{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:44KTV2RRA3GGMWDT2T2WGIMVIE","short_pith_number":"pith:44KTV2RR","canonical_record":{"source":{"id":"2209.15141","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-09-30T00:07:48Z","cross_cats_sorted":[],"title_canon_sha256":"47a8148a8407b967a44c9b39aee272f04986f1fe72d5f9da9a0ac42b0abe4cdc","abstract_canon_sha256":"e0e093adf2ea5afaa44098a1296dd4b4f945ea84d7a3fd3b24fe37b990238d8b"},"schema_version":"1.0"},"canonical_sha256":"e7153aea3106cc665873d4f5632195413832e780b85a1c6ef5aba00d3eec2d82","source":{"kind":"arxiv","id":"2209.15141","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2209.15141","created_at":"2026-07-05T05:13:38Z"},{"alias_kind":"arxiv_version","alias_value":"2209.15141v2","created_at":"2026-07-05T05:13:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.15141","created_at":"2026-07-05T05:13:38Z"},{"alias_kind":"pith_short_12","alias_value":"44KTV2RRA3GG","created_at":"2026-07-05T05:13:38Z"},{"alias_kind":"pith_short_16","alias_value":"44KTV2RRA3GGMWDT","created_at":"2026-07-05T05:13:38Z"},{"alias_kind":"pith_short_8","alias_value":"44KTV2RR","created_at":"2026-07-05T05:13:38Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:44KTV2RRA3GGMWDT2T2WGIMVIE","target":"record","payload":{"canonical_record":{"source":{"id":"2209.15141","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-09-30T00:07:48Z","cross_cats_sorted":[],"title_canon_sha256":"47a8148a8407b967a44c9b39aee272f04986f1fe72d5f9da9a0ac42b0abe4cdc","abstract_canon_sha256":"e0e093adf2ea5afaa44098a1296dd4b4f945ea84d7a3fd3b24fe37b990238d8b"},"schema_version":"1.0"},"canonical_sha256":"e7153aea3106cc665873d4f5632195413832e780b85a1c6ef5aba00d3eec2d82","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:13:38.158342Z","signature_b64":"EG6Wv3cxu7YpwdU0fRPm/dvN8mqdxwW+XTEay8Y+WTaEZmD0epc2pFC+gdMztTqMJTmzhsYeguQ/7KpcHQeIBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e7153aea3106cc665873d4f5632195413832e780b85a1c6ef5aba00d3eec2d82","last_reissued_at":"2026-07-05T05:13:38.157867Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:13:38.157867Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2209.15141","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":"2026-07-05T05:13:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gziG6uYQA7b2FYigjeLzQrbzhTtSAZJhyLUPaVZfi8GTXHmWUFlqQjSLz+2VFxJQwVT4laGUQD2wBwRP4DXPCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T18:31:50.943906Z"},"content_sha256":"8c437b3cf0b3a68b93350a30f9598c067bb6f99167a6ede660953d9c402d748f","schema_version":"1.0","event_id":"sha256:8c437b3cf0b3a68b93350a30f9598c067bb6f99167a6ede660953d9c402d748f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:44KTV2RRA3GGMWDT2T2WGIMVIE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"On Convergence of Average-Reward Off-Policy Control Algorithms in Weakly Communicating MDPs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Richard S. Sutton, Yi Wan","submitted_at":"2022-09-30T00:07:48Z","abstract_excerpt":"We show two average-reward off-policy control algorithms, Differential Q-learning (Wan, Naik, & Sutton 2021a) and RVI Q-learning (Abounadi Bertsekas & Borkar 2001), converge in weakly communicating MDPs. Weakly communicating MDPs are the most general MDPs that can be solved by a learning algorithm with a single stream of experience. The original convergence proofs of the two algorithms require that the solution set of the average-reward optimality equation only has one degree of freedom, which is not necessarily true for weakly communicating MDPs. To the best of our knowledge, our results are "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.15141","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/2209.15141/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":"2026-07-05T05:13:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sE9ThHDbW+qZn5s8mFSfgBAmv/eR+os7sMA8qrjwWZJGjo/En/cK0wg4J8MddZNzPc8nx/Ou9TovCfmoCOL4DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T18:31:50.944463Z"},"content_sha256":"53565e862a1f19e2a326e4b2ca899748ac7c28b546f59b7b26d52255e488ce69","schema_version":"1.0","event_id":"sha256:53565e862a1f19e2a326e4b2ca899748ac7c28b546f59b7b26d52255e488ce69"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/44KTV2RRA3GGMWDT2T2WGIMVIE/bundle.json","state_url":"https://pith.science