{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:RSGTTCCX5X63WHVPTP6GW2OWWB","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":"174ff20f58f1eb56dc423c561b5760964fa959754d77071cbbe4bdaff7af4c1e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-01-04T17:19:52Z","title_canon_sha256":"c382bdbc48f00bdff623dae4f5b7e273857dc9aabb7aa731e41f0687c9fa8063"},"schema_version":"1.0","source":{"id":"2201.01251","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2201.01251","created_at":"2026-07-05T04:05:37Z"},{"alias_kind":"arxiv_version","alias_value":"2201.01251v3","created_at":"2026-07-05T04:05:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.01251","created_at":"2026-07-05T04:05:37Z"},{"alias_kind":"pith_short_12","alias_value":"RSGTTCCX5X63","created_at":"2026-07-05T04:05:37Z"},{"alias_kind":"pith_short_16","alias_value":"RSGTTCCX5X63WHVP","created_at":"2026-07-05T04:05:37Z"},{"alias_kind":"pith_short_8","alias_value":"RSGTTCCX","created_at":"2026-07-05T04:05:37Z"}],"graph_snapshots":[{"event_id":"sha256:6c80d5d347eb1aa61fc3d0db16fbf3c725d4506d1cab8b1bad749c6acff86813","target":"graph","created_at":"2026-07-05T04:05:37Z","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/2201.01251/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Text adventure games present unique challenges to reinforcement learning methods due to their combinatorially large action spaces and sparse rewards. The interplay of these two factors is particularly demanding because large action spaces require extensive exploration, while sparse rewards provide limited feedback. This work proposes to tackle the explore-vs-exploit dilemma using a multi-stage approach that explicitly disentangles these two strategies within each episode. Our algorithm, called eXploit-Then-eXplore (XTX), begins each episode using an exploitation policy that imitates a set of p","authors_text":"Jens Tuyls, Karthik Narasimhan, Sham Kakade, Shunyu Yao","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-01-04T17:19:52Z","title":"Multi-Stage Episodic Control for Strategic Exploration in Text Games"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.01251","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:ce32df757997e2d5febabf7333a817d313d6928ecdb3bc98d4c40dc770b997c2","target":"record","created_at":"2026-07-05T04:05:37Z","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":"174ff20f58f1eb56dc423c561b5760964fa959754d77071cbbe4bdaff7af4c1e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-01-04T17:19:52Z","title_canon_sha256":"c382bdbc48f00bdff623dae4f5b7e273857dc9aabb7aa731e41f0687c9fa8063"},"schema_version":"1.0","source":{"id":"2201.01251","kind":"arxiv","version":3}},"canonical_sha256":"8c8d398857edfdbb1eaf9bfc6b69d6b065331ec85bbc345a16fe2de86f87cea7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8c8d398857edfdbb1eaf9bfc6b69d6b065331ec85bbc345a16fe2de86f87cea7","first_computed_at":"2026-07-05T04:05:37.959604Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:05:37.959604Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"isLCMTI5XH0Rs4jX3fYYACU6rg8wQFIEeTTKbK90RTfgxnKEKUyt1Erd2yZEEEF8EbGhal9p7aO7tgzT1wMVDA==","signature_status":"signed_v1","signed_at":"2026-07-05T04:05:37.960031Z","signed_message":"canonical_sha256_bytes"},"source_id":"2201.01251","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ce32df757997e2d5febabf7333a817d313d6928ecdb3bc98d4c40dc770b997c2","sha256:6c80d5d347eb1aa61fc3d0db16fbf3c725d4506d1cab8b1bad749c6acff86813"],"state_sha256":"3b626e25d9d1cfa2ce48843d1d596a9432c9d596c5aec518eac4c630bbe4c2a3"}