{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:26RNVLS7K2SD6ACQHTTEPHVXGX","short_pith_number":"pith:26RNVLS7","schema_version":"1.0","canonical_sha256":"d7a2daae5f56a43f00503ce6479eb735c4305699372907f8a289cebc39822f38","source":{"kind":"arxiv","id":"2405.17832","version":1},"attestation_state":"computed","paper":{"title":"Mollification Effects of Policy Gradient Methods","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Sicun Gao, Sylvia Herbert, Tao Wang","submitted_at":"2024-05-28T05:05:33Z","abstract_excerpt":"Policy gradient methods have enabled deep reinforcement learning (RL) to approach challenging continuous control problems, even when the underlying systems involve highly nonlinear dynamics that generate complex non-smooth optimization landscapes. We develop a rigorous framework for understanding how policy gradient methods mollify non-smooth optimization landscapes to enable effective policy search, as well as the downside of it: while making the objective function smoother and easier to optimize, the stochastic objective deviates further from the original problem. We demonstrate the equivale"},"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":"2405.17832","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-28T05:05:33Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"f2f853ef986f58ed7fc2653e6a3801c0729bd6ea8c5589fb6241adb92078d8f9","abstract_canon_sha256":"643743067a61b93b93a0221955b2788d578f05d52817aec741cd4822bdb09952"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:24:11.954590Z","signature_b64":"vZNvaAFCH2WMFD70PTlaw6oMxLpmbCKdoI5vSWm1gR57ORveQQkMaE53hg3o4uYn06C6dArWu4S8DuIZ0Py5Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d7a2daae5f56a43f00503ce6479eb735c4305699372907f8a289cebc39822f38","last_reissued_at":"2026-07-05T08:24:11.954170Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:24:11.954170Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Mollification Effects of Policy Gradient Methods","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Sicun Gao, Sylvia Herbert, Tao Wang","submitted_at":"2024-05-28T05:05:33Z","abstract_excerpt":"Policy gradient methods have enabled deep reinforcement learning (RL) to approach challenging continuous control problems, even when the underlying systems involve highly nonlinear dynamics that generate complex non-smooth optimization landscapes. We develop a rigorous framework for understanding how policy gradient methods mollify non-smooth optimization landscapes to enable effective policy search, as well as the downside of it: while making the objective function smoother and easier to optimize, the stochastic objective deviates further from the original problem. We demonstrate the equivale"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.17832","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2405.17832/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":"2405.17832","created_at":"2026-07-05T08:24:11.954232+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.17832v1","created_at":"2026-07-05T08:24:11.954232+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.17832","created_at":"2026-07-05T08:24:11.954232+00:00"},{"alias_kind":"pith_short_12","alias_value":"26RNVLS7K2SD","created_at":"2026-07-05T08:24:11.954232+00:00"},{"alias_kind":"pith_short_16","alias_value":"26RNVLS7K2SD6ACQ","created_at":"2026-07-05T08:24:11.954232+00:00"},{"alias_kind":"pith_short_8","alias_value":"26RNVLS7","created_at":"2026-07-05T08:24:11.954232+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/26RNVLS7K2SD6ACQHTTEPHVXGX","json":"https://pith.science/pith/26RNVLS7K2SD6ACQHTTEPHVXGX.json","graph_json":"https://pith.science/api/pith-number/26RNVLS7K2SD6ACQHTTEPHVXGX/graph.json","events_json":"https://pith.science/api/pith-number/26RNVLS7K2SD6ACQHTTEPHVXGX/events.json","paper":"https://pith.science/paper/26RNVLS7"},"agent_actions":{"view_html":"https://pith.science/pith/26RNVLS7K2SD6ACQHTTEPHVXGX","download_json":"https://pith.science/pith/26RNVLS7K2SD6ACQHTTEPHVXGX.json","view_paper":"https://pith.science/paper/26RNVLS7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.17832&json=true","fetch_graph":"https://pith.science/api/pith-number/26RNVLS7K2SD6ACQHTTEPHVXGX/graph.json","fetch_events":"https://pith.science/api/pith-number/26RNVLS7K2SD6ACQHTTEPHVXGX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/26RNVLS7K2SD6ACQHTTEPHVXGX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/26RNVLS7K2SD6ACQHTTEPHVXGX/action/storage_attestation","attest_author":"https://pith.science/pith/26RNVLS7K2SD6ACQHTTEPHVXGX/action/author_attestation","sign_citation":"https://pith.science/pith/26RNVLS7K2SD6ACQHTTEPHVXGX/action/citation_signature","submit_replication":"https://pith.science/pith/26RNVLS7K2SD6ACQHTTEPHVXGX/action/replication_record"}},"created_at":"2026-07-05T08:24:11.954232+00:00","updated_at":"2026-07-05T08:24:11.954232+00:00"}