{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:TTU7UBGAII5GRFAGTHOSREWKKG","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":"57529924e1ad7a717f9efa4dec0ec36f71bec205b2749d112222567ff686dc3a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-13T20:12:09Z","title_canon_sha256":"860810fff8b36b1c44ac8b147a54dd488c2b8e1c2bd97a1992fd6f3fe8a9efad"},"schema_version":"1.0","source":{"id":"2406.09563","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.09563","created_at":"2026-07-05T09:50:48Z"},{"alias_kind":"arxiv_version","alias_value":"2406.09563v2","created_at":"2026-07-05T09:50:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.09563","created_at":"2026-07-05T09:50:48Z"},{"alias_kind":"pith_short_12","alias_value":"TTU7UBGAII5G","created_at":"2026-07-05T09:50:48Z"},{"alias_kind":"pith_short_16","alias_value":"TTU7UBGAII5GRFAG","created_at":"2026-07-05T09:50:48Z"},{"alias_kind":"pith_short_8","alias_value":"TTU7UBGA","created_at":"2026-07-05T09:50:48Z"}],"graph_snapshots":[{"event_id":"sha256:5f4e1fd83d15a1a27d31526272e403aa4992b933c58bc19e3b9949ab0ad97e0d","target":"graph","created_at":"2026-07-05T09:50:48Z","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/2406.09563/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we present the $\\texttt{e-COP}$ algorithm, the first policy optimization algorithm for constrained Reinforcement Learning (RL) in episodic (finite horizon) settings. Such formulations are applicable when there are separate sets of optimization criteria and constraints on a system's behavior. We approach this problem by first establishing a policy difference lemma for the episodic setting, which provides the theoretical foundation for the algorithm. Then, we propose to combine a set of established and novel solution ideas to yield the $\\texttt{e-COP}$ algorithm that is easy to im","authors_text":"Akhil Agnihotri, Deepak Ramachandran, Rahul Jain, Sahil Singla","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-13T20:12:09Z","title":"e-COP : Episodic Constrained Optimization of Policies"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.09563","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":"sha256:9dbdc4b2a46dea7185cd4feb060b98d586713160361fc4436a93aa6af5d83d17","target":"record","created_at":"2026-07-05T09:50:48Z","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":"57529924e1ad7a717f9efa4dec0ec36f71bec205b2749d112222567ff686dc3a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-13T20:12:09Z","title_canon_sha256":"860810fff8b36b1c44ac8b147a54dd488c2b8e1c2bd97a1992fd6f3fe8a9efad"},"schema_version":"1.0","source":{"id":"2406.09563","kind":"arxiv","version":2}},"canonical_sha256":"9ce9fa04c0423a68940699dd2892ca51afdacd52c0faceecb9ad65f3da7dacc2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9ce9fa04c0423a68940699dd2892ca51afdacd52c0faceecb9ad65f3da7dacc2","first_computed_at":"2026-07-05T09:50:48.532621Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:50:48.532621Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UKHp6npRCPz2xFP8k8ODmKATlIzhCBNn+AQD3o+74vnmEKvOhCjovb2IytbSLYFO9K7oyxPVtk1cS3Vf2GbVDA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:50:48.533212Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.09563","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9dbdc4b2a46dea7185cd4feb060b98d586713160361fc4436a93aa6af5d83d17","sha256:5f4e1fd83d15a1a27d31526272e403aa4992b933c58bc19e3b9949ab0ad97e0d"],"state_sha256":"c3f4f01a3b9143c776eb2529820b51def04033e173172344ff6b5b678b1924fc"}