{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:KRVL4OZOYYZ52RRNO2XVFWETQ3","short_pith_number":"pith:KRVL4OZO","schema_version":"1.0","canonical_sha256":"546abe3b2ec633dd462d76af52d89386c730c7f08d5a1f8a50326919a6336472","source":{"kind":"arxiv","id":"1806.11525","version":2},"attestation_state":"computed","paper":{"title":"Counting to Explore and Generalize in Text-based Games","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Adam Trischler, Alessandro Sordoni, Marc-Alexandre C\\^ot\\'e, Matthew Hausknecht, Remi Tachet des Combes, Romain Laroche, Xingdi Yuan","submitted_at":"2018-06-29T16:40:29Z","abstract_excerpt":"We propose a recurrent RL agent with an episodic exploration mechanism that helps discovering good policies in text-based game environments. We show promising results on a set of generated text-based games of varying difficulty where the goal is to collect a coin located at the end of a chain of rooms. In contrast to previous text-based RL approaches, we observe that our agent learns policies that generalize to unseen games of greater difficulty."},"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":"1806.11525","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-06-29T16:40:29Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"6cc6acb799843d0eb00476f4d98736c131d740c24e8d2eda75c72713dacb4262","abstract_canon_sha256":"8215e7961293b7e37f417cf67c343f6deb53e192cb35ecad5a6a681a7aa56f02"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:51:54.462406Z","signature_b64":"LeHKUl3T0JDvHPyrOt7515u5x46EeX0p8Z6uqe82E77t7NCDHlTp5GWdWNzfLchT8rIQv7ph9Mf7BCVNnI+YAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"546abe3b2ec633dd462d76af52d89386c730c7f08d5a1f8a50326919a6336472","last_reissued_at":"2026-05-17T23:51:54.461994Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:51:54.461994Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Counting to Explore and Generalize in Text-based Games","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Adam Trischler, Alessandro Sordoni, Marc-Alexandre C\\^ot\\'e, Matthew Hausknecht, Remi Tachet des Combes, Romain Laroche, Xingdi Yuan","submitted_at":"2018-06-29T16:40:29Z","abstract_excerpt":"We propose a recurrent RL agent with an episodic exploration mechanism that helps discovering good policies in text-based game environments. We show promising results on a set of generated text-based games of varying difficulty where the goal is to collect a coin located at the end of a chain of rooms. In contrast to previous text-based RL approaches, we observe that our agent learns policies that generalize to unseen games of greater difficulty."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.11525","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1806.11525","created_at":"2026-05-17T23:51:54.462053+00:00"},{"alias_kind":"arxiv_version","alias_value":"1806.11525v2","created_at":"2026-05-17T23:51:54.462053+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.11525","created_at":"2026-05-17T23:51:54.462053+00:00"},{"alias_kind":"pith_short_12","alias_value":"KRVL4OZOYYZ5","created_at":"2026-05-18T12:32:33.847187+00:00"},{"alias_kind":"pith_short_16","alias_value":"KRVL4OZOYYZ52RRN","created_at":"2026-05-18T12:32:33.847187+00:00"},{"alias_kind":"pith_short_8","alias_value":"KRVL4OZO","created_at":"2026-05-18T12:32:33.847187+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2010.03768","citing_title":"ALFWorld: Aligning Text and Embodied Environments for Interactive Learning","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KRVL4OZOYYZ52RRNO2XVFWETQ3","json":"https://pith.science/pith/KRVL4OZOYYZ52RRNO2XVFWETQ3.json","graph_json":"https://pith.science/api/pith-number/KRVL4OZOYYZ52RRNO2XVFWETQ3/graph.json","events_json":"https://pith.science/api/pith-number/KRVL4OZOYYZ52RRNO2XVFWETQ3/events.json","paper":"https://pith.science/paper/KRVL4OZO"},"agent_actions":{"view_html":"https://pith.science/pith/KRVL4OZOYYZ52RRNO2XVFWETQ3","download_json":"https://pith.science/pith/KRVL4OZOYYZ52RRNO2XVFWETQ3.json","view_paper":"https://pith.science/paper/KRVL4OZO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1806.11525&json=true","fetch_graph":"https://pith.science/api/pith-number/KRVL4OZOYYZ52RRNO2XVFWETQ3/graph.json","fetch_events":"https://pith.science/api/pith-number/KRVL4OZOYYZ52RRNO2XVFWETQ3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KRVL4OZOYYZ52RRNO2XVFWETQ3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KRVL4OZOYYZ52RRNO2XVFWETQ3/action/storage_attestation","attest_author":"https://pith.science/pith/KRVL4OZOYYZ52RRNO2XVFWETQ3/action/author_attestation","sign_citation":"https://pith.science/pith/KRVL4OZOYYZ52RRNO2XVFWETQ3/action/citation_signature","submit_replication":"https://pith.science/pith/KRVL4OZOYYZ52RRNO2XVFWETQ3/action/replication_record"}},"created_at":"2026-05-17T23:51:54.462053+00:00","updated_at":"2026-05-17T23:51:54.462053+00:00"}