{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:OYIPUZZYSWQ65BC7VL3NGZIG45","short_pith_number":"pith:OYIPUZZY","schema_version":"1.0","canonical_sha256":"7610fa673895a1ee845faaf6d36506e779549771e4f0a2e596007c608510fb3f","source":{"kind":"arxiv","id":"1803.08456","version":1},"attestation_state":"computed","paper":{"title":"Deep Reinforcement Learning with Model Learning and Monte Carlo Tree Search in Minecraft","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.AI","authors_text":"Stephan Alaniz","submitted_at":"2018-03-22T16:53:34Z","abstract_excerpt":"Deep reinforcement learning has been successfully applied to several visual-input tasks using model-free methods. In this paper, we propose a model-based approach that combines learning a DNN-based transition model with Monte Carlo tree search to solve a block-placing task in Minecraft. Our learned transition model predicts the next frame and the rewards one step ahead given the last four frames of the agent's first-person-view image and the current action. Then a Monte Carlo tree search algorithm uses this model to plan the best sequence of actions for the agent to perform. On the proposed ta"},"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":"1803.08456","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-03-22T16:53:34Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"c440dd94aecacb51d83b191141bfd05bcff18880c1ad7805adfb95672cba0b01","abstract_canon_sha256":"bcf825c2b2ecc57894e790462761d12323f8df3f5e3b69894bbf2fb868e0393e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:20:22.806063Z","signature_b64":"Ke6ooI258sFmkC/fcVoxb62B3p9K+xGJkHHgQ2y5MiXJumA7LbXE6BkKrIPo8SB8Sjvwy526IC4Np1BaKv/9Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7610fa673895a1ee845faaf6d36506e779549771e4f0a2e596007c608510fb3f","last_reissued_at":"2026-05-18T00:20:22.805418Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:20:22.805418Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep Reinforcement Learning with Model Learning and Monte Carlo Tree Search in Minecraft","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.AI","authors_text":"Stephan Alaniz","submitted_at":"2018-03-22T16:53:34Z","abstract_excerpt":"Deep reinforcement learning has been successfully applied to several visual-input tasks using model-free methods. In this paper, we propose a model-based approach that combines learning a DNN-based transition model with Monte Carlo tree search to solve a block-placing task in Minecraft. Our learned transition model predicts the next frame and the rewards one step ahead given the last four frames of the agent's first-person-view image and the current action. Then a Monte Carlo tree search algorithm uses this model to plan the best sequence of actions for the agent to perform. On the proposed ta"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.08456","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":"1803.08456","created_at":"2026-05-18T00:20:22.805501+00:00"},{"alias_kind":"arxiv_version","alias_value":"1803.08456v1","created_at":"2026-05-18T00:20:22.805501+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.08456","created_at":"2026-05-18T00:20:22.805501+00:00"},{"alias_kind":"pith_short_12","alias_value":"OYIPUZZYSWQ6","created_at":"2026-05-18T12:32:43.782077+00:00"},{"alias_kind":"pith_short_16","alias_value":"OYIPUZZYSWQ65BC7","created_at":"2026-05-18T12:32:43.782077+00:00"},{"alias_kind":"pith_short_8","alias_value":"OYIPUZZY","created_at":"2026-05-18T12:32:43.782077+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"1907.08584","citing_title":"CraftAssist: A Framework for Dialogue-enabled Interactive Agents","ref_index":1,"is_internal_anchor":true},{"citing_arxiv_id":"1907.09273","citing_title":"Why Build an Assistant in Minecraft?","ref_index":3,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OYIPUZZYSWQ65BC7VL3NGZIG45","json":"https://pith.science/pith/OYIPUZZYSWQ65BC7VL3NGZIG45.json","graph_json":"https://pith.science/api/pith-number/OYIPUZZYSWQ65BC7VL3NGZIG45/graph.json","events_json":"https://pith.science/api/pith-number/OYIPUZZYSWQ65BC7VL3NGZIG45/events.json","paper":"https://pith.science/paper/OYIPUZZY"},"agent_actions":{"view_html":"https://pith.science/pith/OYIPUZZYSWQ65BC7VL3NGZIG45","download_json":"https://pith.science/pith/OYIPUZZYSWQ65BC7VL3NGZIG45.json","view_paper":"https://pith.science/paper/OYIPUZZY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1803.08456&json=true","fetch_graph":"https://pith.science/api/pith-number/OYIPUZZYSWQ65BC7VL3NGZIG45/graph.json","fetch_events":"https://pith.science/api/pith-number/OYIPUZZYSWQ65BC7VL3NGZIG45/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OYIPUZZYSWQ65BC7VL3NGZIG45/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OYIPUZZYSWQ65BC7VL3NGZIG45/action/storage_attestation","attest_author":"https://pith.science/pith/OYIPUZZYSWQ65BC7VL3NGZIG45/action/author_attestation","sign_citation":"https://pith.science/pith/OYIPUZZYSWQ65BC7VL3NGZIG45/action/citation_signature","submit_replication":"https://pith.science/pith/OYIPUZZYSWQ65BC7VL3NGZIG45/action/replication_record"}},"created_at":"2026-05-18T00:20:22.805501+00:00","updated_at":"2026-05-18T00:20:22.805501+00:00"}