{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:ZU2MR5LPRJNLRVZ6KXUSCWEAUZ","short_pith_number":"pith:ZU2MR5LP","canonical_record":{"source":{"id":"2012.14098","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2020-12-28T05:02:26Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"4a58d404c193fd85d22c81812464e001389a05aefbf37486d3e09f1a8bdaabd6","abstract_canon_sha256":"7feb0acb648ca23e800da7c4bc047fb4f905b729a16ffc249f247662866bf339"},"schema_version":"1.0"},"canonical_sha256":"cd34c8f56f8a5ab8d73e55e9215880a64a6aa3bba122001cf06adea527babb72","source":{"kind":"arxiv","id":"2012.14098","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2012.14098","created_at":"2026-07-05T06:51:15Z"},{"alias_kind":"arxiv_version","alias_value":"2012.14098v2","created_at":"2026-07-05T06:51:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.14098","created_at":"2026-07-05T06:51:15Z"},{"alias_kind":"pith_short_12","alias_value":"ZU2MR5LPRJNL","created_at":"2026-07-05T06:51:15Z"},{"alias_kind":"pith_short_16","alias_value":"ZU2MR5LPRJNLRVZ6","created_at":"2026-07-05T06:51:15Z"},{"alias_kind":"pith_short_8","alias_value":"ZU2MR5LP","created_at":"2026-07-05T06:51:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:ZU2MR5LPRJNLRVZ6KXUSCWEAUZ","target":"record","payload":{"canonical_record":{"source":{"id":"2012.14098","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2020-12-28T05:02:26Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"4a58d404c193fd85d22c81812464e001389a05aefbf37486d3e09f1a8bdaabd6","abstract_canon_sha256":"7feb0acb648ca23e800da7c4bc047fb4f905b729a16ffc249f247662866bf339"},"schema_version":"1.0"},"canonical_sha256":"cd34c8f56f8a5ab8d73e55e9215880a64a6aa3bba122001cf06adea527babb72","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:51:15.973971Z","signature_b64":"U6kPPiuZuyRhk42RJKJ2MKhTc0qXZXqhZKHPby5Cn53h911UkAgWrHkl4BSNdPk7xEm6nHUBKIyYZa3OnFtaDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cd34c8f56f8a5ab8d73e55e9215880a64a6aa3bba122001cf06adea527babb72","last_reissued_at":"2026-07-05T06:51:15.973466Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:51:15.973466Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2012.14098","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:51:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hUAIjQrP3zEB+/MPy6mSqJqOjjHg2d2w76vTkQwYm1vIq+Thj/98c759FxuUAtVjAihhKOp4+fZQH4Ce6YppBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-16T14:50:35.180294Z"},"content_sha256":"49be74ce5bac4df51084e649a9153ef101b902d80f2632679fa16d8cea382e08","schema_version":"1.0","event_id":"sha256:49be74ce5bac4df51084e649a9153ef101b902d80f2632679fa16d8cea382e08"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:ZU2MR5LPRJNLRVZ6KXUSCWEAUZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Risk-Sensitive Deep RL: Variance-Constrained Actor-Critic Provably Finds Globally Optimal Policy","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Ethan X. Fang, Han Zhong, Runze Li, Xun Deng, Zhaoran Wang, Zhuoran Yang","submitted_at":"2020-12-28T05:02:26Z","abstract_excerpt":"While deep reinforcement learning has achieved tremendous successes in various applications, most existing works only focus on maximizing the expected value of total return and thus ignore its inherent stochasticity. Such stochasticity is also known as the aleatoric uncertainty and is closely related to the notion of risk. In this work, we make the first attempt to study risk-sensitive deep reinforcement learning under the average reward setting with the variance risk criteria. In particular, we focus on a variance-constrained policy optimization problem where the goal is to find a policy that"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.14098","kind":"arxiv","version":2},"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/2012.14098/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":"2026-07-05T06:51:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aRi7awjwmRmEzj3OItE2rpZMbKh1UifToWcTNhViBoCSaXITirVjF4zuZEDXzfd8+ALItbXAU9dc58iYm1pDAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-16T14:50:35.180707Z"},"content_sha256":"d73fbac821de0f5658cd15cc572b62f5e95f15bef7fa96244ce14071f33a0944","schema_version":"1.0","event_id":"sha256:d73fbac821de0f5658cd15cc572b62f5e95f15bef7fa96244ce14071f33a0944"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZU2MR5LPRJNLRVZ6KXUSCWEAUZ/bundle.json","state_url":"https://pith.science/pith/ZU2MR5LPRJNLRVZ6KXUSCWEAUZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZU2MR5LPRJNLRVZ6KXUSCWEAUZ/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":"2026-07-16T14:50:35Z","links":{"resolver":"https://pith.science/pith/ZU2MR5LPRJNLRVZ6KXUSCWEAUZ","bundle":"https://pith.science/pith/ZU2MR5LPRJNLRVZ6KXUSCWEAUZ/bundle.json","state":"https://pith.science/pith/ZU2MR5LPRJNLRVZ6KXUSCWEAUZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZU2MR5LPRJNLRVZ6KXUSCWEAUZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:ZU2MR5LPRJNLRVZ6KXUSCWEAUZ","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":"7feb0acb648ca23e800da7c4bc047fb4f905b729a16ffc249f247662866bf339","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2020-12-28T05:02:26Z","title_canon_sha256":"4a58d404c193fd85d22c81812464e001389a05aefbf37486d3e09f1a8bdaabd6"},"schema_version":"1.0","source":{"id":"2012.14098","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2012.14098","created_at":"2026-07-05T06:51:15Z"},{"alias_kind":"arxiv_version","alias_value":"2012.14098v2","created_at":"2026-07-05T06:51:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.14098","created_at":"2026-07-05T06:51:15Z"},{"alias_kind":"pith_short_12","alias_value":"ZU2MR5LPRJNL","created_at":"2026-07-05T06:51:15Z"},{"alias_kind":"pith_short_16","alias_value":"ZU2MR5LPRJNLRVZ6","created_at":"2026-07-05T06:51:15Z"},{"alias_kind":"pith_short_8","alias_value":"ZU2MR5LP","created_at":"2026-07-05T06:51:15Z"}],"graph_snapshots":[{"event_id":"sha256:d73fbac821de0f5658cd15cc572b62f5e95f15bef7fa96244ce14071f33a0944","target":"graph","created_at":"2026-07-05T06:51:15Z","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/2012.14098/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While deep reinforcement learning has achieved tremendous successes in various applications, most existing works only focus on maximizing the expected value of total return and thus ignore its inherent stochasticity. Such stochasticity is also known as the aleatoric uncertainty and is closely related to the notion of risk. In this work, we make the first attempt to study risk-sensitive deep reinforcement learning under the average reward setting with the variance risk criteria. In particular, we focus on a variance-constrained policy optimization problem where the goal is to find a policy that","authors_text":"Ethan X. Fang, Han Zhong, Runze Li, Xun Deng, Zhaoran Wang, Zhuoran Yang","cross_cats":["math.OC","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2020-12-28T05:02:26Z","title":"Risk-Sensitive Deep RL: Variance-Constrained Actor-Critic Provably Finds Globally Optimal Policy"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.14098","kind":"arxiv","version":2},"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":"sha256:49be74ce5bac4df51084e649a9153ef101b902d80f2632679fa16d8cea382e08","target":"record","created_at":"2026-07-05T06:51:15Z","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":"7feb0acb648ca23e800da7c4bc047fb4f905b729a16ffc249f247662866bf339","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2020-12-28T05:02:26Z","title_canon_sha256":"4a58d404c193fd85d22c81812464e001389a05aefbf37486d3e09f1a8bdaabd6"},"schema_version":"1.0","source":{"id":"2012.14098","kind":"arxiv","version":2}},"canonical_sha256":"cd34c8f56f8a5ab8d73e55e9215880a64a6aa3bba122001cf06adea527babb72","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cd34c8f56f8a5ab8d73e55e9215880a64a6aa3bba122001cf06adea527babb72","first_computed_at":"2026-07-05T06:51:15.973466Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:51:15.973466Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"U6kPPiuZuyRhk42RJKJ2MKhTc0qXZXqhZKHPby5Cn53h911UkAgWrHkl4BSNdPk7xEm6nHUBKIyYZa3OnFtaDA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:51:15.973971Z","signed_message":"canonical_sha256_bytes"},"source_id":"2012.14098","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:49be74ce5bac4df51084e649a9153ef101b902d80f2632679fa16d8cea382e08","sha256:d73fbac821de0f5658cd15cc572b62f5e95f15bef7fa96244ce14071f33a0944"],"state_sha256":"6cc64b314c52c51c1048ee888b24e1b964c98784b64a2e6d1ea9ed5fc6bfb98f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OIZIyTE9PNKLxfgX8iCDAecJkg2R38DFqAS7fMflBTckReK7/a58cowvo7pVhVVnS3yw9bjao58v+XxD0n1bDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-16T14:50:35.183710Z","bundle_sha256":"8f6fd13d9f977305251f274f0821de51c55b37246ee62c4ea91e78a3003a9665"}}