{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2013:R2OB7L42PXNPG5YR6IA3UJPNNA","short_pith_number":"pith:R2OB7L42","canonical_record":{"source":{"id":"1309.6868","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2013-09-26T12:51:47Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"cddfb8e929fdc5e04baeed7a5caf4f84f7afebc38925affa26c8c1fd1366085f","abstract_canon_sha256":"3dc7e2fce3ebea39de031dd4f0c614374d7b42716f08326adfab0ce7766394ba"},"schema_version":"1.0"},"canonical_sha256":"8e9c1faf9a7ddaf37711f201ba25ed681d2e4605fb3d4d7da3345904ec7ca1c3","source":{"kind":"arxiv","id":"1309.6868","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1309.6868","created_at":"2026-05-18T03:12:09Z"},{"alias_kind":"arxiv_version","alias_value":"1309.6868v1","created_at":"2026-05-18T03:12:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1309.6868","created_at":"2026-05-18T03:12:09Z"},{"alias_kind":"pith_short_12","alias_value":"R2OB7L42PXNP","created_at":"2026-05-18T12:27:57Z"},{"alias_kind":"pith_short_16","alias_value":"R2OB7L42PXNPG5YR","created_at":"2026-05-18T12:27:57Z"},{"alias_kind":"pith_short_8","alias_value":"R2OB7L42","created_at":"2026-05-18T12:27:57Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2013:R2OB7L42PXNPG5YR6IA3UJPNNA","target":"record","payload":{"canonical_record":{"source":{"id":"1309.6868","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2013-09-26T12:51:47Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"cddfb8e929fdc5e04baeed7a5caf4f84f7afebc38925affa26c8c1fd1366085f","abstract_canon_sha256":"3dc7e2fce3ebea39de031dd4f0c614374d7b42716f08326adfab0ce7766394ba"},"schema_version":"1.0"},"canonical_sha256":"8e9c1faf9a7ddaf37711f201ba25ed681d2e4605fb3d4d7da3345904ec7ca1c3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:12:09.952891Z","signature_b64":"/dcu5qJuaFOGEnUaOzER/0k2CepsbXCYD+IcDsCANxW2/Xh5dYJhaFUcE/ki6yqZlfYE/Spol8+eH4TNkn7jAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8e9c1faf9a7ddaf37711f201ba25ed681d2e4605fb3d4d7da3345904ec7ca1c3","last_reissued_at":"2026-05-18T03:12:09.952346Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:12:09.952346Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1309.6868","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":"2026-05-18T03:12:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6zxd1mdlrJ2CZUSQboxAQiiGEODW1WAbcaFfrHNe6A5OJkjChBzlgf0sU8iPekdsfV/uUTIA15UP9vQjf0FYAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T12:10:31.531751Z"},"content_sha256":"838e9fa9ea03c4ab2fdc1f9e9bba61cab62795df22fa4a4c5ad37160f8a92714","schema_version":"1.0","event_id":"sha256:838e9fa9ea03c4ab2fdc1f9e9bba61cab62795df22fa4a4c5ad37160f8a92714"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2013:R2OB7L42PXNPG5YR6IA3UJPNNA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Approximate Kalman Filter Q-Learning for Continuous State-Space MDPs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Charles Tripp, Ross D. Shachter","submitted_at":"2013-09-26T12:51:47Z","abstract_excerpt":"We seek to learn an effective policy for a Markov Decision Process (MDP) with continuous states via Q-Learning. Given a set of basis functions over state action pairs we search for a corresponding set of linear weights that minimizes the mean Bellman residual. Our algorithm uses a Kalman filter model to estimate those weights and we have developed a simpler approximate Kalman filter model that outperforms the current state of the art projected TD-Learning methods on several standard benchmark problems."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1309.6868","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":""},"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":"2026-05-18T03:12:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wby+c3TAlYMygBaFUtq7TdbVDhRx05KhOCRtS7xF3jZ3tK+HN+IDuJyWzX0uC6JZwkuPeYKsXZNzpVY/odsCAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T12:10:31.532099Z"},"content_sha256":"2d075387f0240f360d9ff363166c1fbf49161a9f20fba0703f30ee9db666f0ed","schema_version":"1.0","event_id":"sha256:2d075387f0240f360d9ff363166c1fbf49161a9f20fba0703f30ee9db666f0ed"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/R2OB7L42PXNPG5YR6IA3UJPNNA/bundle.json","state_url":"https