{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:3JEK5ETN7WY7KRIQ6D4F2ZN6XI","short_pith_number":"pith:3JEK5ETN","canonical_record":{"source":{"id":"1803.07246","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-03-20T03:52:04Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"326d3c5c482ca9ef061e80410b4df964884ebb69a4e16e2982ea0c6bd57d98f0","abstract_canon_sha256":"65f3ebdbf0e6ef08cbac4b5527ff40f45b194bff4aba640d2e46823c0ed287bb"},"schema_version":"1.0"},"canonical_sha256":"da48ae926dfdb1f54510f0f85d65beba2793d6c2cc23cc59b9a8ee2a01fbd248","source":{"kind":"arxiv","id":"1803.07246","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1803.07246","created_at":"2026-05-18T00:20:33Z"},{"alias_kind":"arxiv_version","alias_value":"1803.07246v1","created_at":"2026-05-18T00:20:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.07246","created_at":"2026-05-18T00:20:33Z"},{"alias_kind":"pith_short_12","alias_value":"3JEK5ETN7WY7","created_at":"2026-05-18T12:32:02Z"},{"alias_kind":"pith_short_16","alias_value":"3JEK5ETN7WY7KRIQ","created_at":"2026-05-18T12:32:02Z"},{"alias_kind":"pith_short_8","alias_value":"3JEK5ETN","created_at":"2026-05-18T12:32:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:3JEK5ETN7WY7KRIQ6D4F2ZN6XI","target":"record","payload":{"canonical_record":{"source":{"id":"1803.07246","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-03-20T03:52:04Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"326d3c5c482ca9ef061e80410b4df964884ebb69a4e16e2982ea0c6bd57d98f0","abstract_canon_sha256":"65f3ebdbf0e6ef08cbac4b5527ff40f45b194bff4aba640d2e46823c0ed287bb"},"schema_version":"1.0"},"canonical_sha256":"da48ae926dfdb1f54510f0f85d65beba2793d6c2cc23cc59b9a8ee2a01fbd248","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:20:33.854597Z","signature_b64":"FRU+zRXFId4OqM9YNy06FmGbMAnCpAyiZMvejzn0eAh8nYmeVlLkGQHLw4jJJbaMAuhY3JitUnjFxqspJiKYCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"da48ae926dfdb1f54510f0f85d65beba2793d6c2cc23cc59b9a8ee2a01fbd248","last_reissued_at":"2026-05-18T00:20:33.854128Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:20:33.854128Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1803.07246","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":"2026-05-18T00:20:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7cx7SnRYlcmrZHQZ/7euHEgx89T4/tWafQFgc5e2DP3GXlFXlgBWl2da/1LYcnFbl8D6AlLrX7Z+MCcqsrcDBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T14:02:26.535051Z"},"content_sha256":"55a3103e236f56d1440382727729b9ec608e80aeae819e3bbf61e13657ff4310","schema_version":"1.0","event_id":"sha256:55a3103e236f56d1440382727729b9ec608e80aeae819e3bbf61e13657ff4310"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:3JEK5ETN7WY7KRIQ6D4F2ZN6XI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Variance Reduction for Policy Gradient with Action-Dependent Factorized Baselines","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alexandre M Bayen, Aravind Rajeswaran, Cathy Wu, Igor Mordatch, Pieter Abbeel, Sham Kakade, Vikash Kumar, Yan Duan","submitted_at":"2018-03-20T03:52:04Z","abstract_excerpt":"Policy gradient methods have enjoyed great success in deep reinforcement learning but suffer from high variance of gradient estimates. The high variance problem is particularly exasperated in problems with long horizons or high-dimensional action spaces. To mitigate this issue, we derive a bias-free action-dependent baseline for variance reduction which fully exploits the structural form of the stochastic policy itself and does not make any additional assumptions about the MDP. We demonstrate and quantify the benefit of the action-dependent baseline through both theoretical analysis as well as"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.07246","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":"2026-05-18T00:20:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LvQSedqBcRdgHvXrj39Kv6YSQXFpqC263vDy6DNSt6esYVdGtnMq0pUHxzHr+KqvhKc6Lpj66KQyC4OaeKMTDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T14:02:26.535444Z"},"content_sha256":"8ca30c05b80cff0621902b52a3c27378543993a07f19f0c28b44e3c01d889a93","schema_version":"1.0","event_id":"sha256:8ca30c05b80cff0621902b52a3c27378543993a07f19f0c28b44e3c01d889a93"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3JEK5ETN7WY7KRIQ6D4F2ZN6XI/bundle.json","state_url":"https://pith.science