{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:WYIIWNO4RYLQHA7FIXOR63UIBY","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":"f20f2ad1407791e518d12f58c1c1c9bbb45c87e640dffdef04077cdb0de9b505","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-08T05:09:32Z","title_canon_sha256":"153b57b70daefce59dfb273566817ac9e56d49b82570195a34308c3f490eb329"},"schema_version":"1.0","source":{"id":"2006.04354","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.04354","created_at":"2026-07-05T01:58:09Z"},{"alias_kind":"arxiv_version","alias_value":"2006.04354v2","created_at":"2026-07-05T01:58:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.04354","created_at":"2026-07-05T01:58:09Z"},{"alias_kind":"pith_short_12","alias_value":"WYIIWNO4RYLQ","created_at":"2026-07-05T01:58:09Z"},{"alias_kind":"pith_short_16","alias_value":"WYIIWNO4RYLQHA7F","created_at":"2026-07-05T01:58:09Z"},{"alias_kind":"pith_short_8","alias_value":"WYIIWNO4","created_at":"2026-07-05T01:58:09Z"}],"graph_snapshots":[{"event_id":"sha256:3ee0218b31e95221be22704429ae4c3cb7e1a1bc82babea1a195afee93e5ae96","target":"graph","created_at":"2026-07-05T01:58:09Z","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/2006.04354/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recently, model-free reinforcement learning has attracted research attention due to its simplicity, memory and computation efficiency, and the flexibility to combine with function approximation. In this paper, we propose Exploration Enhanced Q-learning (EE-QL), a model-free algorithm for infinite-horizon average-reward Markov Decision Processes (MDPs) that achieves regret bound of $O(\\sqrt{T})$ for the general class of weakly communicating MDPs, where $T$ is the number of interactions. EE-QL assumes that an online concentrating approximation of the optimal average reward is available. This is ","authors_text":"Chen-Yu Wei, Haipeng Luo, Mehdi Jafarnia-Jahromi, Rahul Jain","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-08T05:09:32Z","title":"A Model-free Learning Algorithm for Infinite-horizon Average-reward MDPs with Near-optimal Regret"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.04354","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":"sha256:204a7828b81f41754c520df9d5ad1a2a5ddb24188a7d632d9456a8bd780c3eaf","target":"record","created_at":"2026-07-05T01:58:09Z","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":"f20f2ad1407791e518d12f58c1c1c9bbb45c87e640dffdef04077cdb0de9b505","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-08T05:09:32Z","title_canon_sha256":"153b57b70daefce59dfb273566817ac9e56d49b82570195a34308c3f490eb329"},"schema_version":"1.0","source":{"id":"2006.04354","kind":"arxiv","version":2}},"canonical_sha256":"b6108b35dc8e170383e545dd1f6e880e3e74cdbba0d7d3f630824d16c38c87b4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b6108b35dc8e170383e545dd1f6e880e3e74cdbba0d7d3f630824d16c38c87b4","first_computed_at":"2026-07-05T01:58:09.982734Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:58:09.982734Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mS8ndHpdRAjYuQd2/U5e6HVZrC+Vf/BJh106P0tVoNvVor12vQVct1YA3/+9Y3Q/i9J61n/1BPwQQH3WVgq9AA==","signature_status":"signed_v1","signed_at":"2026-07-05T01:58:09.983235Z","signed_message":"canonical_sha256_bytes"},"source_id":"2006.04354","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:204a7828b81f41754c520df9d5ad1a2a5ddb24188a7d632d9456a8bd780c3eaf","sha256:3ee0218b31e95221be22704429ae4c3cb7e1a1bc82babea1a195afee93e5ae96"],"state_sha256":"a9685d12c846579ed4c1e267dc89f2ff148ffc6780320abf8d1a96f447ddf294"}