{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2012:HSSZPTVPAVZRR45SAY6A6E3U2P","short_pith_number":"pith:HSSZPTVP","schema_version":"1.0","canonical_sha256":"3ca597ceaf057318f3b2063c0f1374d3fa713801fcf00d06b80ab90daed9a347","source":{"kind":"arxiv","id":"1202.3699","version":1},"attestation_state":"computed","paper":{"title":"Learning is planning: near Bayes-optimal reinforcement learning via Monte-Carlo tree search","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"John Asmuth, Michael L. Littman","submitted_at":"2012-02-14T16:41:17Z","abstract_excerpt":"Bayes-optimal behavior, while well-defined, is often difficult to achieve. Recent advances in the use of Monte-Carlo tree search (MCTS) have shown that it is possible to act near-optimally in Markov Decision Processes (MDPs) with very large or infinite state spaces. Bayes-optimal behavior in an unknown MDP is equivalent to optimal behavior in the known belief-space MDP, although the size of this belief-space MDP grows exponentially with the amount of history retained, and is potentially infinite. We show how an agent can use one particular MCTS algorithm, Forward Search Sparse Sampling (FSSS),"},"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":"1202.3699","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2012-02-14T16:41:17Z","cross_cats_sorted":[],"title_canon_sha256":"0cb1178f66869cc9bdf9f57cc67d3032fa3ec16b6d612ea6fcf8644a26a4e23e","abstract_canon_sha256":"e3537fdf202976c8fe777234f8448121f5fbb8ab5edf24c7023b1f8dd26ee30c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T04:02:03.522164Z","signature_b64":"RK0LRkrmEz+twuaidVGdDlb/AURQbGUw2V+j7K/phfnp3Yw4LPyPoRfS337xWspMKD76kHeCslA6UkRhUF1qCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3ca597ceaf057318f3b2063c0f1374d3fa713801fcf00d06b80ab90daed9a347","last_reissued_at":"2026-05-18T04:02:03.521556Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T04:02:03.521556Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning is planning: near Bayes-optimal reinforcement learning via Monte-Carlo tree search","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"John Asmuth, Michael L. Littman","submitted_at":"2012-02-14T16:41:17Z","abstract_excerpt":"Bayes-optimal behavior, while well-defined, is often difficult to achieve. Recent advances in the use of Monte-Carlo tree search (MCTS) have shown that it is possible to act near-optimally in Markov Decision Processes (MDPs) with very large or infinite state spaces. Bayes-optimal behavior in an unknown MDP is equivalent to optimal behavior in the known belief-space MDP, although the size of this belief-space MDP grows exponentially with the amount of history retained, and is potentially infinite. We show how an agent can use one particular MCTS algorithm, Forward Search Sparse Sampling (FSSS),"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1202.3699","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":"1202.3699","created_at":"2026-05-18T04:02:03.521638+00:00"},{"alias_kind":"arxiv_version","alias_value":"1202.3699v1","created_at":"2026-05-18T04:02:03.521638+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1202.3699","created_at":"2026-05-18T04:02:03.521638+00:00"},{"alias_kind":"pith_short_12","alias_value":"HSSZPTVPAVZR","created_at":"2026-05-18T12:27:09.501522+00:00"},{"alias_kind":"pith_short_16","alias_value":"HSSZPTVPAVZRR45S","created_at":"2026-05-18T12:27:09.501522+00:00"},{"alias_kind":"pith_short_8","alias_value":"HSSZPTVP","created_at":"2026-05-18T12:27:09.501522+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HSSZPTVPAVZRR45SAY6A6E3U2P","json":"https://pith.science/pith/HSSZPTVPAVZRR45SAY6A6E3U2P.json","graph_json":"https://pith.science/api/pith-number/HSSZPTVPAVZRR45SAY6A6E3U2P/graph.json","events_json":"https://pith.science/api/pith-number/HSSZPTVPAVZRR45SAY6A6E3U2P/events.json","paper":"https://pith.science/paper/HSSZPTVP"},"agent_actions":{"view_html":"https://pith.science/pith/HSSZPTVPAVZRR45SAY6A6E3U2P","download_json":"https://pith.science/pith/HSSZPTVPAVZRR45SAY6A6E3U2P.json","view_paper":"https://pith.science/paper/HSSZPTVP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1202.3699&json=true","fetch_graph":"https://pith.science/api/pith-number/HSSZPTVPAVZRR45SAY6A6E3U2P/graph.json","fetch_events":"https://pith.science/api/pith-number/HSSZPTVPAVZRR45SAY6A6E3U2P/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HSSZPTVPAVZRR45SAY6A6E3U2P/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HSSZPTVPAVZRR45SAY6A6E3U2P/action/storage_attestation","attest_author":"https://pith.science/pith/HSSZPTVPAVZRR45SAY6A6E3U2P/action/author_attestation","sign_citation":"https://pith.science/pith/HSSZPTVPAVZRR45SAY6A6E3U2P/action/citation_signature","submit_replication":"https://pith.science/pith/HSSZPTVPAVZRR45SAY6A6E3U2P/action/replication_record"}},"created_at":"2026-05-18T04:02:03.521638+00:00","updated_at":"2026-05-18T04:02:03.521638+00:00"}