{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:DMQWEGIZUTRSYQ6QJWFZQTIFWA","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":"afdde6122dc144c95a3902a69834d857451c2b6ad7be015dc2097990fa7c2f8a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-05-18T17:58:54Z","title_canon_sha256":"a727db3280e4077fefb9482a1ffca224a18ec72959bd5fbfc9aa9809b5873d2d"},"schema_version":"1.0","source":{"id":"2205.09123","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.09123","created_at":"2026-07-05T04:24:41Z"},{"alias_kind":"arxiv_version","alias_value":"2205.09123v1","created_at":"2026-07-05T04:24:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.09123","created_at":"2026-07-05T04:24:41Z"},{"alias_kind":"pith_short_12","alias_value":"DMQWEGIZUTRS","created_at":"2026-07-05T04:24:41Z"},{"alias_kind":"pith_short_16","alias_value":"DMQWEGIZUTRSYQ6Q","created_at":"2026-07-05T04:24:41Z"},{"alias_kind":"pith_short_8","alias_value":"DMQWEGIZ","created_at":"2026-07-05T04:24:41Z"}],"graph_snapshots":[{"event_id":"sha256:3304262046194637d59d7ca8c4f9900d06c642a32b20314a44fa14476ebfe9dd","target":"graph","created_at":"2026-07-05T04:24:41Z","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/2205.09123/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Advantage Actor-critic (A2C) and Proximal Policy Optimization (PPO) are popular deep reinforcement learning algorithms used for game AI in recent years. A common understanding is that A2C and PPO are separate algorithms because PPO's clipped objective appears significantly different than A2C's objective. In this paper, however, we show A2C is a special case of PPO. We present theoretical justifications and pseudocode analysis to demonstrate why. To validate our claim, we conduct an empirical experiment using \\texttt{Stable-baselines3}, showing A2C and PPO produce the \\textit{exact} same models","authors_text":"Anssi Kanervisto, Antonin Raffin, Rousslan Fernand Julien Dossa, Santiago Onta\\~n\\'on, Shengyi Huang, Weixun Wang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-05-18T17:58:54Z","title":"A2C is a special case of PPO"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.09123","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":"sha256:0174bb0b7ee630ac209acd794d954b1a623783694e43f3b51759f5ebdfa740d8","target":"record","created_at":"2026-07-05T04:24:41Z","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":"afdde6122dc144c95a3902a69834d857451c2b6ad7be015dc2097990fa7c2f8a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-05-18T17:58:54Z","title_canon_sha256":"a727db3280e4077fefb9482a1ffca224a18ec72959bd5fbfc9aa9809b5873d2d"},"schema_version":"1.0","source":{"id":"2205.09123","kind":"arxiv","version":1}},"canonical_sha256":"1b21621919a4e32c43d04d8b984d05b01b5a0bc111204325b15e1e033a01741a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1b21621919a4e32c43d04d8b984d05b01b5a0bc111204325b15e1e033a01741a","first_computed_at":"2026-07-05T04:24:41.370944Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:24:41.370944Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"And5S1d+qH/2bOoX62YqRWFSira7D0noHC05N9cdsKpE8O19KlCk3Y7QsH+NLLIxO2usy5eyOhl8+BbwwNy0AA==","signature_status":"signed_v1","signed_at":"2026-07-05T04:24:41.371440Z","signed_message":"canonical_sha256_bytes"},"source_id":"2205.09123","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0174bb0b7ee630ac209acd794d954b1a623783694e43f3b51759f5ebdfa740d8","sha256:3304262046194637d59d7ca8c4f9900d06c642a32b20314a44fa14476ebfe9dd"],"state_sha256":"80bf1b3635392005a036028e3c0a71ac1f800207c1eab2f7224296da0f86d964"}