{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:5RFNBMNTSW6F6YN2PZX4KDBY4A","short_pith_number":"pith:5RFNBMNT","canonical_record":{"source":{"id":"1801.05566","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-01-17T06:09:09Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"dcec97c91fddc191290b4a66e7e14191336b5bf1e5169df616d62788d5a63f65","abstract_canon_sha256":"73e7ab40803377b1c68d7ad1999bcd5f3ba0e16133e1d11c862570526a6670d7"},"schema_version":"1.0"},"canonical_sha256":"ec4ad0b1b395bc5f61ba7e6fc50c38e033035039cf5b08559770d046f6a15d7d","source":{"kind":"arxiv","id":"1801.05566","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1801.05566","created_at":"2026-05-18T00:25:40Z"},{"alias_kind":"arxiv_version","alias_value":"1801.05566v1","created_at":"2026-05-18T00:25:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1801.05566","created_at":"2026-05-18T00:25:40Z"},{"alias_kind":"pith_short_12","alias_value":"5RFNBMNTSW6F","created_at":"2026-05-18T12:32:08Z"},{"alias_kind":"pith_short_16","alias_value":"5RFNBMNTSW6F6YN2","created_at":"2026-05-18T12:32:08Z"},{"alias_kind":"pith_short_8","alias_value":"5RFNBMNT","created_at":"2026-05-18T12:32:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:5RFNBMNTSW6F6YN2PZX4KDBY4A","target":"record","payload":{"canonical_record":{"source":{"id":"1801.05566","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-01-17T06:09:09Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"dcec97c91fddc191290b4a66e7e14191336b5bf1e5169df616d62788d5a63f65","abstract_canon_sha256":"73e7ab40803377b1c68d7ad1999bcd5f3ba0e16133e1d11c862570526a6670d7"},"schema_version":"1.0"},"canonical_sha256":"ec4ad0b1b395bc5f61ba7e6fc50c38e033035039cf5b08559770d046f6a15d7d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:25:40.879202Z","signature_b64":"Zrdmvfdg6KJJMvsHRFnVzvvKnADN0cy/ta+UX1ujHkrMxxJJyFJFlFZV9M1iGHi0zkNXbPZLf85TkPeN9qZWBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ec4ad0b1b395bc5f61ba7e6fc50c38e033035039cf5b08559770d046f6a15d7d","last_reissued_at":"2026-05-18T00:25:40.878648Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:25:40.878648Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1801.05566","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":"2026-05-18T00:25:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SBcs0Myle6TcUb57KQ/TQFkVv6rlRUB4yP6f9nvcTOxfKlrH16vwVIMyB6VEN6wPZd0/y1vLSokNWz+/bMFsDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T21:28:00.267803Z"},"content_sha256":"c7b2ed0635ba413a3322525c2356b31cf5668730fc95508a714d48e4bdb2ea4e","schema_version":"1.0","event_id":"sha256:c7b2ed0635ba413a3322525c2356b31cf5668730fc95508a714d48e4bdb2ea4e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:5RFNBMNTSW6F6YN2PZX4KDBY4A","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"An Empirical Analysis of Proximal Policy Optimization with Kronecker-factored Natural Gradients","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.AI","authors_text":"Jiaming Song, Yuhuai Wu","submitted_at":"2018-01-17T06:09:09Z","abstract_excerpt":"In this technical report, we consider an approach that combines the PPO objective and K-FAC natural gradient optimization, for which we call PPOKFAC. We perform a range of empirical analysis on various aspects of the algorithm, such as sample complexity, training speed, and sensitivity to batch size and training epochs. We observe that PPOKFAC is able to outperform PPO in terms of sample complexity and speed in a range of MuJoCo environments, while being scalable in terms of batch size. In spite of this, it seems that adding more epochs is not necessarily helpful for sample efficiency, and PPO"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1801.05566","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":"2026-05-18T00:25:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gT4yl9PpL1nkxH5lsPGksr+LBQtC04hjafyHQzHOiAp7F9OXaQGhDPzrWmrtXiIskkf89kYv8j0x0HsbeFa2AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T21:28:00.268503Z"},"content_sha256":"f6d14b6d9892b5157dc983fd458201333913dafeccfab078956cde1bbabfbb3b","schema_version":"1.0","event_id":"sha256:f6d14b6d9892b5157dc983fd458201333913dafeccfab078956cde1bbabfbb3b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5RFNBMNTSW6F6YN2PZX4KDBY4A/bundle.json","state_url":"https://