{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:SNBYEMAWWB6M4YSNZTTANCDBN6","short_pith_number":"pith:SNBYEMAW","schema_version":"1.0","canonical_sha256":"9343823016b07cce624dcce60688616f91821b984f887115554000c6feb3620c","source":{"kind":"arxiv","id":"1706.06643","version":1},"attestation_state":"computed","paper":{"title":"Policy Gradient Methods for Reinforcement Learning with Function Approximation and Action-Dependent Baselines","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Emma Brunskill, Philip S. Thomas","submitted_at":"2017-06-20T19:47:44Z","abstract_excerpt":"We show how an action-dependent baseline can be used by the policy gradient theorem using function approximation, originally presented with action-independent baselines by (Sutton et al. 2000)."},"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":"1706.06643","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-06-20T19:47:44Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"f01b6b90c58f66ebd509113fefebd4dd74ef820731c7d4d91d50ddb43130c1ff","abstract_canon_sha256":"4a3a941101eb33ddf7dde0703e2e89c79857fac8b6b3bd58f7247e2dfd85b3f5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:41:57.339545Z","signature_b64":"2Irqpa2UQgG1EGva8DmoOSGL5pnJf1PCTOZs3NCbYlZh92KTGI9exhOoD41vWLnLirBY/X/QP6iSH9hStFx+BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9343823016b07cce624dcce60688616f91821b984f887115554000c6feb3620c","last_reissued_at":"2026-05-18T00:41:57.338751Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:41:57.338751Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Policy Gradient Methods for Reinforcement Learning with Function Approximation and Action-Dependent Baselines","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Emma Brunskill, Philip S. Thomas","submitted_at":"2017-06-20T19:47:44Z","abstract_excerpt":"We show how an action-dependent baseline can be used by the policy gradient theorem using function approximation, originally presented with action-independent baselines by (Sutton et al. 2000)."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1706.06643","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":""},"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":"1706.06643","created_at":"2026-05-18T00:41:57.338957+00:00"},{"alias_kind":"arxiv_version","alias_value":"1706.06643v1","created_at":"2026-05-18T00:41:57.338957+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1706.06643","created_at":"2026-05-18T00:41:57.338957+00:00"},{"alias_kind":"pith_short_12","alias_value":"SNBYEMAWWB6M","created_at":"2026-05-18T12:31:43.269735+00:00"},{"alias_kind":"pith_short_16","alias_value":"SNBYEMAWWB6M4YSN","created_at":"2026-05-18T12:31:43.269735+00:00"},{"alias_kind":"pith_short_8","alias_value":"SNBYEMAW","created_at":"2026-05-18T12:31:43.269735+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.17706","citing_title":"OmniVLA-RL: A Vision-Language-Action Model with Spatial Understanding and Online RL","ref_index":47,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SNBYEMAWWB6M4YSNZTTANCDBN6","json":"https://pith.science/pith/SNBYEMAWWB6M4YSNZTTANCDBN6.json","graph_json":"https://pith.science/api/pith-number/SNBYEMAWWB6M4YSNZTTANCDBN6/graph.json","events_json":"https://pith.science/api/pith-number/SNBYEMAWWB6M4YSNZTTANCDBN6/events.json","paper":"https://pith.science/paper/SNBYEMAW"},"agent_actions":{"view_html":"https://pith.science/pith/SNBYEMAWWB6M4YSNZTTANCDBN6","download_json":"https://pith.science/pith/SNBYEMAWWB6M4YSNZTTANCDBN6.json","view_paper":"https://pith.science/paper/SNBYEMAW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1706.06643&json=true","fetch_graph":"https://pith.science/api/pith-number/SNBYEMAWWB6M4YSNZTTANCDBN6/graph.json","fetch_events":"https://pith.science/api/pith-number/SNBYEMAWWB6M4YSNZTTANCDBN6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SNBYEMAWWB6M4YSNZTTANCDBN6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SNBYEMAWWB6M4YSNZTTANCDBN6/action/storage_attestation","attest_author":"https://pith.science/pith/SNBYEMAWWB6M4YSNZTTANCDBN6/action/author_attestation","sign_citation":"https://pith.science/pith/SNBYEMAWWB6M4YSNZTTANCDBN6/action/citation_signature","submit_replication":"https://pith.science/pith/SNBYEMAWWB6M4YSNZTTANCDBN6/action/replication_record"}},"created_at":"2026-05-18T00:41:57.338957+00:00","updated_at":"2026-05-18T00:41:57.338957+00:00"}