{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:GFYTTFOJW4IVIWZT7VNINNPN7A","short_pith_number":"pith:GFYTTFOJ","canonical_record":{"source":{"id":"2005.09195","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2020-05-19T03:37:59Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"a9e80e9fc397fddc2ba70e37aa1dd796afca3a7d3b1834c52a95158131ca00c1","abstract_canon_sha256":"bb5e5fb2f02871e4d296c0bd8e71d792b3840789ab49c9cf18072d13ba3e2e41"},"schema_version":"1.0"},"canonical_sha256":"31713995c9b711545b33fd5a86b5edf8085ff64d0bec8b722faa04ab07963e53","source":{"kind":"arxiv","id":"2005.09195","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2005.09195","created_at":"2026-07-05T01:03:47Z"},{"alias_kind":"arxiv_version","alias_value":"2005.09195v1","created_at":"2026-07-05T01:03:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.09195","created_at":"2026-07-05T01:03:47Z"},{"alias_kind":"pith_short_12","alias_value":"GFYTTFOJW4IV","created_at":"2026-07-05T01:03:47Z"},{"alias_kind":"pith_short_16","alias_value":"GFYTTFOJW4IVIWZT","created_at":"2026-07-05T01:03:47Z"},{"alias_kind":"pith_short_8","alias_value":"GFYTTFOJ","created_at":"2026-07-05T01:03:47Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:GFYTTFOJW4IVIWZT7VNINNPN7A","target":"record","payload":{"canonical_record":{"source":{"id":"2005.09195","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2020-05-19T03:37:59Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"a9e80e9fc397fddc2ba70e37aa1dd796afca3a7d3b1834c52a95158131ca00c1","abstract_canon_sha256":"bb5e5fb2f02871e4d296c0bd8e71d792b3840789ab49c9cf18072d13ba3e2e41"},"schema_version":"1.0"},"canonical_sha256":"31713995c9b711545b33fd5a86b5edf8085ff64d0bec8b722faa04ab07963e53","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:03:47.850281Z","signature_b64":"KikCyBa8sjTfF6noxYMZa1HQpDgkdcLLAqlrki+UB+lc6DNm+xIOn36kPXFrRcPZQ7S7QQIdpq96ZgR3GURKCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"31713995c9b711545b33fd5a86b5edf8085ff64d0bec8b722faa04ab07963e53","last_reissued_at":"2026-07-05T01:03:47.849868Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:03:47.849868Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2005.09195","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:03:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"U8UsA6juk9wmHQCjXvKKchGoXxfTuE9e6g0sMeqVWdjevENU+kk5Lp/wHogIfgk03go8wV7vjfm/3SMa3LzzDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T17:24:55.781195Z"},"content_sha256":"9faa07c25bd33adef82c7a1f90629b70f136068cdaf32fcc7f853e7f96c49411","schema_version":"1.0","event_id":"sha256:9faa07c25bd33adef82c7a1f90629b70f136068cdaf32fcc7f853e7f96c49411"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:GFYTTFOJW4IVIWZT7VNINNPN7A","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Riemannian Proximal Policy Optimization","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Baocheng Zhu, Chen Li, James Zhang, Mingzhe Wu, Shijun Wang, Wei Chu, Yuan Qi","submitted_at":"2020-05-19T03:37:59Z","abstract_excerpt":"In this paper, We propose a general Riemannian proximal optimization algorithm with guaranteed convergence to solve Markov decision process (MDP) problems. To model policy functions in MDP, we employ Gaussian mixture model (GMM) and formulate it as a nonconvex optimization problem in the Riemannian space of positive semidefinite matrices. For two given policy functions, we also provide its lower bound on policy improvement by using bounds derived from the Wasserstein distance of GMMs. Preliminary experiments show the efficacy of our proposed Riemannian proximal policy optimization algorithm."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.09195","kind":"arxiv","version":1},"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/2005.09195/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":"2026-07-05T01:03:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PQM8wQ7WpQgddd9M4YcXfiT5zopgQPhzzG6907QmHZghdAL4yO91AyHv4moGCL9V7WH4JOzm9FB9P6xQshWkDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T17:24:55.781764Z"},"content_sha256":"fc317891e6a5d6548035d5190b64c261afcaab170d0cf6a814b6a8da36529cac","schema_version":"1.0","event_id":"sha256:fc317891e6a5d6548035d5190b64c261afcaab170d0cf6a814b6a8da36529cac"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GFYTTFOJW4IVIWZT7VNINNPN7A/bundle.json","state_url":"https://pith.science