{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:EO6PWDQQB5J77OQDNS5SFBWYLW","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":"931881afa395cc51ac9429deeafb455836482cfbad810a752089907f845c8d47","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SY","submitted_at":"2016-09-29T18:12:58Z","title_canon_sha256":"f1f38d051708da7d12b7dd1e750d176974b72c0c07808a81fcd17799c185d027"},"schema_version":"1.0","source":{"id":"1609.09449","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1609.09449","created_at":"2026-05-18T01:03:37Z"},{"alias_kind":"arxiv_version","alias_value":"1609.09449v1","created_at":"2026-05-18T01:03:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1609.09449","created_at":"2026-05-18T01:03:37Z"},{"alias_kind":"pith_short_12","alias_value":"EO6PWDQQB5J7","created_at":"2026-05-18T12:30:12Z"},{"alias_kind":"pith_short_16","alias_value":"EO6PWDQQB5J77OQD","created_at":"2026-05-18T12:30:12Z"},{"alias_kind":"pith_short_8","alias_value":"EO6PWDQQ","created_at":"2026-05-18T12:30:12Z"}],"graph_snapshots":[{"event_id":"sha256:1c04673f3c12d20ea4623db0ce4b84c0746e4befcf87992e4d4f5f2e1f156f78","target":"graph","created_at":"2026-05-18T01:03:37Z","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":"In this paper, we provide a new algorithm for the problem of prediction in Reinforcement Learning, \\emph{i.e.}, estimating the Value Function of a Markov Reward Process (MRP) using the linear function approximation architecture, with memory and computation costs scaling quadratically in the size of the feature set. The algorithm is a multi-timescale variant of the very popular Cross Entropy (CE) method which is a model based search method to find the global optimum of a real-valued function. This is the first time a model based search method is used for the prediction problem. The application ","authors_text":"Ajin George Joseph, Shalabh Bhatnagar","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SY","submitted_at":"2016-09-29T18:12:58Z","title":"A Cross Entropy based Stochastic Approximation Algorithm for Reinforcement Learning with Linear Function Approximation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1609.09449","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:e19128ad6d0d1eef3d84f6bef02aaa0cc3acee3958dae64687f3848430e3b7c8","target":"record","created_at":"2026-05-18T01:03:37Z","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":"931881afa395cc51ac9429deeafb455836482cfbad810a752089907f845c8d47","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SY","submitted_at":"2016-09-29T18:12:58Z","title_canon_sha256":"f1f38d051708da7d12b7dd1e750d176974b72c0c07808a81fcd17799c185d027"},"schema_version":"1.0","source":{"id":"1609.09449","kind":"arxiv","version":1}},"canonical_sha256":"23bcfb0e100f53ffba036cbb2286d85dae65574ad642f181ebed2ed48fcd1574","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"23bcfb0e100f53ffba036cbb2286d85dae65574ad642f181ebed2ed48fcd1574","first_computed_at":"2026-05-18T01:03:37.866738Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:03:37.866738Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cMteWcG2QGtPklR/3jWXyRt3cJWWunbUyb1TCioAcfkJDPKGFJlLSCBof8LhT8jFNjyZ5pfU50qW4dslUMVoDg==","signature_status":"signed_v1","signed_at":"2026-05-18T01:03:37.867196Z","signed_message":"canonical_sha256_bytes"},"source_id":"1609.09449","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e19128ad6d0d1eef3d84f6bef02aaa0cc3acee3958dae64687f3848430e3b7c8","sha256:1c04673f3c12d20ea4623db0ce4b84c0746e4befcf87992e4d4f5f2e1f156f78"],"state_sha256":"44f2e2430b07451c6566b3e7fb7d7e05f4ee34024405c8f370dbbde691d1e825"}