{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:HWMCJR4P4MMUKCOC3FGRGPTJLY","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":"515f17763edab563545009f7f42ca159276ae4126ad932244f376b29438cd760","cross_cats_sorted":["cs.NE","cs.RO","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-06T18:54:21Z","title_canon_sha256":"5d7ae50a174e750b5777e4903fddfe8f795b812c5354238e18b15fa0865ef164"},"schema_version":"1.0","source":{"id":"1811.02553","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1811.02553","created_at":"2026-07-05T01:05:22Z"},{"alias_kind":"arxiv_version","alias_value":"1811.02553v4","created_at":"2026-07-05T01:05:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.02553","created_at":"2026-07-05T01:05:22Z"},{"alias_kind":"pith_short_12","alias_value":"HWMCJR4P4MMU","created_at":"2026-07-05T01:05:22Z"},{"alias_kind":"pith_short_16","alias_value":"HWMCJR4P4MMUKCOC","created_at":"2026-07-05T01:05:22Z"},{"alias_kind":"pith_short_8","alias_value":"HWMCJR4P","created_at":"2026-07-05T01:05:22Z"}],"graph_snapshots":[{"event_id":"sha256:8a9cdd3a3a918b4f98251c62c271da5256805ef4faa04802d2ef00bb7edd7314","target":"graph","created_at":"2026-07-05T01:05:22Z","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/1811.02553/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study how the behavior of deep policy gradient algorithms reflects the conceptual framework motivating their development. To this end, we propose a fine-grained analysis of state-of-the-art methods based on key elements of this framework: gradient estimation, value prediction, and optimization landscapes. Our results show that the behavior of deep policy gradient algorithms often deviates from what their motivating framework would predict: the surrogate objective does not match the true reward landscape, learned value estimators fail to fit the true value function, and gradient estimates po","authors_text":"Aleksander Madry, Andrew Ilyas, Dimitris Tsipras, Firdaus Janoos, Larry Rudolph, Logan Engstrom, Shibani Santurkar","cross_cats":["cs.NE","cs.RO","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-06T18:54:21Z","title":"A Closer Look at Deep Policy Gradients"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.02553","kind":"arxiv","version":4},"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":"sha256:1ca3fa63e7a2193da9e61c29408db6a3927d31206205f4025ae9797fd22db5f7","target":"record","created_at":"2026-07-05T01:05:22Z","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":"515f17763edab563545009f7f42ca159276ae4126ad932244f376b29438cd760","cross_cats_sorted":["cs.NE","cs.RO","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-06T18:54:21Z","title_canon_sha256":"5d7ae50a174e750b5777e4903fddfe8f795b812c5354238e18b15fa0865ef164"},"schema_version":"1.0","source":{"id":"1811.02553","kind":"arxiv","version":4}},"canonical_sha256":"3d9824c78fe3194509c2d94d133e695e10859a73782a7c6e565fd0e380604ba6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3d9824c78fe3194509c2d94d133e695e10859a73782a7c6e565fd0e380604ba6","first_computed_at":"2026-07-05T01:05:22.859768Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:05:22.859768Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"sfgTyayLhY7wZhEGh4PkPKVuoqV8dPs4W2gaAes1V3w+RAZB5h/vE7HX5r7XD58+JSxGNaVJwZmRqPgBvpPfCg==","signature_status":"signed_v1","signed_at":"2026-07-05T01:05:22.860250Z","signed_message":"canonical_sha256_bytes"},"source_id":"1811.02553","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1ca3fa63e7a2193da9e61c29408db6a3927d31206205f4025ae9797fd22db5f7","sha256:8a9cdd3a3a918b4f98251c62c271da5256805ef4faa04802d2ef00bb7edd7314"],"state_sha256":"9333243e46683ab791eb87cb4eaf9b2d61d989ea4c6391670df881aafb77755b"}