{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2014:B67GQFU3GW53YM6PDQZW2NA5AU","short_pith_number":"pith:B67GQFU3","canonical_record":{"source":{"id":"1412.0180","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2014-11-30T06:06:23Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"8b9709a97c82e99fa4bdd9a9fdcd1b36f398881760bfc988966673e7932672a9","abstract_canon_sha256":"5ee211976ff010d2e5df88a6a1d9b656564b9fb76fc5801140743f24d5114b5a"},"schema_version":"1.0"},"canonical_sha256":"0fbe68169b35bbbc33cf1c336d341d053090bb0e7dd63a9a02722f961f584df7","source":{"kind":"arxiv","id":"1412.0180","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2014:B67GQFU3GW53YM6PDQZW2NA5AU","target":"record","payload":{"canonical_record":{"source":{"id":"1412.0180","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2014-11-30T06:06:23Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"8b9709a97c82e99fa4bdd9a9fdcd1b36f398881760bfc988966673e7932672a9","abstract_canon_sha256":"5ee211976ff010d2e5df88a6a1d9b656564b9fb76fc5801140743f24d5114b5a"},"schema_version":"1.0"},"canonical_sha256":"0fbe68169b35bbbc33cf1c336d341d053090bb0e7dd63a9a02722f961f584df7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:55:10.119406Z","signature_b64":"029u4QTOT5iHDUJ2Tfzw530NYVnxKnZgXYOV9Gvglj+gsuOB6HhMOxckOdYN7fTYg/HDvHOIRv+phdDsU99IBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0fbe68169b35bbbc33cf1c336d341d053090bb0e7dd63a9a02722f961f584df7","last_reissued_at":"2026-05-17T23:55:10.118954Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:55:10.118954Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1412.0180","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:55:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QCbFFBXr4fk15TXMzYlYmEk9l3GaNn7q+DKy6PJV8rplDgZuKmdXaGmCkSbP+m8fNQpNl9Eb+SMczSuP0FuXDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T18:02:01.256638Z"},"content_sha256":"16bca1c1c002129617e9ec93a7b6fabdefbffd6916ed13143eeb273f09def647","schema_version":"1.0","event_id":"sha256:16bca1c1c002129617e9ec93a7b6fabdefbffd6916ed13143eeb273f09def647"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2014:B67GQFU3GW53YM6PDQZW2NA5AU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Empirical Q-Value Iteration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"math.OC","authors_text":"Dileep Kalathil, Rahul Jain, Vivek S. Borkar","submitted_at":"2014-11-30T06:06:23Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1412.0180","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"2026-05-17T23:55:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GtmR2GMJakWjGf9EVbIoxPN8sEG/1GIJv2sRqEzTMednOFY4DKkSS1rMpQypF8VjidJwMUn/fBB5BPZHR81wAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T18:02:01.257507Z"},"content_sha256":"ed6e907b4f701536c8d307393c9b8073b966700680f3c6517db48e33a780787b","schema_version":"1.0","event_id":"sha256:ed6e907b4f701536c8d307393c9b8073b966700680f3c6517db48e33a780787b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/B67GQFU3GW53YM6PDQZW2NA5AU/bundle.json","state_url":"https://pith.science/pith/B67GQFU3GW53YM6PDQZW2NA5AU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/B67GQFU3GW53YM6PDQZW2NA5AU/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":"2026-05-25T18:02:01Z","links":{"resolver":"https://pith.science/pith/B67GQFU3GW53YM6PDQZW2NA5AU","bundle":"https://pith.science/pith/B67GQFU3GW53YM6PDQZW2NA5AU/bundle.json","state":"https://pith.science/pith/B67GQFU3GW53YM6PDQZW2NA5AU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/B67GQFU3GW53YM6PDQZW2NA5AU/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xd1TXbHmXr1riuoC0VeNZzI1Ljkr/lD273qxsC47hlegu4zgp2DT2HeLzeHxyHU6/EMc83FapxcNp8AkurI2Ag==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T18:02:01.262184Z","bundle_sha256":"99ddffee231b7a2cf055111b4646365e90a7c0e68beffcd434f1a370a7975b30"}}