{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2014:B67GQFU3GW53YM6PDQZW2NA5AU","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":"5ee211976ff010d2e5df88a6a1d9b656564b9fb76fc5801140743f24d5114b5a","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2014-11-30T06:06:23Z","title_canon_sha256":"8b9709a97c82e99fa4bdd9a9fdcd1b36f398881760bfc988966673e7932672a9"},"schema_version":"1.0","source":{"id":"1412.0180","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1412.0180","created_at":"2026-05-17T23:55:10Z"},{"alias_kind":"arxiv_version","alias_value":"1412.0180v3","created_at":"2026-05-17T23:55:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1412.0180","created_at":"2026-05-17T23:55:10Z"},{"alias_kind":"pith_short_12","alias_value":"B67GQFU3GW53","created_at":"2026-05-18T12:28:22Z"},{"alias_kind":"pith_short_16","alias_value":"B67GQFU3GW53YM6P","created_at":"2026-05-18T12:28:22Z"},{"alias_kind":"pith_short_8","alias_value":"B67GQFU3","created_at":"2026-05-18T12:28:22Z"}],"graph_snapshots":[{"event_id":"sha256:ed6e907b4f701536c8d307393c9b8073b966700680f3c6517db48e33a780787b","target":"graph","created_at":"2026-05-17T23:55:10Z","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"},"paper":{"abstract_excerpt":"We propose a new simple and natural algorithm for learning the optimal Q-value function of a discounted-cost Markov Decision Process (MDP) when the transition kernels are unknown. Unlike the classical learning algorithms for MDPs, such as Q-learning and actor-critic algorithms, this algorithm doesn't depend on a stochastic approximation-based method. We show that our algorithm, which we call the empirical Q-value iteration (EQVI) algorithm, converges to the optimal Q-value function. We also give a rate of convergence or a non-asymptotic sample complexity bound, and also show that an asynchrono","authors_text":"Dileep Kalathil, Rahul Jain, Vivek S. Borkar","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2014-11-30T06:06:23Z","title":"Empirical Q-Value Iteration"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1412.0180","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":"sha256:16bca1c1c002129617e9ec93a7b6fabdefbffd6916ed13143eeb273f09def647","target":"record","created_at":"2026-05-17T23:55:10Z","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":"5ee211976ff010d2e5df88a6a1d9b656564b9fb76fc5801140743f24d5114b5a","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2014-11-30T06:06:23Z","title_canon_sha256":"8b9709a97c82e99fa4bdd9a9fdcd1b36f398881760bfc988966673e7932672a9"},"schema_version":"1.0","source":{"id":"1412.0180","kind":"arxiv","version":3}},"canonical_sha256":"0fbe68169b35bbbc33cf1c336d341d053090bb0e7dd63a9a02722f961f584df7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0fbe68169b35bbbc33cf1c336d341d053090bb0e7dd63a9a02722f961f584df7","first_computed_at":"2026-05-17T23:55:10.118954Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:55:10.118954Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"029u4QTOT5iHDUJ2Tfzw530NYVnxKnZgXYOV9Gvglj+gsuOB6HhMOxckOdYN7fTYg/HDvHOIRv+phdDsU99IBA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:55:10.119406Z","signed_message":"canonical_sha256_bytes"},"source_id":"1412.0180","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:16bca1c1c002129617e9ec93a7b6fabdefbffd6916ed13143eeb273f09def647","sha256:ed6e907b4f701536c8d307393c9b8073b966700680f3c6517db48e33a780787b"],"state_sha256":"6c03ae1880d0371c929ce5cdb7f210961ae01d2697f6f455ef05b3354d6b7b19"}