{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:R7VN6GBZWH3UJMMBMBUN2BOR6L","short_pith_number":"pith:R7VN6GBZ","schema_version":"1.0","canonical_sha256":"8feadf1839b1f744b1816068dd05d1f2d002f90d1417f42c5ad1f98fec061e90","source":{"kind":"arxiv","id":"1809.03299","version":1},"attestation_state":"computed","paper":{"title":"Monte Carlo Tree Search for Verifying Reachability in Markov Decision Processes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LO","authors_text":"Jan K\\v{r}et\\'insk\\'y, Ond\\v{r}ej Sl\\'ame\\v{c}ka, Pranav Ashok, Tom\\'a\\v{s} Br\\'azdil","submitted_at":"2018-09-10T13:31:02Z","abstract_excerpt":"The maximum reachability probabilities in a Markov decision process can be computed using value iteration (VI). Recently, simulation-based heuristic extensions of VI have been introduced, such as bounded real-time dynamic programming (BRTDP), which often manage to avoid explicit analysis of the whole state space while preserving guarantees on the computed result. In this paper, we introduce a new class of such heuristics, based on Monte Carlo tree search (MCTS), a technique celebrated in various machine-learning settings. We provide a spectrum of algorithms ranging from MCTS to BRTDP. We evalu"},"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":"1809.03299","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LO","submitted_at":"2018-09-10T13:31:02Z","cross_cats_sorted":[],"title_canon_sha256":"077e090be994c6178d9cff506323701c1af96e7e4ae35ee14b20fbbaa23ff7b3","abstract_canon_sha256":"b4a80f6612ece0bce3aaba0c586f8fd7731429b69be5e5c2e55b24428c3cbc6b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:06:09.297175Z","signature_b64":"vaJvCFScb1Nuf292iTPODx0WsJB+F6SLf+gVtSPfA5RD46S81NGmEeYlpQsuI825phlLaA2yGgiEh+SOom/xAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8feadf1839b1f744b1816068dd05d1f2d002f90d1417f42c5ad1f98fec061e90","last_reissued_at":"2026-05-18T00:06:09.296468Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:06:09.296468Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Monte Carlo Tree Search for Verifying Reachability in Markov Decision Processes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LO","authors_text":"Jan K\\v{r}et\\'insk\\'y, Ond\\v{r}ej Sl\\'ame\\v{c}ka, Pranav Ashok, Tom\\'a\\v{s} Br\\'azdil","submitted_at":"2018-09-10T13:31:02Z","abstract_excerpt":"The maximum reachability probabilities in a Markov decision process can be computed using value iteration (VI). Recently, simulation-based heuristic extensions of VI have been introduced, such as bounded real-time dynamic programming (BRTDP), which often manage to avoid explicit analysis of the whole state space while preserving guarantees on the computed result. In this paper, we introduce a new class of such heuristics, based on Monte Carlo tree search (MCTS), a technique celebrated in various machine-learning settings. We provide a spectrum of algorithms ranging from MCTS to BRTDP. We evalu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.03299","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":"1809.03299","created_at":"2026-05-18T00:06:09.296581+00:00"},{"alias_kind":"arxiv_version","alias_value":"1809.03299v1","created_at":"2026-05-18T00:06:09.296581+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.03299","created_at":"2026-05-18T00:06:09.296581+00:00"},{"alias_kind":"pith_short_12","alias_value":"R7VN6GBZWH3U","created_at":"2026-05-18T12:32:50.500415+00:00"},{"alias_kind":"pith_short_16","alias_value":"R7VN6GBZWH3UJMMB","created_at":"2026-05-18T12:32:50.500415+00:00"},{"alias_kind":"pith_short_8","alias_value":"R7VN6GBZ","created_at":"2026-05-18T12:32:50.500415+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/R7VN6GBZWH3UJMMBMBUN2BOR6L","json":"https://pith.science/pith/R7VN6GBZWH3UJMMBMBUN2BOR6L.json","graph_json":"https://pith.science/api/pith-number/R7VN6GBZWH3UJMMBMBUN2BOR6L/graph.json","events_json":"https://pith.science/api/pith-number/R7VN6GBZWH3UJMMBMBUN2BOR6L/events.json","paper":"https://pith.science/paper/R7VN6GBZ"},"agent_actions":{"view_html":"https://pith.science/pith/R7VN6GBZWH3UJMMBMBUN2BOR6L","download_json":"https://pith.science/pith/R7VN6GBZWH3UJMMBMBUN2BOR6L.json","view_paper":"https://pith.science/paper/R7VN6GBZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1809.03299&json=true","fetch_graph":"https://pith.science/api/pith-number/R7VN6GBZWH3UJMMBMBUN2BOR6L/graph.json","fetch_events":"https://pith.science/api/pith-number/R7VN6GBZWH3UJMMBMBUN2BOR6L/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/R7VN6GBZWH3UJMMBMBUN2BOR6L/action/timestamp_anchor","attest_storage":"https://pith.science/pith/R7VN6GBZWH3UJMMBMBUN2BOR6L/action/storage_attestation","attest_author":"https://pith.science/pith/R7VN6GBZWH3UJMMBMBUN2BOR6L/action/author_attestation","sign_citation":"https://pith.science/pith/R7VN6GBZWH3UJMMBMBUN2BOR6L/action/citation_signature","submit_replication":"https://pith.science/pith/R7VN6GBZWH3UJMMBMBUN2BOR6L/action/replication_record"}},"created_at":"2026-05-18T00:06:09.296581+00:00","updated_at":"2026-05-18T00:06:09.296581+00:00"}