{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:2RJU4DV3TOXJGLLSCK6EP53V76","short_pith_number":"pith:2RJU4DV3","canonical_record":{"source":{"id":"2411.06069","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-09T05:03:10Z","cross_cats_sorted":["cs.GT","stat.ML"],"title_canon_sha256":"ba5d6ff07cbade86b577d40418343c052ff0a0cf5a00559e27d972a15c392ffe","abstract_canon_sha256":"5a288f3e34183e64fe0a54a69dc1a326ce5875b3a3ee21adc8c21ee733d5d924"},"schema_version":"1.0"},"canonical_sha256":"d4534e0ebb9bae932d7212bc47f775ff92790f55cd9f373d0521c84820085e5d","source":{"kind":"arxiv","id":"2411.06069","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.06069","created_at":"2026-07-05T09:33:16Z"},{"alias_kind":"arxiv_version","alias_value":"2411.06069v1","created_at":"2026-07-05T09:33:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.06069","created_at":"2026-07-05T09:33:16Z"},{"alias_kind":"pith_short_12","alias_value":"2RJU4DV3TOXJ","created_at":"2026-07-05T09:33:16Z"},{"alias_kind":"pith_short_16","alias_value":"2RJU4DV3TOXJGLLS","created_at":"2026-07-05T09:33:16Z"},{"alias_kind":"pith_short_8","alias_value":"2RJU4DV3","created_at":"2026-07-05T09:33:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:2RJU4DV3TOXJGLLSCK6EP53V76","target":"record","payload":{"canonical_record":{"source":{"id":"2411.06069","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-09T05:03:10Z","cross_cats_sorted":["cs.GT","stat.ML"],"title_canon_sha256":"ba5d6ff07cbade86b577d40418343c052ff0a0cf5a00559e27d972a15c392ffe","abstract_canon_sha256":"5a288f3e34183e64fe0a54a69dc1a326ce5875b3a3ee21adc8c21ee733d5d924"},"schema_version":"1.0"},"canonical_sha256":"d4534e0ebb9bae932d7212bc47f775ff92790f55cd9f373d0521c84820085e5d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:33:16.554943Z","signature_b64":"U7E10Rpju4OZAy2nA72sbaE/UyCYDKhIvEsRPvhKgQQ5m50pSG3l27wT8SNdhRr9JG7yQfBXyCJBWAU+R44rCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d4534e0ebb9bae932d7212bc47f775ff92790f55cd9f373d0521c84820085e5d","last_reissued_at":"2026-07-05T09:33:16.554335Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:33:16.554335Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.06069","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":"2026-07-05T09:33:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AhVDPmdU+YCWLKwgeqaHdZlYXJ6p18Wf/RPLJ1V74nMwTv0ex9Sgxva5YdVJlV3h48OkGovVbmLymZPuvXr4AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T05:01:22.002785Z"},"content_sha256":"2f89d0700a4db398f47461083a53828d4b90023b544b76886bcbfcfc09607ddc","schema_version":"1.0","event_id":"sha256:2f89d0700a4db398f47461083a53828d4b90023b544b76886bcbfcfc09607ddc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:2RJU4DV3TOXJGLLSCK6EP53V76","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Model Selection for Average Reward RL with Application to Utility Maximization in Repeated Games","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.GT","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alireza Masoumian, James R. Wright","submitted_at":"2024-11-09T05:03:10Z","abstract_excerpt":"In standard RL, a learner attempts to learn an optimal policy for a Markov Decision Process whose structure (e.g. state space) is known. In online model selection, a learner attempts to learn an optimal policy for an MDP knowing only that it belongs to one of $M >1$ model classes of varying complexity. Recent results have shown that this can be feasibly accomplished in episodic online RL. In this work, we propose $\\mathsf{MRBEAR}$, an online model selection algorithm for the average reward RL setting. The regret of the algorithm is in $\\tilde O(M C_{m^*}^2 \\mathsf{B}_{m^*}(T,\\delta))$ where $C"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.06069","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/2411.06069/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":"2026-07-05T09:33:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"s8PzzOeL1w05G6k9OWzi9uzvgMFaEskvPcr5f+wsU1XChl5NbQZWT2G64ieRrnIbMZCgacVhYxuAQWUgn5qKAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T05:01:22.003153Z"},"content_sha256":"f78a58e1c7780c7aaab925a4180fd11fca3021d93052f725d06a0c83916502f1","schema_version":"1.0","event_id":"sha256:f78a58e1c7780c7aaab925a4180fd11fca3021d93052f725d06a0c83916502f1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2RJU4DV3TOXJGLLSCK6EP53V76/bundle.json","state_url":"https://pith