pith.science/pith/5RFNBMNTSW6F6YN2PZX4KDBY4A/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5RFNBMNTSW6F6YN2PZX4KDBY4A/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":"2026-05-25T21:28:00Z","links":{"resolver":"https://pith.science/pith/5RFNBMNTSW6F6YN2PZX4KDBY4A","bundle":"https://pith.science/pith/5RFNBMNTSW6F6YN2PZX4KDBY4A/bundle.json","state":"https://pith.science/pith/5RFNBMNTSW6F6YN2PZX4KDBY4A/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5RFNBMNTSW6F6YN2PZX4KDBY4A/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:5RFNBMNTSW6F6YN2PZX4KDBY4A","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":"73e7ab40803377b1c68d7ad1999bcd5f3ba0e16133e1d11c862570526a6670d7","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-01-17T06:09:09Z","title_canon_sha256":"dcec97c91fddc191290b4a66e7e14191336b5bf1e5169df616d62788d5a63f65"},"schema_version":"1.0","source":{"id":"1801.05566","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1801.05566","created_at":"2026-05-18T00:25:40Z"},{"alias_kind":"arxiv_version","alias_value":"1801.05566v1","created_at":"2026-05-18T00:25:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1801.05566","created_at":"2026-05-18T00:25:40Z"},{"alias_kind":"pith_short_12","alias_value":"5RFNBMNTSW6F","created_at":"2026-05-18T12:32:08Z"},{"alias_kind":"pith_short_16","alias_value":"5RFNBMNTSW6F6YN2","created_at":"2026-05-18T12:32:08Z"},{"alias_kind":"pith_short_8","alias_value":"5RFNBMNT","created_at":"2026-05-18T12:32:08Z"}],"graph_snapshots":[{"event_id":"sha256:f6d14b6d9892b5157dc983fd458201333913dafeccfab078956cde1bbabfbb3b","target":"graph","created_at":"2026-05-18T00:25:40Z","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 this technical report, we consider an approach that combines the PPO objective and K-FAC natural gradient optimization, for which we call PPOKFAC. We perform a range of empirical analysis on various aspects of the algorithm, such as sample complexity, training speed, and sensitivity to batch size and training epochs. We observe that PPOKFAC is able to outperform PPO in terms of sample complexity and speed in a range of MuJoCo environments, while being scalable in terms of batch size. In spite of this, it seems that adding more epochs is not necessarily helpful for sample efficiency, and PPO","authors_text":"Jiaming Song, Yuhuai Wu","cross_cats":["cs.LG","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-01-17T06:09:09Z","title":"An Empirical Analysis of Proximal Policy Optimization with Kronecker-factored Natural Gradients"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1801.05566","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:c7b2ed0635ba413a3322525c2356b31cf5668730fc95508a714d48e4bdb2ea4e","target":"record","created_at":"2026-05-18T00:25:40Z","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":"73e7ab40803377b1c68d7ad1999bcd5f3ba0e16133e1d11c862570526a6670d7","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-01-17T06:09:09Z","title_canon_sha256":"dcec97c91fddc191290b4a66e7e14191336b5bf1e5169df616d62788d5a63f65"},"schema_version":"1.0","source":{"id":"1801.05566","kind":"arxiv","version":1}},"canonical_sha256":"ec4ad0b1b395bc5f61ba7e6fc50c38e033035039cf5b08559770d046f6a15d7d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ec4ad0b1b395bc5f61ba7e6fc50c38e033035039cf5b08559770d046f6a15d7d","first_computed_at":"2026-05-18T00:25:40.878648Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:25:40.878648Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Zrdmvfdg6KJJMvsHRFnVzvvKnADN0cy/ta+UX1ujHkrMxxJJyFJFlFZV9M1iGHi0zkNXbPZLf85TkPeN9qZWBg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:25:40.879202Z","signed_message":"canonical_sha256_bytes"},"source_id":"1801.05566","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c7b2ed0635ba413a3322525c2356b31cf5668730fc95508a714d48e4bdb2ea4e","sha256:f6d14b6d9892b5157dc983fd458201333913dafeccfab078956cde1bbabfbb3b"],"state_sha256":"0e5e56704fbd0c40945ecaa53f1ad8f8ec371b1b9a6643157c09cbcf03d09c6b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fnh53EeUO3aAnf5TP4VdkOWQzQ0SbBpdKYFjVqJpLTWCxBsGwlC6Nh4vSMgrxaRgHyW9Tm7XPn6fvVsm/S3mDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T21:28:00.272097Z","bundle_sha256":"046b5d335a868f50d1dfe2b7098f6748bde71b8ae5958a9cc39abadcb8730974"}}