{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:XI4JAU7VVILJ42UL4C2HNYJMQI","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":"98b360510f6d8b04f391ad8962251f53eae9a9581bc3c1417511492e27549384","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-05-07T02:49:10Z","title_canon_sha256":"b8e30bc55826273ba885430c624af905a1c84ec484edd9fd19c48d63089b92ad"},"schema_version":"1.0","source":{"id":"1705.02553","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1705.02553","created_at":"2026-05-18T00:42:12Z"},{"alias_kind":"arxiv_version","alias_value":"1705.02553v1","created_at":"2026-05-18T00:42:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.02553","created_at":"2026-05-18T00:42:12Z"},{"alias_kind":"pith_short_12","alias_value":"XI4JAU7VVILJ","created_at":"2026-05-18T12:31:53Z"},{"alias_kind":"pith_short_16","alias_value":"XI4JAU7VVILJ42UL","created_at":"2026-05-18T12:31:53Z"},{"alias_kind":"pith_short_8","alias_value":"XI4JAU7V","created_at":"2026-05-18T12:31:53Z"}],"graph_snapshots":[{"event_id":"sha256:dbc9081965682df2b5f1feec49a42c5936fc4eb45ecdd731f939b27aed4965ba","target":"graph","created_at":"2026-05-18T00:42:12Z","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 reinforcement learning algorithm for partially observable Markov decision processes (POMDP) based on spectral decomposition methods. While spectral methods have been previously employed for consistent learning of (passive) latent variable models such as hidden Markov models, POMDPs are more challenging since the learner interacts with the environment and possibly changes the future observations in the process. We devise a learning algorithm running through epochs, in each epoch we employ spectral techniques to learn the POMDP parameters from a trajectory generated by a fixed p","authors_text":"Alessandro Lazaric, Animashree Anandkumar, Kamyar Azizzadenesheli","cross_cats":["cs.LG","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-05-07T02:49:10Z","title":"Experimental results : Reinforcement Learning of POMDPs using Spectral Methods"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.02553","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:d691595a56405ca8c931cdda5a556d0b1dd7d21564f096af68cdc31b5e7f29b6","target":"record","created_at":"2026-05-18T00:42:12Z","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":"98b360510f6d8b04f391ad8962251f53eae9a9581bc3c1417511492e27549384","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-05-07T02:49:10Z","title_canon_sha256":"b8e30bc55826273ba885430c624af905a1c84ec484edd9fd19c48d63089b92ad"},"schema_version":"1.0","source":{"id":"1705.02553","kind":"arxiv","version":1}},"canonical_sha256":"ba389053f5aa169e6a8be0b476e12c820b93f21cc7e8a307dde359b6e86adbf1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ba389053f5aa169e6a8be0b476e12c820b93f21cc7e8a307dde359b6e86adbf1","first_computed_at":"2026-05-18T00:42:12.054812Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:42:12.054812Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vz7v8mvTH/LxFe7nCg2SEP08MFOPA0moU1LDHhL58iFgUxtTZHfWxaxfcHCY3W0Eh/Kz5vc74Cugzi3Rda/IDg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:42:12.055255Z","signed_message":"canonical_sha256_bytes"},"source_id":"1705.02553","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d691595a56405ca8c931cdda5a556d0b1dd7d21564f096af68cdc31b5e7f29b6","sha256:dbc9081965682df2b5f1feec49a42c5936fc4eb45ecdd731f939b27aed4965ba"],"state_sha256":"6731a4d9d57810b842f2f6105f5cdddcaa775b00cf14cedfbc2d6da3035a1c82"}