{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:DS5XIDUCNVDQIPAZKAJLEBXPZK","short_pith_number":"pith:DS5XIDUC","schema_version":"1.0","canonical_sha256":"1cbb740e826d47043c195012b206efca8e4215cf296a1eb38f64f3f5e509ddfb","source":{"kind":"arxiv","id":"2105.08666","version":4},"attestation_state":"computed","paper":{"title":"Reinforcement Learning With Sparse-Executing Actions via Sparsity Regularization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Jing-cheng Pang, Shengyi Jiang, Tian Xu, Yang Yu, Yu-Ren Liu","submitted_at":"2021-05-18T16:50:42Z","abstract_excerpt":"Reinforcement learning (RL) has demonstrated impressive performance in decision-making tasks like embodied control, autonomous driving and financial trading. In many decision-making tasks, the agents often encounter the problem of executing actions under limited budgets. However, classic RL methods typically overlook the challenges posed by such sparse-executing actions. They operate under the assumption that all actions can be taken for a unlimited number of times, both in the formulation of the problem and in the development of effective algorithms. To tackle the issue of limited action exec"},"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":"2105.08666","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-05-18T16:50:42Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"9387f2482b6daff155316c09ac3b5fadce70ce09fc663e3fb9e94eca34e097c5","abstract_canon_sha256":"dc5591396d7dbf87362e033b8dee303432b1ce846280bdc183abb1af4a621dae"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:46:14.395721Z","signature_b64":"30PF4v6b2Rycb9g+0XLgGzvOdxXejcT7eFHyQKTxQMJipgrmR23yS1A5VJfvpiQoV/Eub8SzMN3Fm5ru1MXqBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1cbb740e826d47043c195012b206efca8e4215cf296a1eb38f64f3f5e509ddfb","last_reissued_at":"2026-07-05T08:46:14.395345Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:46:14.395345Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reinforcement Learning With Sparse-Executing Actions via Sparsity Regularization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Jing-cheng Pang, Shengyi Jiang, Tian Xu, Yang Yu, Yu-Ren Liu","submitted_at":"2021-05-18T16:50:42Z","abstract_excerpt":"Reinforcement learning (RL) has demonstrated impressive performance in decision-making tasks like embodied control, autonomous driving and financial trading. In many decision-making tasks, the agents often encounter the problem of executing actions under limited budgets. However, classic RL methods typically overlook the challenges posed by such sparse-executing actions. They operate under the assumption that all actions can be taken for a unlimited number of times, both in the formulation of the problem and in the development of effective algorithms. To tackle the issue of limited action exec"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.08666","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/2105.08666/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":"2105.08666","created_at":"2026-07-05T08:46:14.395401+00:00"},{"alias_kind":"arxiv_version","alias_value":"2105.08666v4","created_at":"2026-07-05T08:46:14.395401+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.08666","created_at":"2026-07-05T08:46:14.395401+00:00"},{"alias_kind":"pith_short_12","alias_value":"DS5XIDUCNVDQ","created_at":"2026-07-05T08:46:14.395401+00:00"},{"alias_kind":"pith_short_16","alias_value":"DS5XIDUCNVDQIPAZ","created_at":"2026-07-05T08:46:14.395401+00:00"},{"alias_kind":"pith_short_8","alias_value":"DS5XIDUC","created_at":"2026-07-05T08:46:14.395401+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/DS5XIDUCNVDQIPAZKAJLEBXPZK","json":"https://pith.science/pith/DS5XIDUCNVDQIPAZKAJLEBXPZK.json","graph_json":"https://pith.science/api/pith-number/DS5XIDUCNVDQIPAZKAJLEBXPZK/graph.json","events_json":"https://pith.science/api/pith-number/DS5XIDUCNVDQIPAZKAJLEBXPZK/events.json","paper":"https://pith.science/paper/DS5XIDUC"},"agent_actions":{"view_html":"https://pith.science/pith/DS5XIDUCNVDQIPAZKAJLEBXPZK","download_json":"https://pith.science/pith/DS5XIDUCNVDQIPAZKAJLEBXPZK.json","view_paper":"https://pith.science/paper/DS5XIDUC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2105.08666&json=true","fetch_graph":"https://pith.science/api/pith-number/DS5XIDUCNVDQIPAZKAJLEBXPZK/graph.json","fetch_events":"https://pith.science/api/pith-number/DS5XIDUCNVDQIPAZKAJLEBXPZK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DS5XIDUCNVDQIPAZKAJLEBXPZK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DS5XIDUCNVDQIPAZKAJLEBXPZK/action/storage_attestation","attest_author":"https://pith.science/pith/DS5XIDUCNVDQIPAZKAJLEBXPZK/action/author_attestation","sign_citation":"https://pith.science/pith/DS5XIDUCNVDQIPAZKAJLEBXPZK/action/citation_signature","submit_replication":"https://pith.science/pith/DS5XIDUCNVDQIPAZKAJLEBXPZK/action/replication_record"}},"created_at":"2026-07-05T08:46:14.395401+00:00","updated_at":"2026-07-05T08:46:14.395401+00:00"}