{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:F2IYR6WUE5ITSVPZBA4P4D6HAS","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":"44829335da540d45c972add31d8405be937e9cc81cb7a4e7d87c811527743b70","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-08-13T17:48:10Z","title_canon_sha256":"800d40b4f632b96216edbb10560952e5e67d4a173b39700fecb36f3f815e2f4c"},"schema_version":"1.0","source":{"id":"1908.04777","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1908.04777","created_at":"2026-07-05T00:56:29Z"},{"alias_kind":"arxiv_version","alias_value":"1908.04777v3","created_at":"2026-07-05T00:56:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.04777","created_at":"2026-07-05T00:56:29Z"},{"alias_kind":"pith_short_12","alias_value":"F2IYR6WUE5IT","created_at":"2026-07-05T00:56:29Z"},{"alias_kind":"pith_short_16","alias_value":"F2IYR6WUE5ITSVPZ","created_at":"2026-07-05T00:56:29Z"},{"alias_kind":"pith_short_8","alias_value":"F2IYR6WU","created_at":"2026-07-05T00:56:29Z"}],"graph_snapshots":[{"event_id":"sha256:3d658325ba4685e957fd577304b0197696499f4ac372d8b30e0bc8cfefa3ad83","target":"graph","created_at":"2026-07-05T00:56:29Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/1908.04777/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Jonathan May, Xusen Yin","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-08-13T17:48:10Z","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"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.04777","kind":"arxiv","version":3},"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":"sha256:728cab3c2c91ea3a8f20068c16d41a728b3a176c933a860ce2155cbeef4545c7","target":"record","created_at":"2026-07-05T00:56:29Z","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":"44829335da540d45c972add31d8405be937e9cc81cb7a4e7d87c811527743b70","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-08-13T17:48:10Z","title_canon_sha256":"800d40b4f632b96216edbb10560952e5e67d4a173b39700fecb36f3f815e2f4c"},"schema_version":"1.0","source":{"id":"1908.04777","kind":"arxiv","version":3}},"canonical_sha256":"2e9188fad427513955f90838fe0fc7049a3a43258060858aa11ecc896f3ac6bb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2e9188fad427513955f90838fe0fc7049a3a43258060858aa11ecc896f3ac6bb","first_computed_at":"2026-07-05T00:56:29.725681Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:56:29.725681Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0Pv5UxF0DEgSdvaXCJ538d+azYQhUhgebKONyXXpI+CzwSspS1VuIg+N1UeBnb5OhxkbE2K40V5+P9Somu/9Ag==","signature_status":"signed_v1","signed_at":"2026-07-05T00:56:29.726070Z","signed_message":"canonical_sha256_bytes"},"source_id":"1908.04777","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:728cab3c2c91ea3a8f20068c16d41a728b3a176c933a860ce2155cbeef4545c7","sha256:3d658325ba4685e957fd577304b0197696499f4ac372d8b30e0bc8cfefa3ad83"],"state_sha256":"ef701d4e61430330870e3b170fe175f555d36fc46da2c6cd0ca8622d773ec5d8"}