/pith/3JEK5ETN7WY7KRIQ6D4F2ZN6XI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3JEK5ETN7WY7KRIQ6D4F2ZN6XI/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":"2026-06-05T14:02:26Z","links":{"resolver":"https://pith.science/pith/3JEK5ETN7WY7KRIQ6D4F2ZN6XI","bundle":"https://pith.science/pith/3JEK5ETN7WY7KRIQ6D4F2ZN6XI/bundle.json","state":"https://pith.science/pith/3JEK5ETN7WY7KRIQ6D4F2ZN6XI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3JEK5ETN7WY7KRIQ6D4F2ZN6XI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:3JEK5ETN7WY7KRIQ6D4F2ZN6XI","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":"65f3ebdbf0e6ef08cbac4b5527ff40f45b194bff4aba640d2e46823c0ed287bb","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-03-20T03:52:04Z","title_canon_sha256":"326d3c5c482ca9ef061e80410b4df964884ebb69a4e16e2982ea0c6bd57d98f0"},"schema_version":"1.0","source":{"id":"1803.07246","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1803.07246","created_at":"2026-05-18T00:20:33Z"},{"alias_kind":"arxiv_version","alias_value":"1803.07246v1","created_at":"2026-05-18T00:20:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.07246","created_at":"2026-05-18T00:20:33Z"},{"alias_kind":"pith_short_12","alias_value":"3JEK5ETN7WY7","created_at":"2026-05-18T12:32:02Z"},{"alias_kind":"pith_short_16","alias_value":"3JEK5ETN7WY7KRIQ","created_at":"2026-05-18T12:32:02Z"},{"alias_kind":"pith_short_8","alias_value":"3JEK5ETN","created_at":"2026-05-18T12:32:02Z"}],"graph_snapshots":[{"event_id":"sha256:8ca30c05b80cff0621902b52a3c27378543993a07f19f0c28b44e3c01d889a93","target":"graph","created_at":"2026-05-18T00:20:33Z","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":"Policy gradient methods have enjoyed great success in deep reinforcement learning but suffer from high variance of gradient estimates. The high variance problem is particularly exasperated in problems with long horizons or high-dimensional action spaces. To mitigate this issue, we derive a bias-free action-dependent baseline for variance reduction which fully exploits the structural form of the stochastic policy itself and does not make any additional assumptions about the MDP. We demonstrate and quantify the benefit of the action-dependent baseline through both theoretical analysis as well as","authors_text":"Alexandre M Bayen, Aravind Rajeswaran, Cathy Wu, Igor Mordatch, Pieter Abbeel, Sham Kakade, Vikash Kumar, Yan Duan","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-03-20T03:52:04Z","title":"Variance Reduction for Policy Gradient with Action-Dependent Factorized Baselines"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.07246","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":"sha256:55a3103e236f56d1440382727729b9ec608e80aeae819e3bbf61e13657ff4310","target":"record","created_at":"2026-05-18T00:20:33Z","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":"65f3ebdbf0e6ef08cbac4b5527ff40f45b194bff4aba640d2e46823c0ed287bb","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-03-20T03:52:04Z","title_canon_sha256":"326d3c5c482ca9ef061e80410b4df964884ebb69a4e16e2982ea0c6bd57d98f0"},"schema_version":"1.0","source":{"id":"1803.07246","kind":"arxiv","version":1}},"canonical_sha256":"da48ae926dfdb1f54510f0f85d65beba2793d6c2cc23cc59b9a8ee2a01fbd248","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"da48ae926dfdb1f54510f0f85d65beba2793d6c2cc23cc59b9a8ee2a01fbd248","first_computed_at":"2026-05-18T00:20:33.854128Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:20:33.854128Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FRU+zRXFId4OqM9YNy06FmGbMAnCpAyiZMvejzn0eAh8nYmeVlLkGQHLw4jJJbaMAuhY3JitUnjFxqspJiKYCQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:20:33.854597Z","signed_message":"canonical_sha256_bytes"},"source_id":"1803.07246","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:55a3103e236f56d1440382727729b9ec608e80aeae819e3bbf61e13657ff4310","sha256:8ca30c05b80cff0621902b52a3c27378543993a07f19f0c28b44e3c01d889a93"],"state_sha256":"7f5a0dda3a368b73f8e268d1099a5bf6f27f192dd26e20ba66d3cb37baf4ccf6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MHbnKRkBBEVdd5YfEjLac27/jF73lbbCIjpy8cIUKR1Wv1kxXybO4KDl26TDv/Jm08aKTA6V4u/UOUDCHAIjAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-05T14:02:26.537398Z","bundle_sha256":"dcd57386240cfe54a65efa0251a93c9a4e2818857dd7d49b426aba0c51228cef"}}