{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:MQNN356VTAYLG7TG4JQWGZWMW2","short_pith_number":"pith:MQNN356V","schema_version":"1.0","canonical_sha256":"641addf7d59830b37e66e2616366ccb6aa22005ed529780714b0bfcc11f0a932","source":{"kind":"arxiv","id":"2406.00614","version":1},"attestation_state":"computed","paper":{"title":"Efficient Monte Carlo Tree Search via On-the-Fly State-Conditioned Action Abstraction","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Byoung-Tak Zhang, Dooyoung Kim, Inwoo Hwang, Sanghack Lee, Yunhyeok Kwak","submitted_at":"2024-06-02T04:31:30Z","abstract_excerpt":"Monte Carlo Tree Search (MCTS) has showcased its efficacy across a broad spectrum of decision-making problems. However, its performance often degrades under vast combinatorial action space, especially where an action is composed of multiple sub-actions. In this work, we propose an action abstraction based on the compositional structure between a state and sub-actions for improving the efficiency of MCTS under a factored action space. Our method learns a latent dynamics model with an auxiliary network that captures sub-actions relevant to the transition on the current state, which we call state"},"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":"2406.00614","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-02T04:31:30Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f53d4aca6135951d257e3c04887848ff45c0ab36bb98e646c159b1357f3195c7","abstract_canon_sha256":"c000fec469975572f45c894dbd5ec406be25b5729476ef33a1c03633ec6a85b3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:26:28.125117Z","signature_b64":"yTOudL1bAeb8eRn/ax4OgkC2sA6IwBgkzIaO9/FOGpzgoDB31Q/QpKzhVVF/wdCeMNAa3AE0v0Cz2WnSizGsAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"641addf7d59830b37e66e2616366ccb6aa22005ed529780714b0bfcc11f0a932","last_reissued_at":"2026-07-05T08:26:28.124620Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:26:28.124620Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Efficient Monte Carlo Tree Search via On-the-Fly State-Conditioned Action Abstraction","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Byoung-Tak Zhang, Dooyoung Kim, Inwoo Hwang, Sanghack Lee, Yunhyeok Kwak","submitted_at":"2024-06-02T04:31:30Z","abstract_excerpt":"Monte Carlo Tree Search (MCTS) has showcased its efficacy across a broad spectrum of decision-making problems. However, its performance often degrades under vast combinatorial action space, especially where an action is composed of multiple sub-actions. In this work, we propose an action abstraction based on the compositional structure between a state and sub-actions for improving the efficiency of MCTS under a factored action space. Our method learns a latent dynamics model with an auxiliary network that captures sub-actions relevant to the transition on the current state, which we call state"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.00614","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2406.00614/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2406.00614","created_at":"2026-07-05T08:26:28.124682+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.00614v1","created_at":"2026-07-05T08:26:28.124682+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.00614","created_at":"2026-07-05T08:26:28.124682+00:00"},{"alias_kind":"pith_short_12","alias_value":"MQNN356VTAYL","created_at":"2026-07-05T08:26:28.124682+00:00"},{"alias_kind":"pith_short_16","alias_value":"MQNN356VTAYLG7TG","created_at":"2026-07-05T08:26:28.124682+00:00"},{"alias_kind":"pith_short_8","alias_value":"MQNN356V","created_at":"2026-07-05T08:26:28.124682+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.00751","citing_title":"NonZero: Interaction-Guided Exploration for Multi-Agent Monte Carlo Tree Search","ref_index":16,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MQNN356VTAYLG7TG4JQWGZWMW2","json":"https://pith.science/pith/MQNN356VTAYLG7TG4JQWGZWMW2.json","graph_json":"https://pith.science/api/pith-number/MQNN356VTAYLG7TG4JQWGZWMW2/graph.json","events_json":"https://pith.science/api/pith-number/MQNN356VTAYLG7TG4JQWGZWMW2/events.json","paper":"https://pith.science/paper/MQNN356V"},"agent_actions":{"view_html":"https://pith.science/pith/MQNN356VTAYLG7TG4JQWGZWMW2","download_json":"https://pith.science/pith/MQNN356VTAYLG7TG4JQWGZWMW2.json","view_paper":"https://pith.science/paper/MQNN356V","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.00614&json=true","fetch_graph":"https://pith.science/api/pith-number/MQNN356VTAYLG7TG4JQWGZWMW2/graph.json","fetch_events":"https://pith.science/api/pith-number/MQNN356VTAYLG7TG4JQWGZWMW2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MQNN356VTAYLG7TG4JQWGZWMW2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MQNN356VTAYLG7TG4JQWGZWMW2/action/storage_attestation","attest_author":"https://pith.science/pith/MQNN356VTAYLG7TG4JQWGZWMW2/action/author_attestation","sign_citation":"https://pith.science/pith/MQNN356VTAYLG7TG4JQWGZWMW2/action/citation_signature","submit_replication":"https://pith.science/pith/MQNN356VTAYLG7TG4JQWGZWMW2/action/replication_record"}},"created_at":"2026-07-05T08:26:28.124682+00:00","updated_at":"2026-07-05T08:26:28.124682+00:00"}