{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:KRVL4OZOYYZ52RRNO2XVFWETQ3","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":"8215e7961293b7e37f417cf67c343f6deb53e192cb35ecad5a6a681a7aa56f02","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-06-29T16:40:29Z","title_canon_sha256":"6cc6acb799843d0eb00476f4d98736c131d740c24e8d2eda75c72713dacb4262"},"schema_version":"1.0","source":{"id":"1806.11525","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1806.11525","created_at":"2026-05-17T23:51:54Z"},{"alias_kind":"arxiv_version","alias_value":"1806.11525v2","created_at":"2026-05-17T23:51:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.11525","created_at":"2026-05-17T23:51:54Z"},{"alias_kind":"pith_short_12","alias_value":"KRVL4OZOYYZ5","created_at":"2026-05-18T12:32:33Z"},{"alias_kind":"pith_short_16","alias_value":"KRVL4OZOYYZ52RRN","created_at":"2026-05-18T12:32:33Z"},{"alias_kind":"pith_short_8","alias_value":"KRVL4OZO","created_at":"2026-05-18T12:32:33Z"}],"graph_snapshots":[{"event_id":"sha256:13f56d008a749dcb42209482123ddfc1ce0652a3495812ad28f7556f92a811ee","target":"graph","created_at":"2026-05-17T23:51:54Z","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"},"paper":{"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.","authors_text":"Adam Trischler, Alessandro Sordoni, Marc-Alexandre C\\^ot\\'e, Matthew Hausknecht, Remi Tachet des Combes, Romain Laroche, Xingdi Yuan","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-06-29T16:40:29Z","title":"Counting to Explore and Generalize in Text-based Games"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.11525","kind":"arxiv","version":2},"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":"sha256:6c314c56d0fee5a681f91987093ecb5e15a64dfad2c2795e096b0ee9cad85b8f","target":"record","created_at":"2026-05-17T23:51:54Z","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":"8215e7961293b7e37f417cf67c343f6deb53e192cb35ecad5a6a681a7aa56f02","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-06-29T16:40:29Z","title_canon_sha256":"6cc6acb799843d0eb00476f4d98736c131d740c24e8d2eda75c72713dacb4262"},"schema_version":"1.0","source":{"id":"1806.11525","kind":"arxiv","version":2}},"canonical_sha256":"546abe3b2ec633dd462d76af52d89386c730c7f08d5a1f8a50326919a6336472","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"546abe3b2ec633dd462d76af52d89386c730c7f08d5a1f8a50326919a6336472","first_computed_at":"2026-05-17T23:51:54.461994Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:51:54.461994Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LeHKUl3T0JDvHPyrOt7515u5x46EeX0p8Z6uqe82E77t7NCDHlTp5GWdWNzfLchT8rIQv7ph9Mf7BCVNnI+YAQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:51:54.462406Z","signed_message":"canonical_sha256_bytes"},"source_id":"1806.11525","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6c314c56d0fee5a681f91987093ecb5e15a64dfad2c2795e096b0ee9cad85b8f","sha256:13f56d008a749dcb42209482123ddfc1ce0652a3495812ad28f7556f92a811ee"],"state_sha256":"0168f34ff42aded1602cf4f5e7e7ab3e79edae1c6c9eb6f3df57127f03e2ea19"}