/pith/44KTV2RRA3GGMWDT2T2WGIMVIE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/44KTV2RRA3GGMWDT2T2WGIMVIE/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":"2026-08-11T18:31:50Z","links":{"resolver":"https://pith.science/pith/44KTV2RRA3GGMWDT2T2WGIMVIE","bundle":"https://pith.science/pith/44KTV2RRA3GGMWDT2T2WGIMVIE/bundle.json","state":"https://pith.science/pith/44KTV2RRA3GGMWDT2T2WGIMVIE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/44KTV2RRA3GGMWDT2T2WGIMVIE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:44KTV2RRA3GGMWDT2T2WGIMVIE","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":"e0e093adf2ea5afaa44098a1296dd4b4f945ea84d7a3fd3b24fe37b990238d8b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-09-30T00:07:48Z","title_canon_sha256":"47a8148a8407b967a44c9b39aee272f04986f1fe72d5f9da9a0ac42b0abe4cdc"},"schema_version":"1.0","source":{"id":"2209.15141","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2209.15141","created_at":"2026-07-05T05:13:38Z"},{"alias_kind":"arxiv_version","alias_value":"2209.15141v2","created_at":"2026-07-05T05:13:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.15141","created_at":"2026-07-05T05:13:38Z"},{"alias_kind":"pith_short_12","alias_value":"44KTV2RRA3GG","created_at":"2026-07-05T05:13:38Z"},{"alias_kind":"pith_short_16","alias_value":"44KTV2RRA3GGMWDT","created_at":"2026-07-05T05:13:38Z"},{"alias_kind":"pith_short_8","alias_value":"44KTV2RR","created_at":"2026-07-05T05:13:38Z"}],"graph_snapshots":[{"event_id":"sha256:53565e862a1f19e2a326e4b2ca899748ac7c28b546f59b7b26d52255e488ce69","target":"graph","created_at":"2026-07-05T05:13:38Z","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/2209.15141/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We show two average-reward off-policy control algorithms, Differential Q-learning (Wan, Naik, & Sutton 2021a) and RVI Q-learning (Abounadi Bertsekas & Borkar 2001), converge in weakly communicating MDPs. Weakly communicating MDPs are the most general MDPs that can be solved by a learning algorithm with a single stream of experience. The original convergence proofs of the two algorithms require that the solution set of the average-reward optimality equation only has one degree of freedom, which is not necessarily true for weakly communicating MDPs. To the best of our knowledge, our results are ","authors_text":"Richard S. Sutton, Yi Wan","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-09-30T00:07:48Z","title":"On Convergence of Average-Reward Off-Policy Control Algorithms in Weakly Communicating MDPs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.15141","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":"sha256:8c437b3cf0b3a68b93350a30f9598c067bb6f99167a6ede660953d9c402d748f","target":"record","created_at":"2026-07-05T05:13:38Z","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":"e0e093adf2ea5afaa44098a1296dd4b4f945ea84d7a3fd3b24fe37b990238d8b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-09-30T00:07:48Z","title_canon_sha256":"47a8148a8407b967a44c9b39aee272f04986f1fe72d5f9da9a0ac42b0abe4cdc"},"schema_version":"1.0","source":{"id":"2209.15141","kind":"arxiv","version":2}},"canonical_sha256":"e7153aea3106cc665873d4f5632195413832e780b85a1c6ef5aba00d3eec2d82","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e7153aea3106cc665873d4f5632195413832e780b85a1c6ef5aba00d3eec2d82","first_computed_at":"2026-07-05T05:13:38.157867Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:13:38.157867Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"EG6Wv3cxu7YpwdU0fRPm/dvN8mqdxwW+XTEay8Y+WTaEZmD0epc2pFC+gdMztTqMJTmzhsYeguQ/7KpcHQeIBg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:13:38.158342Z","signed_message":"canonical_sha256_bytes"},"source_id":"2209.15141","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8c437b3cf0b3a68b93350a30f9598c067bb6f99167a6ede660953d9c402d748f","sha256:53565e862a1f19e2a326e4b2ca899748ac7c28b546f59b7b26d52255e488ce69"],"state_sha256":"97e7e4d9ca0e8b1b9c5674e8408d6cc774792f08e86d795cef746b86ccc14512"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YRLlqk/IfJKv93un2D/QY0owCpSAzE7uFPk28k5NVAtDNHGLi7K0Tc92VTTOzL2QMBbVGGd0cCYTicTP26N8Aw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T18:31:50.950123Z","bundle_sha256":"56957208441c50baa5f9b766fcc63d3a0e02271479b1156e4bc34325acd7b356"}}