{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:5J3IHVPAC65W3MDI2JH5IKWNPD","short_pith_number":"pith:5J3IHVPA","schema_version":"1.0","canonical_sha256":"ea7683d5e017bb6db068d24fd42acd78eeed53cba6256c056a2805ed5faa5d29","source":{"kind":"arxiv","id":"1903.00725","version":3},"attestation_state":"computed","paper":{"title":"A Regularized Approach to Sparse Optimal Policy in Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Wenhao Yang, Xiang Li, Zhihua Zhang","submitted_at":"2019-03-02T15:34:25Z","abstract_excerpt":"We propose and study a general framework for regularized Markov decision processes (MDPs) where the goal is to find an optimal policy that maximizes the expected discounted total reward plus a policy regularization term. The extant entropy-regularized MDPs can be cast into our framework. Moreover, under our framework, many regularization terms can bring multi-modality and sparsity, which are potentially useful in reinforcement learning. In particular, we present sufficient and necessary conditions that induce a sparse optimal policy. We also conduct a full mathematical analysis of the proposed"},"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":"1903.00725","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-03-02T15:34:25Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"e2c46d61dd5ec8532e298d75c3b4c706c5eb6b27975c18ecb6e2781120c18a71","abstract_canon_sha256":"2a9f0d74869204bc855ca521cf68b06bd89eb7aa3533e52bca0c6441486172cc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:13:13.733650Z","signature_b64":"Ffgpn82tf6v4EJ6YbEYqyN+xNtTcRWjZr1Zk+wYvC3LcTwNn2JgxQzlCEmuIC9TfAecymDbpz4yGh8NhlN0sAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ea7683d5e017bb6db068d24fd42acd78eeed53cba6256c056a2805ed5faa5d29","last_reissued_at":"2026-07-05T00:13:13.733161Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:13:13.733161Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Regularized Approach to Sparse Optimal Policy in Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Wenhao Yang, Xiang Li, Zhihua Zhang","submitted_at":"2019-03-02T15:34:25Z","abstract_excerpt":"We propose and study a general framework for regularized Markov decision processes (MDPs) where the goal is to find an optimal policy that maximizes the expected discounted total reward plus a policy regularization term. The extant entropy-regularized MDPs can be cast into our framework. Moreover, under our framework, many regularization terms can bring multi-modality and sparsity, which are potentially useful in reinforcement learning. In particular, we present sufficient and necessary conditions that induce a sparse optimal policy. We also conduct a full mathematical analysis of the proposed"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.00725","kind":"arxiv","version":3},"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/1903.00725/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":"1903.00725","created_at":"2026-07-05T00:13:13.733218+00:00"},{"alias_kind":"arxiv_version","alias_value":"1903.00725v3","created_at":"2026-07-05T00:13:13.733218+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.00725","created_at":"2026-07-05T00:13:13.733218+00:00"},{"alias_kind":"pith_short_12","alias_value":"5J3IHVPAC65W","created_at":"2026-07-05T00:13:13.733218+00:00"},{"alias_kind":"pith_short_16","alias_value":"5J3IHVPAC65W3MDI","created_at":"2026-07-05T00:13:13.733218+00:00"},{"alias_kind":"pith_short_8","alias_value":"5J3IHVPA","created_at":"2026-07-05T00:13:13.733218+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"1907.04214","citing_title":"Entropic Regularization of Markov Decision Processes","ref_index":43,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5J3IHVPAC65W3MDI2JH5IKWNPD","json":"https://pith.science/pith/5J3IHVPAC65W3MDI2JH5IKWNPD.json","graph_json":"https://pith.science/api/pith-number/5J3IHVPAC65W3MDI2JH5IKWNPD/graph.json","events_json":"https://pith.science/api/pith-number/5J3IHVPAC65W3MDI2JH5IKWNPD/events.json","paper":"https://pith.science/paper/5J3IHVPA"},"agent_actions":{"view_html":"https://pith.science/pith/5J3IHVPAC65W3MDI2JH5IKWNPD","download_json":"https://pith.science/pith/5J3IHVPAC65W3MDI2JH5IKWNPD.json","view_paper":"https://pith.science/paper/5J3IHVPA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1903.00725&json=true","fetch_graph":"https://pith.science/api/pith-number/5J3IHVPAC65W3MDI2JH5IKWNPD/graph.json","fetch_events":"https://pith.science/api/pith-number/5J3IHVPAC65W3MDI2JH5IKWNPD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5J3IHVPAC65W3MDI2JH5IKWNPD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5J3IHVPAC65W3MDI2JH5IKWNPD/action/storage_attestation","attest_author":"https://pith.science/pith/5J3IHVPAC65W3MDI2JH5IKWNPD/action/author_attestation","sign_citation":"https://pith.science/pith/5J3IHVPAC65W3MDI2JH5IKWNPD/action/citation_signature","submit_replication":"https://pith.science/pith/5J3IHVPAC65W3MDI2JH5IKWNPD/action/replication_record"}},"created_at":"2026-07-05T00:13:13.733218+00:00","updated_at":"2026-07-05T00:13:13.733218+00:00"}