{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:DA3433EZWL5SYBFMAEGIUHWQXZ","short_pith_number":"pith:DA3433EZ","canonical_record":{"source":{"id":"2201.09457","kind":"arxiv","version":9},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2022-01-24T04:54:58Z","cross_cats_sorted":["cs.AI","math.OC"],"title_canon_sha256":"c26ce46d9735d520f7267a6d8cd7f550d69dc56a51cb0badf5b3c8384dd73047","abstract_canon_sha256":"6bfede56765642654ed9be2949927922dd005cc62679b6202dab7c0d5ef5418a"},"schema_version":"1.0"},"canonical_sha256":"1837cdec99b2fb2c04ac010c8a1ed0be58e8d38c379c91fbfdc3ea9d1851e027","source":{"kind":"arxiv","id":"2201.09457","version":9},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2201.09457","created_at":"2026-07-05T05:20:09Z"},{"alias_kind":"arxiv_version","alias_value":"2201.09457v9","created_at":"2026-07-05T05:20:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.09457","created_at":"2026-07-05T05:20:09Z"},{"alias_kind":"pith_short_12","alias_value":"DA3433EZWL5S","created_at":"2026-07-05T05:20:09Z"},{"alias_kind":"pith_short_16","alias_value":"DA3433EZWL5SYBFM","created_at":"2026-07-05T05:20:09Z"},{"alias_kind":"pith_short_8","alias_value":"DA3433EZ","created_at":"2026-07-05T05:20:09Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:DA3433EZWL5SYBFMAEGIUHWQXZ","target":"record","payload":{"canonical_record":{"source":{"id":"2201.09457","kind":"arxiv","version":9},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2022-01-24T04:54:58Z","cross_cats_sorted":["cs.AI","math.OC"],"title_canon_sha256":"c26ce46d9735d520f7267a6d8cd7f550d69dc56a51cb0badf5b3c8384dd73047","abstract_canon_sha256":"6bfede56765642654ed9be2949927922dd005cc62679b6202dab7c0d5ef5418a"},"schema_version":"1.0"},"canonical_sha256":"1837cdec99b2fb2c04ac010c8a1ed0be58e8d38c379c91fbfdc3ea9d1851e027","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:20:09.735717Z","signature_b64":"SdvP2mblwSzwkznJ3XfTqnt8yBNYemIViNmZ66vn/fXYksgDpVLRtbW/H0B7Uq3mnG0POKLSH9p3HF9n304wBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1837cdec99b2fb2c04ac010c8a1ed0be58e8d38c379c91fbfdc3ea9d1851e027","last_reissued_at":"2026-07-05T05:20:09.735189Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:20:09.735189Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2201.09457","source_version":9,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:20:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1NFLjZCyiXpsYHVZcbTK/Z8JQLYOTVJL02tojT3d9wzVe0aB0izR0rnKgEqeUGSigq6YiEDD+Hs4uMSRwrLABA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-26T08:24:55.109684Z"},"content_sha256":"e877bf6f4fd4e1715a814031aeabdf9b8c618eadb689db27fd8bb5a76bbbb4f0","schema_version":"1.0","event_id":"sha256:e877bf6f4fd4e1715a814031aeabdf9b8c618eadb689db27fd8bb5a76bbbb4f0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:DA3433EZWL5SYBFMAEGIUHWQXZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Homotopic Policy Mirror Descent: Policy Convergence, Implicit Regularization, and Improved Sample Complexity","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","math.OC"],"primary_cat":"cs.LG","authors_text":"Guanghui Lan, Tuo Zhao, Yan Li","submitted_at":"2022-01-24T04:54:58Z","abstract_excerpt":"We propose a new policy gradient method, named homotopic policy mirror descent (HPMD), for solving discounted, infinite horizon MDPs with finite state and action spaces. HPMD performs a mirror descent type policy update with an additional diminishing regularization term, and possesses several computational properties that seem to be new in the literature. We first establish the global linear convergence of HPMD instantiated with Kullback-Leibler divergence, for both the optimality gap, and a weighted distance to the set of optimal policies. Then local superlinear convergence is obtained for bo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.09457","kind":"arxiv","version":9},"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/2201.09457/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":"2026-07-05T05:20:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8VWohuPm/ROUhh6VmPe1gnHcSrbJGZ0qcJZQB/VQ2U5RqbO8XzL+SV4gH/HeHUUkCbwQDq/rgymxOmOCx9nUBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-26T08:24:55.110060Z"},"content_sha256":"668127f0361d4fbfa7603a4fe2f27d3faba21fc4c3436db3447ddc648062aa10","schema_version":"1.0","event_id":"sha256:668127f0361d4fbfa7603a4fe2f27d3faba21fc4c3436db3447ddc648062aa10"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DA3433EZWL5SYBFMAEGIUHWQXZ/bundle.json","state_url":"https://pith.science