{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:V2CEMBS5MUCCRFJWLPFITLSS7U","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":"681129e3f42cca74b4bf1aed179d52b312c81221b0da7c1fc56e6828fea984ac","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-12-14T07:50:21Z","title_canon_sha256":"a4fc6883232ec4b811191217f648bd195ccb524ed9c8b17af2b34430143b3746"},"schema_version":"1.0","source":{"id":"2312.08710","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.08710","created_at":"2026-07-05T07:24:08Z"},{"alias_kind":"arxiv_version","alias_value":"2312.08710v1","created_at":"2026-07-05T07:24:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.08710","created_at":"2026-07-05T07:24:08Z"},{"alias_kind":"pith_short_12","alias_value":"V2CEMBS5MUCC","created_at":"2026-07-05T07:24:08Z"},{"alias_kind":"pith_short_16","alias_value":"V2CEMBS5MUCCRFJW","created_at":"2026-07-05T07:24:08Z"},{"alias_kind":"pith_short_8","alias_value":"V2CEMBS5","created_at":"2026-07-05T07:24:08Z"}],"graph_snapshots":[{"event_id":"sha256:a7d79bfd03383d796405129bbc384df296462783c93c246d3ba300202856903f","target":"graph","created_at":"2026-07-05T07:24:08Z","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/2312.08710/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce a novel policy learning method that integrates analytical gradients from differentiable environments with the Proximal Policy Optimization (PPO) algorithm. To incorporate analytical gradients into the PPO framework, we introduce the concept of an {\\alpha}-policy that stands as a locally superior policy. By adaptively modifying the {\\alpha} value, we can effectively manage the influence of analytical policy gradients during learning. To this end, we suggest metrics for assessing the variance and bias of analytical gradients, reducing dependence on these gradients when high variance","authors_text":"Laura Yu Zheng, Ming C. Lin, Ryan Sullivan, Sanghyun Son, Yi-Ling Qiao","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-12-14T07:50:21Z","title":"Gradient Informed Proximal Policy Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.08710","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":"sha256:8d433573d8f22339850248c50cadcfde9668bb09a700f28820955414198d971a","target":"record","created_at":"2026-07-05T07:24:08Z","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":"681129e3f42cca74b4bf1aed179d52b312c81221b0da7c1fc56e6828fea984ac","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-12-14T07:50:21Z","title_canon_sha256":"a4fc6883232ec4b811191217f648bd195ccb524ed9c8b17af2b34430143b3746"},"schema_version":"1.0","source":{"id":"2312.08710","kind":"arxiv","version":1}},"canonical_sha256":"ae8446065d65042895365bca89ae52fd3e7e910a7a0aed6e44c8f708e4685e68","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ae8446065d65042895365bca89ae52fd3e7e910a7a0aed6e44c8f708e4685e68","first_computed_at":"2026-07-05T07:24:08.390926Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:24:08.390926Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"varcyU8gNzVI7DG3oUGFiGd76w1SBvOBdTggNwVkfrQaMlv88Na9TsiFqFU5guzVqeSjS3HvrXA1Wkpp09LJBw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:24:08.391637Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.08710","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8d433573d8f22339850248c50cadcfde9668bb09a700f28820955414198d971a","sha256:a7d79bfd03383d796405129bbc384df296462783c93c246d3ba300202856903f"],"state_sha256":"a1c5fb10ec8de1d0ba5effa9390c876f9d796d99161441249bfbdbfff42d09be"}