{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:XSEVWGQ53QKDIK2XZZIY74DIKO","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":"ce4ec11f79205a9ae1c1fca5280203862ee87d608e9ee1d091c163a3cac0051f","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-01T15:29:10Z","title_canon_sha256":"93e01bf3c60f08f707c87f17cdfbd1bd016bf4b28952430808dc540a4b8ba385"},"schema_version":"1.0","source":{"id":"2411.00666","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.00666","created_at":"2026-07-05T09:29:46Z"},{"alias_kind":"arxiv_version","alias_value":"2411.00666v1","created_at":"2026-07-05T09:29:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.00666","created_at":"2026-07-05T09:29:46Z"},{"alias_kind":"pith_short_12","alias_value":"XSEVWGQ53QKD","created_at":"2026-07-05T09:29:46Z"},{"alias_kind":"pith_short_16","alias_value":"XSEVWGQ53QKDIK2X","created_at":"2026-07-05T09:29:46Z"},{"alias_kind":"pith_short_8","alias_value":"XSEVWGQ5","created_at":"2026-07-05T09:29:46Z"}],"graph_snapshots":[{"event_id":"sha256:687a2a2284b0b4eef7e332279b2b861840c3344a75d15bdb945dc60347978e7f","target":"graph","created_at":"2026-07-05T09:29:46Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2411.00666/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Proximal policy optimization (PPO) is a widely-used algorithm for on-policy reinforcement learning. This work offers an alternative perspective of PPO, in which it is decomposed into the inner-loop estimation of update vectors, and the outer-loop application of updates using gradient ascent with unity learning rate. Using this insight we propose outer proximal policy optimization (outer-PPO); a framework wherein these update vectors are applied using an arbitrary gradient-based optimizer. The decoupling of update estimation and update application enabled by outer-PPO highlights several implici","authors_text":"Benjamin Ellis, Charlie B. Tan, Edan Toledo, Ferenc Husz\\'ar, Jakob N. Foerster","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-01T15:29:10Z","title":"Beyond the Boundaries of Proximal Policy Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.00666","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:c7030de8518ddf5a665e1583e52573e3cc3aead2611b5707d9d7a0d6df264115","target":"record","created_at":"2026-07-05T09:29:46Z","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":"ce4ec11f79205a9ae1c1fca5280203862ee87d608e9ee1d091c163a3cac0051f","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-01T15:29:10Z","title_canon_sha256":"93e01bf3c60f08f707c87f17cdfbd1bd016bf4b28952430808dc540a4b8ba385"},"schema_version":"1.0","source":{"id":"2411.00666","kind":"arxiv","version":1}},"canonical_sha256":"bc895b1a1ddc14342b57ce518ff06853867eb709c313721acb251031a340064c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bc895b1a1ddc14342b57ce518ff06853867eb709c313721acb251031a340064c","first_computed_at":"2026-07-05T09:29:46.490555Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:29:46.490555Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"A0FEawnPaUHRUxVAdSoh54fFsaTIXApPuI7DR3Egw0/YwojekfM1BdhAoAWm5+5hrArqVsIB+R8D92mZ5al6BQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:29:46.491045Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.00666","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c7030de8518ddf5a665e1583e52573e3cc3aead2611b5707d9d7a0d6df264115","sha256:687a2a2284b0b4eef7e332279b2b861840c3344a75d15bdb945dc60347978e7f"],"state_sha256":"e8b434b1dbb9358a4e98eb73a8211a4247142f09c2a127ead7e7c6d460b0f79a"}