{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:UNZV4PFVBEBHZNRVPTUTREDNW3","short_pith_number":"pith:UNZV4PFV","schema_version":"1.0","canonical_sha256":"a3735e3cb509027cb6357ce938906db6f8da41c86a4a442a2487d0a69b28c2d5","source":{"kind":"arxiv","id":"1901.10500","version":4},"attestation_state":"computed","paper":{"title":"Discretizing Continuous Action Space for On-Policy Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Shipra Agrawal, Yunhao Tang","submitted_at":"2019-01-29T19:19:50Z","abstract_excerpt":"In this work, we show that discretizing action space for continuous control is a simple yet powerful technique for on-policy optimization. The explosion in the number of discrete actions can be efficiently addressed by a policy with factorized distribution across action dimensions. We show that the discrete policy achieves significant performance gains with state-of-the-art on-policy optimization algorithms (PPO, TRPO, ACKTR) especially on high-dimensional tasks with complex dynamics. Additionally, we show that an ordinal parameterization of the discrete distribution can introduce the inductiv"},"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":"1901.10500","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-29T19:19:50Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"30a1540ea84d69c34db0ca258eaf16f2306fcbaf06600b26a6fbe15e3c7a50b1","abstract_canon_sha256":"861a7699a6b6161a986d27280803c9ed548ba25f145a166a1df3981887e026e2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:49:22.996910Z","signature_b64":"jbDV+Ox3btTKo34xBVWy+FaqqE6gjcQCi/o2jv+ZIAKDdXYY+Oi0RXc1t7NJTWuFayjxN/ugkkzNAV1r9YHxCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a3735e3cb509027cb6357ce938906db6f8da41c86a4a442a2487d0a69b28c2d5","last_reissued_at":"2026-07-05T00:49:22.996494Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:49:22.996494Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Discretizing Continuous Action Space for On-Policy Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Shipra Agrawal, Yunhao Tang","submitted_at":"2019-01-29T19:19:50Z","abstract_excerpt":"In this work, we show that discretizing action space for continuous control is a simple yet powerful technique for on-policy optimization. The explosion in the number of discrete actions can be efficiently addressed by a policy with factorized distribution across action dimensions. We show that the discrete policy achieves significant performance gains with state-of-the-art on-policy optimization algorithms (PPO, TRPO, ACKTR) especially on high-dimensional tasks with complex dynamics. Additionally, we show that an ordinal parameterization of the discrete distribution can introduce the inductiv"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.10500","kind":"arxiv","version":4},"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/1901.10500/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":"1901.10500","created_at":"2026-07-05T00:49:22.996550+00:00"},{"alias_kind":"arxiv_version","alias_value":"1901.10500v4","created_at":"2026-07-05T00:49:22.996550+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.10500","created_at":"2026-07-05T00:49:22.996550+00:00"},{"alias_kind":"pith_short_12","alias_value":"UNZV4PFVBEBH","created_at":"2026-07-05T00:49:22.996550+00:00"},{"alias_kind":"pith_short_16","alias_value":"UNZV4PFVBEBHZNRV","created_at":"2026-07-05T00:49:22.996550+00:00"},{"alias_kind":"pith_short_8","alias_value":"UNZV4PFV","created_at":"2026-07-05T00:49:22.996550+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/UNZV4PFVBEBHZNRVPTUTREDNW3","json":"https://pith.science/pith/UNZV4PFVBEBHZNRVPTUTREDNW3.json","graph_json":"https://pith.science/api/pith-number/UNZV4PFVBEBHZNRVPTUTREDNW3/graph.json","events_json":"https://pith.science/api/pith-number/UNZV4PFVBEBHZNRVPTUTREDNW3/events.json","paper":"https://pith.science/paper/UNZV4PFV"},"agent_actions":{"view_html":"https://pith.science/pith/UNZV4PFVBEBHZNRVPTUTREDNW3","download_json":"https://pith.science/pith/UNZV4PFVBEBHZNRVPTUTREDNW3.json","view_paper":"https://pith.science/paper/UNZV4PFV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1901.10500&json=true","fetch_graph":"https://pith.science/api/pith-number/UNZV4PFVBEBHZNRVPTUTREDNW3/graph.json","fetch_events":"https://pith.science/api/pith-number/UNZV4PFVBEBHZNRVPTUTREDNW3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UNZV4PFVBEBHZNRVPTUTREDNW3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UNZV4PFVBEBHZNRVPTUTREDNW3/action/storage_attestation","attest_author":"https://pith.science/pith/UNZV4PFVBEBHZNRVPTUTREDNW3/action/author_attestation","sign_citation":"https://pith.science/pith/UNZV4PFVBEBHZNRVPTUTREDNW3/action/citation_signature","submit_replication":"https://pith.science/pith/UNZV4PFVBEBHZNRVPTUTREDNW3/action/replication_record"}},"created_at":"2026-07-05T00:49:22.996550+00:00","updated_at":"2026-07-05T00:49:22.996550+00:00"}