.science/pith/2RJU4DV3TOXJGLLSCK6EP53V76/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2RJU4DV3TOXJGLLSCK6EP53V76/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":"2026-07-09T05:01:22Z","links":{"resolver":"https://pith.science/pith/2RJU4DV3TOXJGLLSCK6EP53V76","bundle":"https://pith.science/pith/2RJU4DV3TOXJGLLSCK6EP53V76/bundle.json","state":"https://pith.science/pith/2RJU4DV3TOXJGLLSCK6EP53V76/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2RJU4DV3TOXJGLLSCK6EP53V76/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:2RJU4DV3TOXJGLLSCK6EP53V76","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":"5a288f3e34183e64fe0a54a69dc1a326ce5875b3a3ee21adc8c21ee733d5d924","cross_cats_sorted":["cs.GT","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-09T05:03:10Z","title_canon_sha256":"ba5d6ff07cbade86b577d40418343c052ff0a0cf5a00559e27d972a15c392ffe"},"schema_version":"1.0","source":{"id":"2411.06069","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.06069","created_at":"2026-07-05T09:33:16Z"},{"alias_kind":"arxiv_version","alias_value":"2411.06069v1","created_at":"2026-07-05T09:33:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.06069","created_at":"2026-07-05T09:33:16Z"},{"alias_kind":"pith_short_12","alias_value":"2RJU4DV3TOXJ","created_at":"2026-07-05T09:33:16Z"},{"alias_kind":"pith_short_16","alias_value":"2RJU4DV3TOXJGLLS","created_at":"2026-07-05T09:33:16Z"},{"alias_kind":"pith_short_8","alias_value":"2RJU4DV3","created_at":"2026-07-05T09:33:16Z"}],"graph_snapshots":[{"event_id":"sha256:f78a58e1c7780c7aaab925a4180fd11fca3021d93052f725d06a0c83916502f1","target":"graph","created_at":"2026-07-05T09:33:16Z","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/2411.06069/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In standard RL, a learner attempts to learn an optimal policy for a Markov Decision Process whose structure (e.g. state space) is known. In online model selection, a learner attempts to learn an optimal policy for an MDP knowing only that it belongs to one of $M >1$ model classes of varying complexity. Recent results have shown that this can be feasibly accomplished in episodic online RL. In this work, we propose $\\mathsf{MRBEAR}$, an online model selection algorithm for the average reward RL setting. The regret of the algorithm is in $\\tilde O(M C_{m^*}^2 \\mathsf{B}_{m^*}(T,\\delta))$ where $C","authors_text":"Alireza Masoumian, James R. Wright","cross_cats":["cs.GT","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-09T05:03:10Z","title":"Model Selection for Average Reward RL with Application to Utility Maximization in Repeated Games"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.06069","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":"sha256:2f89d0700a4db398f47461083a53828d4b90023b544b76886bcbfcfc09607ddc","target":"record","created_at":"2026-07-05T09:33:16Z","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":"5a288f3e34183e64fe0a54a69dc1a326ce5875b3a3ee21adc8c21ee733d5d924","cross_cats_sorted":["cs.GT","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-09T05:03:10Z","title_canon_sha256":"ba5d6ff07cbade86b577d40418343c052ff0a0cf5a00559e27d972a15c392ffe"},"schema_version":"1.0","source":{"id":"2411.06069","kind":"arxiv","version":1}},"canonical_sha256":"d4534e0ebb9bae932d7212bc47f775ff92790f55cd9f373d0521c84820085e5d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d4534e0ebb9bae932d7212bc47f775ff92790f55cd9f373d0521c84820085e5d","first_computed_at":"2026-07-05T09:33:16.554335Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:33:16.554335Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"U7E10Rpju4OZAy2nA72sbaE/UyCYDKhIvEsRPvhKgQQ5m50pSG3l27wT8SNdhRr9JG7yQfBXyCJBWAU+R44rCw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:33:16.554943Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.06069","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2f89d0700a4db398f47461083a53828d4b90023b544b76886bcbfcfc09607ddc","sha256:f78a58e1c7780c7aaab925a4180fd11fca3021d93052f725d06a0c83916502f1"],"state_sha256":"db54ea9b466adb0d3b79321581df8ccf9cf51c9a17b9387f00d6e1f6b26ecd73"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NoeaZXxilZgE6zyTKmg3HpWVx/jiNuSoX5D/iGLgybdv6T3pqYJbftiLvHZyMZX7v/IDUbnDR6u46L93oXKjDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-09T05:01:22.005129Z","bundle_sha256":"d4d291ed0cbbe309bca23b30d8805c5348d7e07fa87e52365503840c30382ab1"}}