://pith.science/pith/R2OB7L42PXNPG5YR6IA3UJPNNA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/R2OB7L42PXNPG5YR6IA3UJPNNA/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":"2026-06-02T12:10:31Z","links":{"resolver":"https://pith.science/pith/R2OB7L42PXNPG5YR6IA3UJPNNA","bundle":"https://pith.science/pith/R2OB7L42PXNPG5YR6IA3UJPNNA/bundle.json","state":"https://pith.science/pith/R2OB7L42PXNPG5YR6IA3UJPNNA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/R2OB7L42PXNPG5YR6IA3UJPNNA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2013:R2OB7L42PXNPG5YR6IA3UJPNNA","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":"3dc7e2fce3ebea39de031dd4f0c614374d7b42716f08326adfab0ce7766394ba","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2013-09-26T12:51:47Z","title_canon_sha256":"cddfb8e929fdc5e04baeed7a5caf4f84f7afebc38925affa26c8c1fd1366085f"},"schema_version":"1.0","source":{"id":"1309.6868","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1309.6868","created_at":"2026-05-18T03:12:09Z"},{"alias_kind":"arxiv_version","alias_value":"1309.6868v1","created_at":"2026-05-18T03:12:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1309.6868","created_at":"2026-05-18T03:12:09Z"},{"alias_kind":"pith_short_12","alias_value":"R2OB7L42PXNP","created_at":"2026-05-18T12:27:57Z"},{"alias_kind":"pith_short_16","alias_value":"R2OB7L42PXNPG5YR","created_at":"2026-05-18T12:27:57Z"},{"alias_kind":"pith_short_8","alias_value":"R2OB7L42","created_at":"2026-05-18T12:27:57Z"}],"graph_snapshots":[{"event_id":"sha256:2d075387f0240f360d9ff363166c1fbf49161a9f20fba0703f30ee9db666f0ed","target":"graph","created_at":"2026-05-18T03:12:09Z","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"},"paper":{"abstract_excerpt":"We seek to learn an effective policy for a Markov Decision Process (MDP) with continuous states via Q-Learning. Given a set of basis functions over state action pairs we search for a corresponding set of linear weights that minimizes the mean Bellman residual. Our algorithm uses a Kalman filter model to estimate those weights and we have developed a simpler approximate Kalman filter model that outperforms the current state of the art projected TD-Learning methods on several standard benchmark problems.","authors_text":"Charles Tripp, Ross D. Shachter","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2013-09-26T12:51:47Z","title":"Approximate Kalman Filter Q-Learning for Continuous State-Space MDPs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1309.6868","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":"sha256:838e9fa9ea03c4ab2fdc1f9e9bba61cab62795df22fa4a4c5ad37160f8a92714","target":"record","created_at":"2026-05-18T03:12:09Z","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":"3dc7e2fce3ebea39de031dd4f0c614374d7b42716f08326adfab0ce7766394ba","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2013-09-26T12:51:47Z","title_canon_sha256":"cddfb8e929fdc5e04baeed7a5caf4f84f7afebc38925affa26c8c1fd1366085f"},"schema_version":"1.0","source":{"id":"1309.6868","kind":"arxiv","version":1}},"canonical_sha256":"8e9c1faf9a7ddaf37711f201ba25ed681d2e4605fb3d4d7da3345904ec7ca1c3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8e9c1faf9a7ddaf37711f201ba25ed681d2e4605fb3d4d7da3345904ec7ca1c3","first_computed_at":"2026-05-18T03:12:09.952346Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:12:09.952346Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/dcu5qJuaFOGEnUaOzER/0k2CepsbXCYD+IcDsCANxW2/Xh5dYJhaFUcE/ki6yqZlfYE/Spol8+eH4TNkn7jAQ==","signature_status":"signed_v1","signed_at":"2026-05-18T03:12:09.952891Z","signed_message":"canonical_sha256_bytes"},"source_id":"1309.6868","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:838e9fa9ea03c4ab2fdc1f9e9bba61cab62795df22fa4a4c5ad37160f8a92714","sha256:2d075387f0240f360d9ff363166c1fbf49161a9f20fba0703f30ee9db666f0ed"],"state_sha256":"8239fa243c1833b262708f10cd720b82a372da4bedd31472311486f6c29490e9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eu73u80+IuUYZEke/mznrBelsEUCIVqk5FdtOaLzf8lV5M4rnGjtg8GwOlEEysezIeTHljl265nGcdct3XLnBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-02T12:10:31.534021Z","bundle_sha256":"39cea96f5f9aa6cfe7acbbf93c6df538d30c6c732d1b70113c027b32a7934c75"}}