{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:424ARYA7D7P3E42VKTACYASEOX","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":"c8ab882a614349529e0d6c8b2c0bb962490284df2eede35c5505cc5c71cbb123","cross_cats_sorted":["cs.CL","cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2020-06-12T18:24:06Z","title_canon_sha256":"2381db739867904714e8ef191c295e5454756a47d54bc704d0b4d5acb96c9d02"},"schema_version":"1.0","source":{"id":"2006.07409","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.07409","created_at":"2026-07-05T01:09:59Z"},{"alias_kind":"arxiv_version","alias_value":"2006.07409v1","created_at":"2026-07-05T01:09:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.07409","created_at":"2026-07-05T01:09:59Z"},{"alias_kind":"pith_short_12","alias_value":"424ARYA7D7P3","created_at":"2026-07-05T01:09:59Z"},{"alias_kind":"pith_short_16","alias_value":"424ARYA7D7P3E42V","created_at":"2026-07-05T01:09:59Z"},{"alias_kind":"pith_short_8","alias_value":"424ARYA7","created_at":"2026-07-05T01:09:59Z"}],"graph_snapshots":[{"event_id":"sha256:ed91fa74c94110ef3a50eaeb516390daf7ae1edaed85e3aab0940c69e275e391","target":"graph","created_at":"2026-07-05T01:09:59Z","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/2006.07409/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Text-based games are long puzzles or quests, characterized by a sequence of sparse and potentially deceptive rewards. They provide an ideal platform to develop agents that perceive and act upon the world using a combinatorially sized natural language state-action space. Standard Reinforcement Learning agents are poorly equipped to effectively explore such spaces and often struggle to overcome bottlenecks---states that agents are unable to pass through simply because they do not see the right action sequence enough times to be sufficiently reinforced. We introduce Q*BERT, an agent that learns t","authors_text":"Ethan Tien, Mark O. Riedl, Matthew Hausknecht, Prithviraj Ammanabrolu","cross_cats":["cs.CL","cs.LG","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2020-06-12T18:24:06Z","title":"How to Avoid Being Eaten by a Grue: Structured Exploration Strategies for Textual Worlds"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.07409","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":"sha256:3b770575c8a831c4df69c078338b0088814fe497ae3de75c151302ba38bb9925","target":"record","created_at":"2026-07-05T01:09:59Z","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":"c8ab882a614349529e0d6c8b2c0bb962490284df2eede35c5505cc5c71cbb123","cross_cats_sorted":["cs.CL","cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2020-06-12T18:24:06Z","title_canon_sha256":"2381db739867904714e8ef191c295e5454756a47d54bc704d0b4d5acb96c9d02"},"schema_version":"1.0","source":{"id":"2006.07409","kind":"arxiv","version":1}},"canonical_sha256":"e6b808e01f1fdfb2735554c02c024475f584864d8b63b4c0e0d3fb24b74212ad","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e6b808e01f1fdfb2735554c02c024475f584864d8b63b4c0e0d3fb24b74212ad","first_computed_at":"2026-07-05T01:09:59.831244Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:09:59.831244Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HcGxfk1bsS9N+jhm8XK1jAXTtcxpdeWtbDF4ucgUjsy090cJ0kHn3Mv2/K1mIjeepON75rr/UV7mDpRx+bLWCw==","signature_status":"signed_v1","signed_at":"2026-07-05T01:09:59.831602Z","signed_message":"canonical_sha256_bytes"},"source_id":"2006.07409","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3b770575c8a831c4df69c078338b0088814fe497ae3de75c151302ba38bb9925","sha256:ed91fa74c94110ef3a50eaeb516390daf7ae1edaed85e3aab0940c69e275e391"],"state_sha256":"8624059b9d59a4edd99d3e086d5a64cd50a5a0c29c04aa5be1157b31e3e595cf"}