{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:OYIPUZZYSWQ65BC7VL3NGZIG45","short_pith_number":"pith:OYIPUZZY","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"},"canonical_sha256":"7610fa673895a1ee845faaf6d36506e779549771e4f0a2e596007c608510fb3f","source":{"kind":"arxiv","id":"1803.08456","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1803.08456","created_at":"2026-05-18T00:20:22Z"},{"alias_kind":"arxiv_version","alias_value":"1803.08456v1","created_at":"2026-05-18T00:20:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.08456","created_at":"2026-05-18T00:20:22Z"},{"alias_kind":"pith_short_12","alias_value":"OYIPUZZYSWQ6","created_at":"2026-05-18T12:32:43Z"},{"alias_kind":"pith_short_16","alias_value":"OYIPUZZYSWQ65BC7","created_at":"2026-05-18T12:32:43Z"},{"alias_kind":"pith_short_8","alias_value":"OYIPUZZY","created_at":"2026-05-18T12:32:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:OYIPUZZYSWQ65BC7VL3NGZIG45","target":"record","payload":{"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"},"canonical_sha256":"7610fa673895a1ee845faaf6d36506e779549771e4f0a2e596007c608510fb3f","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"},"source_kind":"arxiv","source_id":"1803.08456","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:20:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FeXruYDfM49ZLOiV/LOlAit5wXwcrm0UW8uv4Y1Hz+JrAYOIOVli5/TEDZtjXYjQ7nBJ93/kAe0CAQbMUtSADA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T16:25:28.964699Z"},"content_sha256":"49101cec93150220cd4e06cf5f16d57f7af0a40b7720c92dbd8fe00cc7958bda","schema_version":"1.0","event_id":"sha256:49101cec93150220cd4e06cf5f16d57f7af0a40b7720c92dbd8fe00cc7958bda"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:OYIPUZZYSWQ65BC7VL3NGZIG45","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:20:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5f+MeikHoPDzddIivl2j5Np+FwdcoLDjJgjn4ULH/lYfBHqu8gzAxsKsa8aJDSs1EuJe4Np7pFxIAv9+t+v7AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T16:25:28.965359Z"},"content_sha256":"81dc0e71e8e5f7518c3183a877970d36d36fe1d394f70d210a40db829994c50d","schema_version":"1.0","event_id":"sha256:81dc0e71e8e5f7518c3183a877970d36d36fe1d394f70d210a40db829994c50d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OYIPUZZYSWQ65BC7VL3NGZIG45/bundle.json","state_url":"https://pith.science/pith/OYIPUZZYSWQ65BC7VL3NGZIG45/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OYIPUZZYSWQ65BC7VL3NGZIG45/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-25T16:25:28Z","links":{"resolver":"https://pith.science/pith/OYIPUZZYSWQ65BC7VL3NGZIG45","bundle":"https://pith.science/pith/OYIPUZZYSWQ65BC7VL3NGZIG45/bundle.json","state":"https://pith.science/pith/OYIPUZZYSWQ65BC7VL3NGZIG45/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OYIPUZZYSWQ65BC7VL3NGZIG45/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:OYIPUZZYSWQ65BC7VL3NGZIG45","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":"bcf825c2b2ecc57894e790462761d12323f8df3f5e3b69894bbf2fb868e0393e","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-03-22T16:53:34Z","title_canon_sha256":"c440dd94aecacb51d83b191141bfd05bcff18880c1ad7805adfb95672cba0b01"},"schema_version":"1.0","source":{"id":"1803.08456","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1803.08456","created_at":"2026-05-18T00:20:22Z"},{"alias_kind":"arxiv_version","alias_value":"1803.08456v1","created_at":"2026-05-18T00:20:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.08456","created_at":"2026-05-18T00:20:22Z"},{"alias_kind":"pith_short_12","alias_value":"OYIPUZZYSWQ6","created_at":"2026-05-18T12:32:43Z"},{"alias_kind":"pith_short_16","alias_value":"OYIPUZZYSWQ65BC7","created_at":"2026-05-18T12:32:43Z"},{"alias_kind":"pith_short_8","alias_value":"OYIPUZZY","created_at":"2026-05-18T12:32:43Z"}],"graph_snapshots":[{"event_id":"sha256:81dc0e71e8e5f7518c3183a877970d36d36fe1d394f70d210a40db829994c50d","target":"graph","created_at":"2026-05-18T00:20:22Z","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":"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","authors_text":"Stephan Alaniz","cross_cats":["cs.LG","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-03-22T16:53:34Z","title":"Deep Reinforcement Learning with Model Learning and Monte Carlo Tree Search in Minecraft"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.08456","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":"sha256:49101cec93150220cd4e06cf5f16d57f7af0a40b7720c92dbd8fe00cc7958bda","target":"record","created_at":"2026-05-18T00:20:22Z","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":"bcf825c2b2ecc57894e790462761d12323f8df3f5e3b69894bbf2fb868e0393e","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-03-22T16:53:34Z","title_canon_sha256":"c440dd94aecacb51d83b191141bfd05bcff18880c1ad7805adfb95672cba0b01"},"schema_version":"1.0","source":{"id":"1803.08456","kind":"arxiv","version":1}},"canonical_sha256":"7610fa673895a1ee845faaf6d36506e779549771e4f0a2e596007c608510fb3f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7610fa673895a1ee845faaf6d36506e779549771e4f0a2e596007c608510fb3f","first_computed_at":"2026-05-18T00:20:22.805418Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:20:22.805418Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Ke6ooI258sFmkC/fcVoxb62B3p9K+xGJkHHgQ2y5MiXJumA7LbXE6BkKrIPo8SB8Sjvwy526IC4Np1BaKv/9Bw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:20:22.806063Z","signed_message":"canonical_sha256_bytes"},"source_id":"1803.08456","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:49101cec93150220cd4e06cf5f16d57f7af0a40b7720c92dbd8fe00cc7958bda","sha256:81dc0e71e8e5f7518c3183a877970d36d36fe1d394f70d210a40db829994c50d"],"state_sha256":"993d99fefe54b2843c4a7cb6a02e3695d410f068719da021bf798a8e939cf287"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"W8/xbk0OdilHLqRqEYwmU2JChD8dxb3+weQs1RSbtXbwjEceDwQ/K8cbVxQjhD246v0l0St3WE06kClo8eq5Bg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T16:25:28.969443Z","bundle_sha256":"80eeaf8055e5fe0b48ed532906f231bb5950e314ce24676e3dee2455f7258699"}}