{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:5J3IHVPAC65W3MDI2JH5IKWNPD","short_pith_number":"pith:5J3IHVPA","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"},"canonical_sha256":"ea7683d5e017bb6db068d24fd42acd78eeed53cba6256c056a2805ed5faa5d29","source":{"kind":"arxiv","id":"1903.00725","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1903.00725","created_at":"2026-07-05T00:13:13Z"},{"alias_kind":"arxiv_version","alias_value":"1903.00725v3","created_at":"2026-07-05T00:13:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.00725","created_at":"2026-07-05T00:13:13Z"},{"alias_kind":"pith_short_12","alias_value":"5J3IHVPAC65W","created_at":"2026-07-05T00:13:13Z"},{"alias_kind":"pith_short_16","alias_value":"5J3IHVPAC65W3MDI","created_at":"2026-07-05T00:13:13Z"},{"alias_kind":"pith_short_8","alias_value":"5J3IHVPA","created_at":"2026-07-05T00:13:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:5J3IHVPAC65W3MDI2JH5IKWNPD","target":"record","payload":{"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"},"canonical_sha256":"ea7683d5e017bb6db068d24fd42acd78eeed53cba6256c056a2805ed5faa5d29","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"},"source_kind":"arxiv","source_id":"1903.00725","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T00:13:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZcsY96bQ+oaupKrDxfOv9fSWjLKAXOjgASWx9R02mtMiyJGseJj0BZQ72PUdZSRpp8WufKkzzxApQNfz3bHaBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T15:04:21.631078Z"},"content_sha256":"4b7e0e6fba1ab6d4a92f1711cf9bd274ac2f17f064940eadc52d41ce7b82703a","schema_version":"1.0","event_id":"sha256:4b7e0e6fba1ab6d4a92f1711cf9bd274ac2f17f064940eadc52d41ce7b82703a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:5J3IHVPAC65W3MDI2JH5IKWNPD","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T00:13:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eHrllqI1kGE7Wqyh/4WxGWNcN2RDqJ3l8PTD/O9VAsTZLUYiv6Zo3h6k5SwSkMxXBM6f0dFgqx4elpQjqgM+Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T15:04:21.631599Z"},"content_sha256":"88095db2c95709672657d3488101de71d74578d9066f435dfcb7921afa92d157","schema_version":"1.0","event_id":"sha256:88095db2c95709672657d3488101de71d74578d9066f435dfcb7921afa92d157"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5J3IHVPAC65W3MDI2JH5IKWNPD/bundle.json","state_url":"https://pith.science/pith/5J3IHVPAC65W3MDI2JH5IKWNPD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5J3IHVPAC65W3MDI2JH5IKWNPD/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-04T15:04:21Z","links":{"resolver":"https://pith.science/pith/5J3IHVPAC65W3MDI2JH5IKWNPD","bundle":"https://pith.science/pith/5J3IHVPAC65W3MDI2JH5IKWNPD/bundle.json","state":"https://pith.science/pith/5J3IHVPAC65W3MDI2JH5IKWNPD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5J3IHVPAC65W3MDI2JH5IKWNPD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:5J3IHVPAC65W3MDI2JH5IKWNPD","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"2a9f0d74869204bc855ca521cf68b06bd89eb7aa3533e52bca0c6441486172cc","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-03-02T15:34:25Z","title_canon_sha256":"e2c46d61dd5ec8532e298d75c3b4c706c5eb6b27975c18ecb6e2781120c18a71"},"schema_version":"1.0","source":{"id":"1903.00725","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1903.00725","created_at":"2026-07-05T00:13:13Z"},{"alias_kind":"arxiv_version","alias_value":"1903.00725v3","created_at":"2026-07-05T00:13:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.00725","created_at":"2026-07-05T00:13:13Z"},{"alias_kind":"pith_short_12","alias_value":"5J3IHVPAC65W","created_at":"2026-07-05T00:13:13Z"},{"alias_kind":"pith_short_16","alias_value":"5J3IHVPAC65W3MDI","created_at":"2026-07-05T00:13:13Z"},{"alias_kind":"pith_short_8","alias_value":"5J3IHVPA","created_at":"2026-07-05T00:13:13Z"}],"graph_snapshots":[{"event_id":"sha256:88095db2c95709672657d3488101de71d74578d9066f435dfcb7921afa92d157","target":"graph","created_at":"2026-07-05T00:13:13Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/1903.00725/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Wenhao Yang, Xiang Li, Zhihua Zhang","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-03-02T15:34:25Z","title":"A Regularized Approach to Sparse Optimal Policy in Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.00725","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:4b7e0e6fba1ab6d4a92f1711cf9bd274ac2f17f064940eadc52d41ce7b82703a","target":"record","created_at":"2026-07-05T00:13:13Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"2a9f0d74869204bc855ca521cf68b06bd89eb7aa3533e52bca0c6441486172cc","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-03-02T15:34:25Z","title_canon_sha256":"e2c46d61dd5ec8532e298d75c3b4c706c5eb6b27975c18ecb6e2781120c18a71"},"schema_version":"1.0","source":{"id":"1903.00725","kind":"arxiv","version":3}},"canonical_sha256":"ea7683d5e017bb6db068d24fd42acd78eeed53cba6256c056a2805ed5faa5d29","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ea7683d5e017bb6db068d24fd42acd78eeed53cba6256c056a2805ed5faa5d29","first_computed_at":"2026-07-05T00:13:13.733161Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:13:13.733161Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Ffgpn82tf6v4EJ6YbEYqyN+xNtTcRWjZr1Zk+wYvC3LcTwNn2JgxQzlCEmuIC9TfAecymDbpz4yGh8NhlN0sAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T00:13:13.733650Z","signed_message":"canonical_sha256_bytes"},"source_id":"1903.00725","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4b7e0e6fba1ab6d4a92f1711cf9bd274ac2f17f064940eadc52d41ce7b82703a","sha256:88095db2c95709672657d3488101de71d74578d9066f435dfcb7921afa92d157"],"state_sha256":"3b561f3b67a9702f95f3274fd07b94f134a0d6fbb758390e0b1c90e3201da948"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8AAU2A+v1sjCzqNqtCHOkxDyLsNINiIPozqaqKC4oZdy3VarXEYXldF2+HSY3/eCPRMtFAci4aQvT3rIKQ21BA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T15:04:21.635235Z","bundle_sha256":"ef2cc4b0bc74528e1b9fd675b73e33a9c2d62715e1959bfb626042945c41d645"}}