{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:F2IYR6WUE5ITSVPZBA4P4D6HAS","short_pith_number":"pith:F2IYR6WU","schema_version":"1.0","canonical_sha256":"2e9188fad427513955f90838fe0fc7049a3a43258060858aa11ecc896f3ac6bb","source":{"kind":"arxiv","id":"1908.04777","version":3},"attestation_state":"computed","paper":{"title":"Learn How to Cook a New Recipe in a New House: Using Map Familiarization, Curriculum Learning, and Bandit Feedback to Learn Families of Text-Based Adventure Games","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Jonathan May, Xusen Yin","submitted_at":"2019-08-13T17:48:10Z","abstract_excerpt":"We consider the task of learning to play families of text-based computer adventure games, i.e., fully textual environments with a common theme (e.g. cooking) and goal (e.g. prepare a meal from a recipe) but with different specifics; new instances of such games are relatively straightforward for humans to master after a brief exposure to the genre but have been curiously difficult for computer agents to learn. We find that the deep Q-learning strategies that have been successfully leveraged for superhuman performance in single-instance action video games can be applied to learn families of text"},"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":"1908.04777","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-08-13T17:48:10Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"800d40b4f632b96216edbb10560952e5e67d4a173b39700fecb36f3f815e2f4c","abstract_canon_sha256":"44829335da540d45c972add31d8405be937e9cc81cb7a4e7d87c811527743b70"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:56:29.726070Z","signature_b64":"0Pv5UxF0DEgSdvaXCJ538d+azYQhUhgebKONyXXpI+CzwSspS1VuIg+N1UeBnb5OhxkbE2K40V5+P9Somu/9Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2e9188fad427513955f90838fe0fc7049a3a43258060858aa11ecc896f3ac6bb","last_reissued_at":"2026-07-05T00:56:29.725681Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:56:29.725681Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learn How to Cook a New Recipe in a New House: Using Map Familiarization, Curriculum Learning, and Bandit Feedback to Learn Families of Text-Based Adventure Games","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Jonathan May, Xusen Yin","submitted_at":"2019-08-13T17:48:10Z","abstract_excerpt":"We consider the task of learning to play families of text-based computer adventure games, i.e., fully textual environments with a common theme (e.g. cooking) and goal (e.g. prepare a meal from a recipe) but with different specifics; new instances of such games are relatively straightforward for humans to master after a brief exposure to the genre but have been curiously difficult for computer agents to learn. We find that the deep Q-learning strategies that have been successfully leveraged for superhuman performance in single-instance action video games can be applied to learn families of text"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.04777","kind":"arxiv","version":3},"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/1908.04777/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":"1908.04777","created_at":"2026-07-05T00:56:29.725736+00:00"},{"alias_kind":"arxiv_version","alias_value":"1908.04777v3","created_at":"2026-07-05T00:56:29.725736+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.04777","created_at":"2026-07-05T00:56:29.725736+00:00"},{"alias_kind":"pith_short_12","alias_value":"F2IYR6WUE5IT","created_at":"2026-07-05T00:56:29.725736+00:00"},{"alias_kind":"pith_short_16","alias_value":"F2IYR6WUE5ITSVPZ","created_at":"2026-07-05T00:56:29.725736+00:00"},{"alias_kind":"pith_short_8","alias_value":"F2IYR6WU","created_at":"2026-07-05T00:56:29.725736+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/F2IYR6WUE5ITSVPZBA4P4D6HAS","json":"https://pith.science/pith/F2IYR6WUE5ITSVPZBA4P4D6HAS.json","graph_json":"https://pith.science/api/pith-number/F2IYR6WUE5ITSVPZBA4P4D6HAS/graph.json","events_json":"https://pith.science/api/pith-number/F2IYR6WUE5ITSVPZBA4P4D6HAS/events.json","paper":"https://pith.science/paper/F2IYR6WU"},"agent_actions":{"view_html":"https://pith.science/pith/F2IYR6WUE5ITSVPZBA4P4D6HAS","download_json":"https://pith.science/pith/F2IYR6WUE5ITSVPZBA4P4D6HAS.json","view_paper":"https://pith.science/paper/F2IYR6WU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1908.04777&json=true","fetch_graph":"https://pith.science/api/pith-number/F2IYR6WUE5ITSVPZBA4P4D6HAS/graph.json","fetch_events":"https://pith.science/api/pith-number/F2IYR6WUE5ITSVPZBA4P4D6HAS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/F2IYR6WUE5ITSVPZBA4P4D6HAS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/F2IYR6WUE5ITSVPZBA4P4D6HAS/action/storage_attestation","attest_author":"https://pith.science/pith/F2IYR6WUE5ITSVPZBA4P4D6HAS/action/author_attestation","sign_citation":"https://pith.science/pith/F2IYR6WUE5ITSVPZBA4P4D6HAS/action/citation_signature","submit_replication":"https://pith.science/pith/F2IYR6WUE5ITSVPZBA4P4D6HAS/action/replication_record"}},"created_at":"2026-07-05T00:56:29.725736+00:00","updated_at":"2026-07-05T00:56:29.725736+00:00"}