O6MSM","bundle":"https://pith.science/pith/743LAUG37E7HHNC2RBZE3O6MSM/bundle.json","state":"https://pith.science/pith/743LAUG37E7HHNC2RBZE3O6MSM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/743LAUG37E7HHNC2RBZE3O6MSM/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Dq4Kia4V5SXBl3rGat7J8LByj1layS6xkXqJHotZ91L46uU642NqGIY+PVH5t4Pp0A4674eu073kgVT6uMhpCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-11T22:59:11.739186Z","bundle_sha256":"7f43943e366d38776d779d72d59a0b25245e5097e56942072674f366d0683e14"}}