{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:6BYGOUEWWAEEI27ERN5KGXXNZH","short_pith_number":"pith:6BYGOUEW","canonical_record":{"source":{"id":"2408.07245","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-08-14T01:01:35Z","cross_cats_sorted":[],"title_canon_sha256":"f097da787f37a785bbe6275d2ded7dfd701e0f0cf40681e97038fcf9862b520e","abstract_canon_sha256":"f7f4f0e039b735e20842c9db93dc63558be96c9e4ead333c5c2c2140c256d531"},"schema_version":"1.0"},"canonical_sha256":"f070675096b008446be48b7aa35eedc9ed95649ca87581bfaa764e359664e183","source":{"kind":"arxiv","id":"2408.07245","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.07245","created_at":"2026-07-05T10:04:57Z"},{"alias_kind":"arxiv_version","alias_value":"2408.07245v3","created_at":"2026-07-05T10:04:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.07245","created_at":"2026-07-05T10:04:57Z"},{"alias_kind":"pith_short_12","alias_value":"6BYGOUEWWAEE","created_at":"2026-07-05T10:04:57Z"},{"alias_kind":"pith_short_16","alias_value":"6BYGOUEWWAEEI27E","created_at":"2026-07-05T10:04:57Z"},{"alias_kind":"pith_short_8","alias_value":"6BYGOUEW","created_at":"2026-07-05T10:04:57Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:6BYGOUEWWAEEI27ERN5KGXXNZH","target":"record","payload":{"canonical_record":{"source":{"id":"2408.07245","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-08-14T01:01:35Z","cross_cats_sorted":[],"title_canon_sha256":"f097da787f37a785bbe6275d2ded7dfd701e0f0cf40681e97038fcf9862b520e","abstract_canon_sha256":"f7f4f0e039b735e20842c9db93dc63558be96c9e4ead333c5c2c2140c256d531"},"schema_version":"1.0"},"canonical_sha256":"f070675096b008446be48b7aa35eedc9ed95649ca87581bfaa764e359664e183","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:04:57.667846Z","signature_b64":"mnOWmUjm/EBYh3c/RSm6IGA//uBaxmqVW+9CT/8PuLGzDawrqY1xjdng7g2f8c8dgxYYOjNEvV0HVf9RJZl5Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f070675096b008446be48b7aa35eedc9ed95649ca87581bfaa764e359664e183","last_reissued_at":"2026-07-05T10:04:57.667369Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:04:57.667369Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2408.07245","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":"2026-07-05T10:04:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"U5YxifUj59ZfxsCvCsJcx2m2Bb5OcGKtlhC4dEJT6owo6qXB9ySMJGG9EtXdEgJnrzPyB4piQ7uw+QuShFV8Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T09:31:56.853714Z"},"content_sha256":"3caa951f55216f5a89581c8b11731d4dfc580cadc0cd0150b77ca10856113f74","schema_version":"1.0","event_id":"sha256:3caa951f55216f5a89581c8b11731d4dfc580cadc0cd0150b77ca10856113f74"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:6BYGOUEWWAEEI27ERN5KGXXNZH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"q-exponential family for policy optimization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Han Wang, Haseeb Shah, Lingwei Zhu, Martha White, Yukie Nagai","submitted_at":"2024-08-14T01:01:35Z","abstract_excerpt":"Policy optimization methods benefit from a simple and tractable policy parametrization, usually the Gaussian for continuous action spaces. In this paper, we consider a broader policy family that remains tractable: the $q$-exponential family. This family of policies is flexible, allowing the specification of both heavy-tailed policies ($q>1$) and light-tailed policies ($q<1$). This paper examines the interplay between $q$-exponential policies for several actor-critic algorithms conducted on both online and offline problems. We find that heavy-tailed policies are more effective in general and ca"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.07245","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/2408.07245/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":"2026-07-05T10:04:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sEphBZ3PnrKD/oFhKV3h29yioZC88SOQpqz6Xphky2eBInTPME5crHmzRE/ts8tw9PO/dC/jS083Ft80Vx3AAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T09:31:56.854273Z"},"content_sha256":"44fd97a64c668f12e2f745d10017329f0a6b5e1e2881bc33654723e57f829a2e","schema_version":"1.0","event_id":"sha256:44fd97a64c668f12e2f745d10017329f0a6b5e1e2881bc33654723e57f829a2e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6BYGOUEWWAEEI27ERN5KGXXNZH/bundle.json","state_url":"https://pith.science/pith/6BYGOUEWWAEEI27ERN5KGXXNZH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6BYGOUEWWAEEI27ERN5KGXXNZH/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":"2026-08-07T09:31:56Z","links":{"resolver":"https://pith.science/pith/6BYGOUEWWAEEI27ERN5KGXXNZH","bundle":"https://pith.science/pith/6BYGOUEWWAEEI27ERN5KGXXNZH/bundle.json","state":"https://pith.science/pith/6BYGOUEWWAEEI27ERN5KGXXNZH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6BYGOUEWWAEEI27ERN5KGXXNZH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:6BYGOUEWWAEEI27ERN5KGXXNZH","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":"f7f4f0e039b735e20842c9db93dc63558be96c9e4ead333c5c2c2140c256d531","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-08-14T01:01:35Z","title_canon_sha256":"f097da787f37a785bbe6275d2ded7dfd701e0f0cf40681e97038fcf9862b520e"},"schema_version":"1.0","source":{"id":"2408.07245","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.07245","created_at":"2026-07-05T10:04:57Z"},{"alias_kind":"arxiv_version","alias_value":"2408.07245v3","created_at":"2026-07-05T10:04:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.07245","created_at":"2026-07-05T10:04:57Z"},{"alias_kind":"pith_short_12","alias_value":"6BYGOUEWWAEE","created_at":"2026-07-05T10:04:57Z"},{"alias_kind":"pith_short_16","alias_value":"6BYGOUEWWAEEI27E","created_at":"2026-07-05T10:04:57Z"},{"alias_kind":"pith_short_8","alias_value":"6BYGOUEW","created_at":"2026-07-05T10:04:57Z"}],"graph_snapshots":[{"event_id":"sha256:44fd97a64c668f12e2f745d10017329f0a6b5e1e2881bc33654723e57f829a2e","target":"graph","created_at":"2026-07-05T10:04:57Z","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/2408.07245/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Policy optimization methods benefit from a simple and tractable policy parametrization, usually the Gaussian for continuous action spaces. In this paper, we consider a broader policy family that remains tractable: the $q$-exponential family. This family of policies is flexible, allowing the specification of both heavy-tailed policies ($q>1$) and light-tailed policies ($q<1$). This paper examines the interplay between $q$-exponential policies for several actor-critic algorithms conducted on both online and offline problems. We find that heavy-tailed policies are more effective in general and ca","authors_text":"Han Wang, Haseeb Shah, Lingwei Zhu, Martha White, Yukie Nagai","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-08-14T01:01:35Z","title":"q-exponential family for policy optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.07245","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":"sha256:3caa951f55216f5a89581c8b11731d4dfc580cadc0cd0150b77ca10856113f74","target":"record","created_at":"2026-07-05T10:04:57Z","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":"f7f4f0e039b735e20842c9db93dc63558be96c9e4ead333c5c2c2140c256d531","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-08-14T01:01:35Z","title_canon_sha256":"f097da787f37a785bbe6275d2ded7dfd701e0f0cf40681e97038fcf9862b520e"},"schema_version":"1.0","source":{"id":"2408.07245","kind":"arxiv","version":3}},"canonical_sha256":"f070675096b008446be48b7aa35eedc9ed95649ca87581bfaa764e359664e183","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f070675096b008446be48b7aa35eedc9ed95649ca87581bfaa764e359664e183","first_computed_at":"2026-07-05T10:04:57.667369Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:04:57.667369Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mnOWmUjm/EBYh3c/RSm6IGA//uBaxmqVW+9CT/8PuLGzDawrqY1xjdng7g2f8c8dgxYYOjNEvV0HVf9RJZl5Cw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:04:57.667846Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.07245","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3caa951f55216f5a89581c8b11731d4dfc580cadc0cd0150b77ca10856113f74","sha256:44fd97a64c668f12e2f745d10017329f0a6b5e1e2881bc33654723e57f829a2e"],"state_sha256":"c51fbcc889be1e0bac771a656889528dd3c89f47f3a9da23e1796792d6a268a6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YouW5jhz5N54I52xtIPguCsIrRTAJAvexcniIpeUwKoEFBtzCmuMVpvbnk/xceEPJ/9hHeHuR2JGnct+eLOoBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T09:31:56.860313Z","bundle_sha256":"92e0bfb00c3c0e6c8b5d94403bcdf7f4cd2df38261914cca40459e8f546daf01"}}