{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:DMDYFWUIYIWCENDR3YGL54DJDM","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":"8b3f3632d943d93ab7b256f4041ea3345f278856036d10452c011e58a5791d3a","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-10-18T00:49:15Z","title_canon_sha256":"a1275882bece149fb2276a83d42cdcc3cbc4588ab8d668c915b4419fe22eaa8d"},"schema_version":"1.0","source":{"id":"1910.08210","kind":"arxiv","version":6}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1910.08210","created_at":"2026-07-05T02:11:20Z"},{"alias_kind":"arxiv_version","alias_value":"1910.08210v6","created_at":"2026-07-05T02:11:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.08210","created_at":"2026-07-05T02:11:20Z"},{"alias_kind":"pith_short_12","alias_value":"DMDYFWUIYIWC","created_at":"2026-07-05T02:11:20Z"},{"alias_kind":"pith_short_16","alias_value":"DMDYFWUIYIWCENDR","created_at":"2026-07-05T02:11:20Z"},{"alias_kind":"pith_short_8","alias_value":"DMDYFWUI","created_at":"2026-07-05T02:11:20Z"}],"graph_snapshots":[{"event_id":"sha256:af688d27e57bfb005e96395d1955a245b1638738bb108dc388abdab6d4ab9314","target":"graph","created_at":"2026-07-05T02:11:20Z","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/1910.08210/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Obtaining policies that can generalise to new environments in reinforcement learning is challenging. In this work, we demonstrate that language understanding via a reading policy learner is a promising vehicle for generalisation to new environments. We propose a grounded policy learning problem, Read to Fight Monsters (RTFM), in which the agent must jointly reason over a language goal, relevant dynamics described in a document, and environment observations. We procedurally generate environment dynamics and corresponding language descriptions of the dynamics, such that agents must read to under","authors_text":"Edward Grefenstette, Tim Rockt\\\"aschel, Victor Zhong","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-10-18T00:49:15Z","title":"RTFM: Generalising to Novel Environment Dynamics via Reading"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1910.08210","kind":"arxiv","version":6},"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:c434d429791d078d852f178d7f6f0b71f83bffb878a9f6068dd37c7f72ed90e1","target":"record","created_at":"2026-07-05T02:11:20Z","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":"8b3f3632d943d93ab7b256f4041ea3345f278856036d10452c011e58a5791d3a","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-10-18T00:49:15Z","title_canon_sha256":"a1275882bece149fb2276a83d42cdcc3cbc4588ab8d668c915b4419fe22eaa8d"},"schema_version":"1.0","source":{"id":"1910.08210","kind":"arxiv","version":6}},"canonical_sha256":"1b0782da88c22c223471de0cbef0691b13783db573a56f0883e4313087028ad3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1b0782da88c22c223471de0cbef0691b13783db573a56f0883e4313087028ad3","first_computed_at":"2026-07-05T02:11:20.150198Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:11:20.150198Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"P95ZSprbpds8xCjpmi9PUbp2AEC2qzB6Y+wdLDxI+R0TDfSybkvdrK6zsahVTLk2tEXgsNA+4UlwkYsLms09Dw==","signature_status":"signed_v1","signed_at":"2026-07-05T02:11:20.150607Z","signed_message":"canonical_sha256_bytes"},"source_id":"1910.08210","source_kind":"arxiv","source_version":6}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c434d429791d078d852f178d7f6f0b71f83bffb878a9f6068dd37c7f72ed90e1","sha256:af688d27e57bfb005e96395d1955a245b1638738bb108dc388abdab6d4ab9314"],"state_sha256":"d30ae7e1895901a72e42c422e4eb93baf87c5aa39ff72a3d944b7c7d2f4e6999"}