{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2012:HSSZPTVPAVZRR45SAY6A6E3U2P","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":"e3537fdf202976c8fe777234f8448121f5fbb8ab5edf24c7023b1f8dd26ee30c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2012-02-14T16:41:17Z","title_canon_sha256":"0cb1178f66869cc9bdf9f57cc67d3032fa3ec16b6d612ea6fcf8644a26a4e23e"},"schema_version":"1.0","source":{"id":"1202.3699","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1202.3699","created_at":"2026-05-18T04:02:03Z"},{"alias_kind":"arxiv_version","alias_value":"1202.3699v1","created_at":"2026-05-18T04:02:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1202.3699","created_at":"2026-05-18T04:02:03Z"},{"alias_kind":"pith_short_12","alias_value":"HSSZPTVPAVZR","created_at":"2026-05-18T12:27:09Z"},{"alias_kind":"pith_short_16","alias_value":"HSSZPTVPAVZRR45S","created_at":"2026-05-18T12:27:09Z"},{"alias_kind":"pith_short_8","alias_value":"HSSZPTVP","created_at":"2026-05-18T12:27:09Z"}],"graph_snapshots":[{"event_id":"sha256:7be2f52069ba26d3a735d578c5ac8a7dd88d3a8f543aa990ca6184ae59962b1c","target":"graph","created_at":"2026-05-18T04:02:03Z","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":"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),","authors_text":"John Asmuth, Michael L. Littman","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2012-02-14T16:41:17Z","title":"Learning is planning: near Bayes-optimal reinforcement learning via Monte-Carlo tree search"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1202.3699","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:bf0c8fabb4230c68dcda92c060e7bfc36aa6a8424c30b37dcc20bd99d503c585","target":"record","created_at":"2026-05-18T04:02:03Z","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":"e3537fdf202976c8fe777234f8448121f5fbb8ab5edf24c7023b1f8dd26ee30c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2012-02-14T16:41:17Z","title_canon_sha256":"0cb1178f66869cc9bdf9f57cc67d3032fa3ec16b6d612ea6fcf8644a26a4e23e"},"schema_version":"1.0","source":{"id":"1202.3699","kind":"arxiv","version":1}},"canonical_sha256":"3ca597ceaf057318f3b2063c0f1374d3fa713801fcf00d06b80ab90daed9a347","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3ca597ceaf057318f3b2063c0f1374d3fa713801fcf00d06b80ab90daed9a347","first_computed_at":"2026-05-18T04:02:03.521556Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T04:02:03.521556Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RK0LRkrmEz+twuaidVGdDlb/AURQbGUw2V+j7K/phfnp3Yw4LPyPoRfS337xWspMKD76kHeCslA6UkRhUF1qCA==","signature_status":"signed_v1","signed_at":"2026-05-18T04:02:03.522164Z","signed_message":"canonical_sha256_bytes"},"source_id":"1202.3699","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bf0c8fabb4230c68dcda92c060e7bfc36aa6a8424c30b37dcc20bd99d503c585","sha256:7be2f52069ba26d3a735d578c5ac8a7dd88d3a8f543aa990ca6184ae59962b1c"],"state_sha256":"8fb6ae42ed80ee2d1992c507f0de3a69502b877b72439c42b92bfa6308aa69e9"}