{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:2GX6FCHDLGSO53WFWA2N566IPG","short_pith_number":"pith:2GX6FCHD","schema_version":"1.0","canonical_sha256":"d1afe288e359a4eeeec5b034defbc879b0b14624b6b7368b4872c1d7b0b435a4","source":{"kind":"arxiv","id":"1711.08068","version":1},"attestation_state":"computed","paper":{"title":"Deterministic Policy Optimization by Combining Pathwise and Score Function Estimators for Discrete Action Spaces","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Daniel Levy, Stefano Ermon","submitted_at":"2017-11-21T22:05:18Z","abstract_excerpt":"Policy optimization methods have shown great promise in solving complex reinforcement and imitation learning tasks. While model-free methods are broadly applicable, they often require many samples to optimize complex policies. Model-based methods greatly improve sample-efficiency but at the cost of poor generalization, requiring a carefully handcrafted model of the system dynamics for each task. Recently, hybrid methods have been successful in trading off applicability for improved sample-complexity. However, these have been limited to continuous action spaces. In this work, we present a new h"},"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":"1711.08068","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-11-21T22:05:18Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"89de8ab25d438fe1e3c8bb087684018e239b9899a3f8bcc0697cd95a19a7f272","abstract_canon_sha256":"d61b3fa428ca6a5024d3687a7f89cd52382814ae5d77a2c7e847ba566dded354"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:29:50.768418Z","signature_b64":"dSwldX927RcALNY5b+xF1eO2YyXn7KTTw3NZTOZzS1u4exDEkpgnea6dREleiWBEvBjQOGCl01DKcLH5MnW2DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d1afe288e359a4eeeec5b034defbc879b0b14624b6b7368b4872c1d7b0b435a4","last_reissued_at":"2026-05-18T00:29:50.767706Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:29:50.767706Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deterministic Policy Optimization by Combining Pathwise and Score Function Estimators for Discrete Action Spaces","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Daniel Levy, Stefano Ermon","submitted_at":"2017-11-21T22:05:18Z","abstract_excerpt":"Policy optimization methods have shown great promise in solving complex reinforcement and imitation learning tasks. While model-free methods are broadly applicable, they often require many samples to optimize complex policies. Model-based methods greatly improve sample-efficiency but at the cost of poor generalization, requiring a carefully handcrafted model of the system dynamics for each task. Recently, hybrid methods have been successful in trading off applicability for improved sample-complexity. However, these have been limited to continuous action spaces. In this work, we present a new h"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.08068","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":"1711.08068","created_at":"2026-05-18T00:29:50.767814+00:00"},{"alias_kind":"arxiv_version","alias_value":"1711.08068v1","created_at":"2026-05-18T00:29:50.767814+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.08068","created_at":"2026-05-18T00:29:50.767814+00:00"},{"alias_kind":"pith_short_12","alias_value":"2GX6FCHDLGSO","created_at":"2026-05-18T12:30:55.937587+00:00"},{"alias_kind":"pith_short_16","alias_value":"2GX6FCHDLGSO53WF","created_at":"2026-05-18T12:30:55.937587+00:00"},{"alias_kind":"pith_short_8","alias_value":"2GX6FCHD","created_at":"2026-05-18T12:30:55.937587+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/2GX6FCHDLGSO53WFWA2N566IPG","json":"https://pith.science/pith/2GX6FCHDLGSO53WFWA2N566IPG.json","graph_json":"https://pith.science/api/pith-number/2GX6FCHDLGSO53WFWA2N566IPG/graph.json","events_json":"https://pith.science/api/pith-number/2GX6FCHDLGSO53WFWA2N566IPG/events.json","paper":"https://pith.science/paper/2GX6FCHD"},"agent_actions":{"view_html":"https://pith.science/pith/2GX6FCHDLGSO53WFWA2N566IPG","download_json":"https://pith.science/pith/2GX6FCHDLGSO53WFWA2N566IPG.json","view_paper":"https://pith.science/paper/2GX6FCHD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1711.08068&json=true","fetch_graph":"https://pith.science/api/pith-number/2GX6FCHDLGSO53WFWA2N566IPG/graph.json","fetch_events":"https://pith.science/api/pith-number/2GX6FCHDLGSO53WFWA2N566IPG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2GX6FCHDLGSO53WFWA2N566IPG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2GX6FCHDLGSO53WFWA2N566IPG/action/storage_attestation","attest_author":"https://pith.science/pith/2GX6FCHDLGSO53WFWA2N566IPG/action/author_attestation","sign_citation":"https://pith.science/pith/2GX6FCHDLGSO53WFWA2N566IPG/action/citation_signature","submit_replication":"https://pith.science/pith/2GX6FCHDLGSO53WFWA2N566IPG/action/replication_record"}},"created_at":"2026-05-18T00:29:50.767814+00:00","updated_at":"2026-05-18T00:29:50.767814+00:00"}