{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:5Y46OVVBJORA3GO26QSCNLDG3E","short_pith_number":"pith:5Y46OVVB","schema_version":"1.0","canonical_sha256":"ee39e756a14ba20d99daf42426ac66d906f24296a05e5e8e31c3484509a39d43","source":{"kind":"arxiv","id":"1505.00274","version":2},"attestation_state":"computed","paper":{"title":"Stick-Breaking Policy Learning in Dec-POMDPs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SY","stat.ML"],"primary_cat":"cs.AI","authors_text":"Christopher Amato, Jonathan P. How, Lawrence Carin, Miao Liu, Xuejun Liao","submitted_at":"2015-05-01T20:29:27Z","abstract_excerpt":"Expectation maximization (EM) has recently been shown to be an efficient algorithm for learning finite-state controllers (FSCs) in large decentralized POMDPs (Dec-POMDPs). However, current methods use fixed-size FSCs and often converge to maxima that are far from optimal. This paper considers a variable-size FSC to represent the local policy of each agent. These variable-size FSCs are constructed using a stick-breaking prior, leading to a new framework called \\emph{decentralized stick-breaking policy representation} (Dec-SBPR). This approach learns the controller parameters with a variational "},"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":"1505.00274","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2015-05-01T20:29:27Z","cross_cats_sorted":["cs.SY","stat.ML"],"title_canon_sha256":"212700f00dd98c9bc5f8f3efdca25fabf4b641655ccd7af2c01a556c963bfa0a","abstract_canon_sha256":"dcbf82ea8f3b5407e24ad84bb59fe4211f1b4284a0533215009eb6be20341938"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:26:18.409604Z","signature_b64":"vS3z8uq0NlIQaUmkWK1mqhi51j5va8P6BY7xgYJ0mY4u2tgDKa38zN9jKXR4rTejMZQ8cAIUXSSyBRHtECGODg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ee39e756a14ba20d99daf42426ac66d906f24296a05e5e8e31c3484509a39d43","last_reissued_at":"2026-05-18T01:26:18.409025Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:26:18.409025Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Stick-Breaking Policy Learning in Dec-POMDPs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SY","stat.ML"],"primary_cat":"cs.AI","authors_text":"Christopher Amato, Jonathan P. How, Lawrence Carin, Miao Liu, Xuejun Liao","submitted_at":"2015-05-01T20:29:27Z","abstract_excerpt":"Expectation maximization (EM) has recently been shown to be an efficient algorithm for learning finite-state controllers (FSCs) in large decentralized POMDPs (Dec-POMDPs). However, current methods use fixed-size FSCs and often converge to maxima that are far from optimal. This paper considers a variable-size FSC to represent the local policy of each agent. These variable-size FSCs are constructed using a stick-breaking prior, leading to a new framework called \\emph{decentralized stick-breaking policy representation} (Dec-SBPR). This approach learns the controller parameters with a variational "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1505.00274","kind":"arxiv","version":2},"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":"1505.00274","created_at":"2026-05-18T01:26:18.409129+00:00"},{"alias_kind":"arxiv_version","alias_value":"1505.00274v2","created_at":"2026-05-18T01:26:18.409129+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1505.00274","created_at":"2026-05-18T01:26:18.409129+00:00"},{"alias_kind":"pith_short_12","alias_value":"5Y46OVVBJORA","created_at":"2026-05-18T12:29:07.941421+00:00"},{"alias_kind":"pith_short_16","alias_value":"5Y46OVVBJORA3GO2","created_at":"2026-05-18T12:29:07.941421+00:00"},{"alias_kind":"pith_short_8","alias_value":"5Y46OVVB","created_at":"2026-05-18T12:29:07.941421+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.00160","citing_title":"Approximations and Learning for Decentralized Stochastic Control and Near Optimal Finite Window Policies","ref_index":29,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5Y46OVVBJORA3GO26QSCNLDG3E","json":"https://pith.science/pith/5Y46OVVBJORA3GO26QSCNLDG3E.json","graph_json":"https://pith.science/api/pith-number/5Y46OVVBJORA3GO26QSCNLDG3E/graph.json","events_json":"https://pith.science/api/pith-number/5Y46OVVBJORA3GO26QSCNLDG3E/events.json","paper":"https://pith.science/paper/5Y46OVVB"},"agent_actions":{"view_html":"https://pith.science/pith/5Y46OVVBJORA3GO26QSCNLDG3E","download_json":"https://pith.science/pith/5Y46OVVBJORA3GO26QSCNLDG3E.json","view_paper":"https://pith.science/paper/5Y46OVVB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1505.00274&json=true","fetch_graph":"https://pith.science/api/pith-number/5Y46OVVBJORA3GO26QSCNLDG3E/graph.json","fetch_events":"https://pith.science/api/pith-number/5Y46OVVBJORA3GO26QSCNLDG3E/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5Y46OVVBJORA3GO26QSCNLDG3E/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5Y46OVVBJORA3GO26QSCNLDG3E/action/storage_attestation","attest_author":"https://pith.science/pith/5Y46OVVBJORA3GO26QSCNLDG3E/action/author_attestation","sign_citation":"https://pith.science/pith/5Y46OVVBJORA3GO26QSCNLDG3E/action/citation_signature","submit_replication":"https://pith.science/pith/5Y46OVVBJORA3GO26QSCNLDG3E/action/replication_record"}},"created_at":"2026-05-18T01:26:18.409129+00:00","updated_at":"2026-05-18T01:26:18.409129+00:00"}