{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:RBZIEWN5CEBN5SNVGD7ODP2FKM","short_pith_number":"pith:RBZIEWN5","schema_version":"1.0","canonical_sha256":"88728259bd1102dec9b530fee1bf45532f220b30cc2b167cf8562acc257bb675","source":{"kind":"arxiv","id":"2104.04004","version":4},"attestation_state":"computed","paper":{"title":"ACERAC: Efficient reinforcement learning in fine time discretization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jakub {\\L}yskawa, Pawe{\\l} Wawrzy\\'nski","submitted_at":"2021-04-08T18:40:20Z","abstract_excerpt":"One of the main goals of reinforcement learning (RL) is to provide a~way for physical machines to learn optimal behavior instead of being programmed. However, effective control of the machines usually requires fine time discretization. The most common RL methods apply independent random elements to each action, which is not suitable in that setting. It is not feasible because it causes the controlled system to jerk, and does not ensure sufficient exploration since a~single action is not long enough to create a~significant experience that could be translated into policy improvement. In our view"},"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":"2104.04004","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-04-08T18:40:20Z","cross_cats_sorted":[],"title_canon_sha256":"0e5bf4cb5f044236df2eceaa129ec700f5cb9cca621196de1b051d7e0c673736","abstract_canon_sha256":"47339d95d83d29a7eb88e3be55e79d086a558dd0b754ac6fc0f71699722f6738"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:38:42.377888Z","signature_b64":"KPUn02H3nSVuhJhEdFnTWJXG16zURf7G7jROp9VjNJGZCdUwI+hQkSXZW9Xk6O7Ctg3pHx6g3ixqnt35q5R+Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"88728259bd1102dec9b530fee1bf45532f220b30cc2b167cf8562acc257bb675","last_reissued_at":"2026-07-05T04:38:42.377436Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:38:42.377436Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ACERAC: Efficient reinforcement learning in fine time discretization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jakub {\\L}yskawa, Pawe{\\l} Wawrzy\\'nski","submitted_at":"2021-04-08T18:40:20Z","abstract_excerpt":"One of the main goals of reinforcement learning (RL) is to provide a~way for physical machines to learn optimal behavior instead of being programmed. However, effective control of the machines usually requires fine time discretization. The most common RL methods apply independent random elements to each action, which is not suitable in that setting. It is not feasible because it causes the controlled system to jerk, and does not ensure sufficient exploration since a~single action is not long enough to create a~significant experience that could be translated into policy improvement. In our view"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.04004","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/2104.04004/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":"2104.04004","created_at":"2026-07-05T04:38:42.377492+00:00"},{"alias_kind":"arxiv_version","alias_value":"2104.04004v4","created_at":"2026-07-05T04:38:42.377492+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.04004","created_at":"2026-07-05T04:38:42.377492+00:00"},{"alias_kind":"pith_short_12","alias_value":"RBZIEWN5CEBN","created_at":"2026-07-05T04:38:42.377492+00:00"},{"alias_kind":"pith_short_16","alias_value":"RBZIEWN5CEBN5SNV","created_at":"2026-07-05T04:38:42.377492+00:00"},{"alias_kind":"pith_short_8","alias_value":"RBZIEWN5","created_at":"2026-07-05T04:38:42.377492+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/RBZIEWN5CEBN5SNVGD7ODP2FKM","json":"https://pith.science/pith/RBZIEWN5CEBN5SNVGD7ODP2FKM.json","graph_json":"https://pith.science/api/pith-number/RBZIEWN5CEBN5SNVGD7ODP2FKM/graph.json","events_json":"https://pith.science/api/pith-number/RBZIEWN5CEBN5SNVGD7ODP2FKM/events.json","paper":"https://pith.science/paper/RBZIEWN5"},"agent_actions":{"view_html":"https://pith.science/pith/RBZIEWN5CEBN5SNVGD7ODP2FKM","download_json":"https://pith.science/pith/RBZIEWN5CEBN5SNVGD7ODP2FKM.json","view_paper":"https://pith.science/paper/RBZIEWN5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2104.04004&json=true","fetch_graph":"https://pith.science/api/pith-number/RBZIEWN5CEBN5SNVGD7ODP2FKM/graph.json","fetch_events":"https://pith.science/api/pith-number/RBZIEWN5CEBN5SNVGD7ODP2FKM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RBZIEWN5CEBN5SNVGD7ODP2FKM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RBZIEWN5CEBN5SNVGD7ODP2FKM/action/storage_attestation","attest_author":"https://pith.science/pith/RBZIEWN5CEBN5SNVGD7ODP2FKM/action/author_attestation","sign_citation":"https://pith.science/pith/RBZIEWN5CEBN5SNVGD7ODP2FKM/action/citation_signature","submit_replication":"https://pith.science/pith/RBZIEWN5CEBN5SNVGD7ODP2FKM/action/replication_record"}},"created_at":"2026-07-05T04:38:42.377492+00:00","updated_at":"2026-07-05T04:38:42.377492+00:00"}