{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2013:M3EG5H6IXB65PBAJGMCGOMHCFP","short_pith_number":"pith:M3EG5H6I","schema_version":"1.0","canonical_sha256":"66c86e9fc8b87dd7840933046730e22bc458e84f205c5035dd4f8ae4e3e2148d","source":{"kind":"arxiv","id":"1301.6721","version":1},"attestation_state":"computed","paper":{"title":"Learning Finite-State Controllers for Partially Observable Environments","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SY"],"primary_cat":"cs.AI","authors_text":"Kee-Eung Kim, Leonid Peshkin, Leslie Pack Kaelbling, Nicolas Meuleau","submitted_at":"2013-01-23T15:59:46Z","abstract_excerpt":"Reactive (memoryless) policies are sufficient in completely observable Markov decision processes (MDPs), but some kind of memory is usually necessary for optimal control of a partially observable MDP. Policies with finite memory can be represented as finite-state automata. In this paper, we extend Baird and Moore's VAPS algorithm to the problem of learning general finite-state automata. Because it performs stochastic gradient descent, this algorithm can be shown to converge to a locally optimal finite-state controller. We provide the details of the algorithm and then consider the question of u"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1301.6721","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2013-01-23T15:59:46Z","cross_cats_sorted":["cs.SY"],"title_canon_sha256":"b1eba76758f4ea8c3cd149d6ab7b2b2a6a2ea60f397d9b15bd00f8ba66e9feb3","abstract_canon_sha256":"fe50ed3b135fc3f23b9c7df70c00eb7e4408fc73bb8264be0e7996c98ab887d8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:35:12.735005Z","signature_b64":"D2vJxQFzjFRnKofYs0Hqig7acyyUpErwOy//WazBqeN2MSl93HA+6m4QBGPxAm/IDhK57ojb0VXTMP7qiv7ZBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"66c86e9fc8b87dd7840933046730e22bc458e84f205c5035dd4f8ae4e3e2148d","last_reissued_at":"2026-05-18T03:35:12.734280Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:35:12.734280Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Finite-State Controllers for Partially Observable Environments","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SY"],"primary_cat":"cs.AI","authors_text":"Kee-Eung Kim, Leonid Peshkin, Leslie Pack Kaelbling, Nicolas Meuleau","submitted_at":"2013-01-23T15:59:46Z","abstract_excerpt":"Reactive (memoryless) policies are sufficient in completely observable Markov decision processes (MDPs), but some kind of memory is usually necessary for optimal control of a partially observable MDP. Policies with finite memory can be represented as finite-state automata. In this paper, we extend Baird and Moore's VAPS algorithm to the problem of learning general finite-state automata. Because it performs stochastic gradient descent, this algorithm can be shown to converge to a locally optimal finite-state controller. We provide the details of the algorithm and then consider the question of u"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1301.6721","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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1301.6721","created_at":"2026-05-18T03:35:12.734415+00:00"},{"alias_kind":"arxiv_version","alias_value":"1301.6721v1","created_at":"2026-05-18T03:35:12.734415+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1301.6721","created_at":"2026-05-18T03:35:12.734415+00:00"},{"alias_kind":"pith_short_12","alias_value":"M3EG5H6IXB65","created_at":"2026-05-18T12:27:51.066281+00:00"},{"alias_kind":"pith_short_16","alias_value":"M3EG5H6IXB65PBAJ","created_at":"2026-05-18T12:27:51.066281+00:00"},{"alias_kind":"pith_short_8","alias_value":"M3EG5H6I","created_at":"2026-05-18T12:27:51.066281+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2505.06111","citing_title":"UniVLA: Learning to Act Anywhere with Task-centric Latent Actions","ref_index":60,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/M3EG5H6IXB65PBAJGMCGOMHCFP","json":"https://pith.science/pith/M3EG5H6IXB65PBAJGMCGOMHCFP.json","graph_json":"https://pith.science/api/pith-number/M3EG5H6IXB65PBAJGMCGOMHCFP/graph.json","events_json":"https://pith.science/api/pith-number/M3EG5H6IXB65PBAJGMCGOMHCFP/events.json","paper":"https://pith.science/paper/M3EG5H6I"},"agent_actions":{"view_html":"https://pith.science/pith/M3EG5H6IXB65PBAJGMCGOMHCFP","download_json":"https://pith.science/pith/M3EG5H6IXB65PBAJGMCGOMHCFP.json","view_paper":"https://pith.science/paper/M3EG5H6I","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1301.6721&json=true","fetch_graph":"https://pith.science/api/pith-number/M3EG5H6IXB65PBAJGMCGOMHCFP/graph.json","fetch_events":"https://pith.science/api/pith-number/M3EG5H6IXB65PBAJGMCGOMHCFP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/M3EG5H6IXB65PBAJGMCGOMHCFP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/M3EG5H6IXB65PBAJGMCGOMHCFP/action/storage_attestation","attest_author":"https://pith.science/pith/M3EG5H6IXB65PBAJGMCGOMHCFP/action/author_attestation","sign_citation":"https://pith.science/pith/M3EG5H6IXB65PBAJGMCGOMHCFP/action/citation_signature","submit_replication":"https://pith.science/pith/M3EG5H6IXB65PBAJGMCGOMHCFP/action/replication_record"}},"created_at":"2026-05-18T03:35:12.734415+00:00","updated_at":"2026-05-18T03:35:12.734415+00:00"}