{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:5MC4VZDDEDK4GAYHWXIGR2WKWS","short_pith_number":"pith:5MC4VZDD","schema_version":"1.0","canonical_sha256":"eb05cae46320d5c30307b5d068eacab4bf6c8929dfc035c7c4b0ed89ab448d14","source":{"kind":"arxiv","id":"1605.09128","version":1},"attestation_state":"computed","paper":{"title":"Control of Memory, Active Perception, and Action in Minecraft","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"cs.AI","authors_text":"Honglak Lee, Junhyuk Oh, Satinder Singh, Valliappa Chockalingam","submitted_at":"2016-05-30T07:40:13Z","abstract_excerpt":"In this paper, we introduce a new set of reinforcement learning (RL) tasks in Minecraft (a flexible 3D world). We then use these tasks to systematically compare and contrast existing deep reinforcement learning (DRL) architectures with our new memory-based DRL architectures. These tasks are designed to emphasize, in a controllable manner, issues that pose challenges for RL methods including partial observability (due to first-person visual observations), delayed rewards, high-dimensional visual observations, and the need to use active perception in a correct manner so as to perform well in the"},"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":"1605.09128","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2016-05-30T07:40:13Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"5f29d459c3cf61d78a29d39f1d0d9fd58b45a28bb415cf31d9330caa9a39f3fc","abstract_canon_sha256":"a0cbebb68b54af6eb6afef5559e5535187ace6e81715b1cc559671f7fa1533df"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:13:22.013615Z","signature_b64":"COY4WUWvmYbXVrE9iZERagS8uCWMRLXd0ff91fNXziXntzlDO+C5Wgpz6Q7Rq/+yIX7rlJRA0zOho5hwry8eAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eb05cae46320d5c30307b5d068eacab4bf6c8929dfc035c7c4b0ed89ab448d14","last_reissued_at":"2026-05-18T01:13:22.012878Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:13:22.012878Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Control of Memory, Active Perception, and Action in Minecraft","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"cs.AI","authors_text":"Honglak Lee, Junhyuk Oh, Satinder Singh, Valliappa Chockalingam","submitted_at":"2016-05-30T07:40:13Z","abstract_excerpt":"In this paper, we introduce a new set of reinforcement learning (RL) tasks in Minecraft (a flexible 3D world). We then use these tasks to systematically compare and contrast existing deep reinforcement learning (DRL) architectures with our new memory-based DRL architectures. These tasks are designed to emphasize, in a controllable manner, issues that pose challenges for RL methods including partial observability (due to first-person visual observations), delayed rewards, high-dimensional visual observations, and the need to use active perception in a correct manner so as to perform well in the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1605.09128","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":"1605.09128","created_at":"2026-05-18T01:13:22.012979+00:00"},{"alias_kind":"arxiv_version","alias_value":"1605.09128v1","created_at":"2026-05-18T01:13:22.012979+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1605.09128","created_at":"2026-05-18T01:13:22.012979+00:00"},{"alias_kind":"pith_short_12","alias_value":"5MC4VZDDEDK4","created_at":"2026-05-18T12:30:01.593930+00:00"},{"alias_kind":"pith_short_16","alias_value":"5MC4VZDDEDK4GAYH","created_at":"2026-05-18T12:30:01.593930+00:00"},{"alias_kind":"pith_short_8","alias_value":"5MC4VZDD","created_at":"2026-05-18T12:30:01.593930+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":15,"is_internal_anchor":true},{"citing_arxiv_id":"1907.09273","citing_title":"Why Build an Assistant in Minecraft?","ref_index":67,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5MC4VZDDEDK4GAYHWXIGR2WKWS","json":"https://pith.science/pith/5MC4VZDDEDK4GAYHWXIGR2WKWS.json","graph_json":"https://pith.science/api/pith-number/5MC4VZDDEDK4GAYHWXIGR2WKWS/graph.json","events_json":"https://pith.science/api/pith-number/5MC4VZDDEDK4GAYHWXIGR2WKWS/events.json","paper":"https://pith.science/paper/5MC4VZDD"},"agent_actions":{"view_html":"https://pith.science/pith/5MC4VZDDEDK4GAYHWXIGR2WKWS","download_json":"https://pith.science/pith/5MC4VZDDEDK4GAYHWXIGR2WKWS.json","view_paper":"https://pith.science/paper/5MC4VZDD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1605.09128&json=true","fetch_graph":"https://pith.science/api/pith-number/5MC4VZDDEDK4GAYHWXIGR2WKWS/graph.json","fetch_events":"https://pith.science/api/pith-number/5MC4VZDDEDK4GAYHWXIGR2WKWS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5MC4VZDDEDK4GAYHWXIGR2WKWS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5MC4VZDDEDK4GAYHWXIGR2WKWS/action/storage_attestation","attest_author":"https://pith.science/pith/5MC4VZDDEDK4GAYHWXIGR2WKWS/action/author_attestation","sign_citation":"https://pith.science/pith/5MC4VZDDEDK4GAYHWXIGR2WKWS/action/citation_signature","submit_replication":"https://pith.science/pith/5MC4VZDDEDK4GAYHWXIGR2WKWS/action/replication_record"}},"created_at":"2026-05-18T01:13:22.012979+00:00","updated_at":"2026-05-18T01:13:22.012979+00:00"}