{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ZBJB7JCCB5WGDNX4Q7FTUJOEXX","short_pith_number":"pith:ZBJB7JCC","schema_version":"1.0","canonical_sha256":"c8521fa4420f6c61b6fc87cb3a25c4bde99afa5bddbc3e19f5cd213e9b3e76ac","source":{"kind":"arxiv","id":"2501.12703","version":2},"attestation_state":"computed","paper":{"title":"HEPPO-GAE: Hardware-Efficient Proximal Policy Optimization with Generalized Advantage Estimation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.AR","authors_text":"Ameer M. S. Abdelhadi, Hazem Taha","submitted_at":"2025-01-22T08:18:56Z","abstract_excerpt":"This paper introduces HEPPO-GAE, an FPGA-based accelerator designed to optimize the Generalized Advantage Estimation (GAE) stage in Proximal Policy Optimization (PPO). Unlike previous approaches that focused on trajectory collection and actor-critic updates, HEPPO-GAE addresses GAE's computational demands with a parallel, pipelined architecture implemented on a single System-on-Chip (SoC). This design allows for the adaptation of various hardware accelerators tailored for different PPO phases. A key innovation is our strategic standardization technique, which combines dynamic reward standardiz"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2501.12703","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AR","submitted_at":"2025-01-22T08:18:56Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"e8370227119b9ba362711481350f322e04b599eeaaa48f7f60d948e01f46ea49","abstract_canon_sha256":"29ef9403eb0321b8b36c47f0a7132fe6ba64db037b18704200ee2f000f43312c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:39:47.479889Z","signature_b64":"JE4CNCyeshoy1JD4dOBTHVTagaL9WnIat8aJmu6KCpsXu46GlZrfReAMRVskNY0RgUO/LWG1uncyXoLkTN1mBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c8521fa4420f6c61b6fc87cb3a25c4bde99afa5bddbc3e19f5cd213e9b3e76ac","last_reissued_at":"2026-07-05T11:39:47.479401Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:39:47.479401Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HEPPO-GAE: Hardware-Efficient Proximal Policy Optimization with Generalized Advantage Estimation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.AR","authors_text":"Ameer M. S. Abdelhadi, Hazem Taha","submitted_at":"2025-01-22T08:18:56Z","abstract_excerpt":"This paper introduces HEPPO-GAE, an FPGA-based accelerator designed to optimize the Generalized Advantage Estimation (GAE) stage in Proximal Policy Optimization (PPO). Unlike previous approaches that focused on trajectory collection and actor-critic updates, HEPPO-GAE addresses GAE's computational demands with a parallel, pipelined architecture implemented on a single System-on-Chip (SoC). This design allows for the adaptation of various hardware accelerators tailored for different PPO phases. A key innovation is our strategic standardization technique, which combines dynamic reward standardiz"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.12703","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2501.12703/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2501.12703","created_at":"2026-07-05T11:39:47.479456+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.12703v2","created_at":"2026-07-05T11:39:47.479456+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.12703","created_at":"2026-07-05T11:39:47.479456+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZBJB7JCCB5WG","created_at":"2026-07-05T11:39:47.479456+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZBJB7JCCB5WGDNX4","created_at":"2026-07-05T11:39:47.479456+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZBJB7JCC","created_at":"2026-07-05T11:39:47.479456+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZBJB7JCCB5WGDNX4Q7FTUJOEXX","json":"https://pith.science/pith/ZBJB7JCCB5WGDNX4Q7FTUJOEXX.json","graph_json":"https://pith.science/api/pith-number/ZBJB7JCCB5WGDNX4Q7FTUJOEXX/graph.json","events_json":"https://pith.science/api/pith-number/ZBJB7JCCB5WGDNX4Q7FTUJOEXX/events.json","paper":"https://pith.science/paper/ZBJB7JCC"},"agent_actions":{"view_html":"https://pith.science/pith/ZBJB7JCCB5WGDNX4Q7FTUJOEXX","download_json":"https://pith.science/pith/ZBJB7JCCB5WGDNX4Q7FTUJOEXX.json","view_paper":"https://pith.science/paper/ZBJB7JCC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.12703&json=true","fetch_graph":"https://pith.science/api/pith-number/ZBJB7JCCB5WGDNX4Q7FTUJOEXX/graph.json","fetch_events":"https://pith.science/api/pith-number/ZBJB7JCCB5WGDNX4Q7FTUJOEXX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZBJB7JCCB5WGDNX4Q7FTUJOEXX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZBJB7JCCB5WGDNX4Q7FTUJOEXX/action/storage_attestation","attest_author":"https://pith.science/pith/ZBJB7JCCB5WGDNX4Q7FTUJOEXX/action/author_attestation","sign_citation":"https://pith.science/pith/ZBJB7JCCB5WGDNX4Q7FTUJOEXX/action/citation_signature","submit_replication":"https://pith.science/pith/ZBJB7JCCB5WGDNX4Q7FTUJOEXX/action/replication_record"}},"created_at":"2026-07-05T11:39:47.479456+00:00","updated_at":"2026-07-05T11:39:47.479456+00:00"}