/pith/GFYTTFOJW4IVIWZT7VNINNPN7A/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GFYTTFOJW4IVIWZT7VNINNPN7A/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":"2026-08-14T17:24:55Z","links":{"resolver":"https://pith.science/pith/GFYTTFOJW4IVIWZT7VNINNPN7A","bundle":"https://pith.science/pith/GFYTTFOJW4IVIWZT7VNINNPN7A/bundle.json","state":"https://pith.science/pith/GFYTTFOJW4IVIWZT7VNINNPN7A/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GFYTTFOJW4IVIWZT7VNINNPN7A/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:GFYTTFOJW4IVIWZT7VNINNPN7A","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":"bb5e5fb2f02871e4d296c0bd8e71d792b3840789ab49c9cf18072d13ba3e2e41","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2020-05-19T03:37:59Z","title_canon_sha256":"a9e80e9fc397fddc2ba70e37aa1dd796afca3a7d3b1834c52a95158131ca00c1"},"schema_version":"1.0","source":{"id":"2005.09195","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2005.09195","created_at":"2026-07-05T01:03:47Z"},{"alias_kind":"arxiv_version","alias_value":"2005.09195v1","created_at":"2026-07-05T01:03:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.09195","created_at":"2026-07-05T01:03:47Z"},{"alias_kind":"pith_short_12","alias_value":"GFYTTFOJW4IV","created_at":"2026-07-05T01:03:47Z"},{"alias_kind":"pith_short_16","alias_value":"GFYTTFOJW4IVIWZT","created_at":"2026-07-05T01:03:47Z"},{"alias_kind":"pith_short_8","alias_value":"GFYTTFOJ","created_at":"2026-07-05T01:03:47Z"}],"graph_snapshots":[{"event_id":"sha256:fc317891e6a5d6548035d5190b64c261afcaab170d0cf6a814b6a8da36529cac","target":"graph","created_at":"2026-07-05T01:03:47Z","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/2005.09195/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, We propose a general Riemannian proximal optimization algorithm with guaranteed convergence to solve Markov decision process (MDP) problems. To model policy functions in MDP, we employ Gaussian mixture model (GMM) and formulate it as a nonconvex optimization problem in the Riemannian space of positive semidefinite matrices. For two given policy functions, we also provide its lower bound on policy improvement by using bounds derived from the Wasserstein distance of GMMs. Preliminary experiments show the efficacy of our proposed Riemannian proximal policy optimization algorithm.","authors_text":"Baocheng Zhu, Chen Li, James Zhang, Mingzhe Wu, Shijun Wang, Wei Chu, Yuan Qi","cross_cats":["stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2020-05-19T03:37:59Z","title":"Riemannian Proximal Policy Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.09195","kind":"arxiv","version":1},"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":"sha256:9faa07c25bd33adef82c7a1f90629b70f136068cdaf32fcc7f853e7f96c49411","target":"record","created_at":"2026-07-05T01:03:47Z","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":"bb5e5fb2f02871e4d296c0bd8e71d792b3840789ab49c9cf18072d13ba3e2e41","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2020-05-19T03:37:59Z","title_canon_sha256":"a9e80e9fc397fddc2ba70e37aa1dd796afca3a7d3b1834c52a95158131ca00c1"},"schema_version":"1.0","source":{"id":"2005.09195","kind":"arxiv","version":1}},"canonical_sha256":"31713995c9b711545b33fd5a86b5edf8085ff64d0bec8b722faa04ab07963e53","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"31713995c9b711545b33fd5a86b5edf8085ff64d0bec8b722faa04ab07963e53","first_computed_at":"2026-07-05T01:03:47.849868Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:03:47.849868Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KikCyBa8sjTfF6noxYMZa1HQpDgkdcLLAqlrki+UB+lc6DNm+xIOn36kPXFrRcPZQ7S7QQIdpq96ZgR3GURKCg==","signature_status":"signed_v1","signed_at":"2026-07-05T01:03:47.850281Z","signed_message":"canonical_sha256_bytes"},"source_id":"2005.09195","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9faa07c25bd33adef82c7a1f90629b70f136068cdaf32fcc7f853e7f96c49411","sha256:fc317891e6a5d6548035d5190b64c261afcaab170d0cf6a814b6a8da36529cac"],"state_sha256":"daae1e37c470ebad97880cc41d7b95d6994b9b10b4d16c94459fa1dd9a027b33"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wc8NVtw+dt1Tq1gQGiA5gFEb717DOcPVgSHz5ifytC1pchniFfqKdYrdjSPo0UWPFAwKNrfGAQcJL41z9xjcBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T17:24:55.787091Z","bundle_sha256":"17fc859e0f0b018af0f3646f1c4702298a24586bfbef6e99ee78d824c90edf2c"}}