/pith/DA3433EZWL5SYBFMAEGIUHWQXZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DA3433EZWL5SYBFMAEGIUHWQXZ/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":"2026-07-26T08:24:55Z","links":{"resolver":"https://pith.science/pith/DA3433EZWL5SYBFMAEGIUHWQXZ","bundle":"https://pith.science/pith/DA3433EZWL5SYBFMAEGIUHWQXZ/bundle.json","state":"https://pith.science/pith/DA3433EZWL5SYBFMAEGIUHWQXZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DA3433EZWL5SYBFMAEGIUHWQXZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:DA3433EZWL5SYBFMAEGIUHWQXZ","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":"6bfede56765642654ed9be2949927922dd005cc62679b6202dab7c0d5ef5418a","cross_cats_sorted":["cs.AI","math.OC"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2022-01-24T04:54:58Z","title_canon_sha256":"c26ce46d9735d520f7267a6d8cd7f550d69dc56a51cb0badf5b3c8384dd73047"},"schema_version":"1.0","source":{"id":"2201.09457","kind":"arxiv","version":9}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2201.09457","created_at":"2026-07-05T05:20:09Z"},{"alias_kind":"arxiv_version","alias_value":"2201.09457v9","created_at":"2026-07-05T05:20:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.09457","created_at":"2026-07-05T05:20:09Z"},{"alias_kind":"pith_short_12","alias_value":"DA3433EZWL5S","created_at":"2026-07-05T05:20:09Z"},{"alias_kind":"pith_short_16","alias_value":"DA3433EZWL5SYBFM","created_at":"2026-07-05T05:20:09Z"},{"alias_kind":"pith_short_8","alias_value":"DA3433EZ","created_at":"2026-07-05T05:20:09Z"}],"graph_snapshots":[{"event_id":"sha256:668127f0361d4fbfa7603a4fe2f27d3faba21fc4c3436db3447ddc648062aa10","target":"graph","created_at":"2026-07-05T05:20:09Z","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/2201.09457/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose a new policy gradient method, named homotopic policy mirror descent (HPMD), for solving discounted, infinite horizon MDPs with finite state and action spaces. HPMD performs a mirror descent type policy update with an additional diminishing regularization term, and possesses several computational properties that seem to be new in the literature. We first establish the global linear convergence of HPMD instantiated with Kullback-Leibler divergence, for both the optimality gap, and a weighted distance to the set of optimal policies. Then local superlinear convergence is obtained for bo","authors_text":"Guanghui Lan, Tuo Zhao, Yan Li","cross_cats":["cs.AI","math.OC"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2022-01-24T04:54:58Z","title":"Homotopic Policy Mirror Descent: Policy Convergence, Implicit Regularization, and Improved Sample Complexity"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.09457","kind":"arxiv","version":9},"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:e877bf6f4fd4e1715a814031aeabdf9b8c618eadb689db27fd8bb5a76bbbb4f0","target":"record","created_at":"2026-07-05T05:20:09Z","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":"6bfede56765642654ed9be2949927922dd005cc62679b6202dab7c0d5ef5418a","cross_cats_sorted":["cs.AI","math.OC"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2022-01-24T04:54:58Z","title_canon_sha256":"c26ce46d9735d520f7267a6d8cd7f550d69dc56a51cb0badf5b3c8384dd73047"},"schema_version":"1.0","source":{"id":"2201.09457","kind":"arxiv","version":9}},"canonical_sha256":"1837cdec99b2fb2c04ac010c8a1ed0be58e8d38c379c91fbfdc3ea9d1851e027","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1837cdec99b2fb2c04ac010c8a1ed0be58e8d38c379c91fbfdc3ea9d1851e027","first_computed_at":"2026-07-05T05:20:09.735189Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:20:09.735189Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SdvP2mblwSzwkznJ3XfTqnt8yBNYemIViNmZ66vn/fXYksgDpVLRtbW/H0B7Uq3mnG0POKLSH9p3HF9n304wBw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:20:09.735717Z","signed_message":"canonical_sha256_bytes"},"source_id":"2201.09457","source_kind":"arxiv","source_version":9}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e877bf6f4fd4e1715a814031aeabdf9b8c618eadb689db27fd8bb5a76bbbb4f0","sha256:668127f0361d4fbfa7603a4fe2f27d3faba21fc4c3436db3447ddc648062aa10"],"state_sha256":"3d3cc9c76a30cbd9a6309341dc4f1c7c3a8e573ab014cdd6e425347b45b08718"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"A1Sh18mI/1wA/8aLt1Lv20Jc4vAZb/neijRAv4ltw83MIIPXuuvWKXCgF89On8u9VaK6hcMxgm4ruk+89azIDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-26T08:24:55.112522Z","bundle_sha256":"3f95bbe4c43ee6ca2ea00c87092922eb293e402de4014f27585c198518dbd192"}}