{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:KBNHSZUZ35EQYNVWQFSAFU35F5","short_pith_number":"pith:KBNHSZUZ","schema_version":"1.0","canonical_sha256":"505a796699df490c36b6816402d37d2f723dc8f9d58b56c1bf6b51f5d72bb140","source":{"kind":"arxiv","id":"2403.03141","version":1},"attestation_state":"computed","paper":{"title":"Language Guided Exploration for RL Agents in Text Environments","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dhruvesh Patel, Hitesh Golchha, Keerthiram Murugesan, Sahil Yerawar, Soham Dan","submitted_at":"2024-03-05T17:26:41Z","abstract_excerpt":"Real-world sequential decision making is characterized by sparse rewards and large decision spaces, posing significant difficulty for experiential learning systems like $\\textit{tabula rasa}$ reinforcement learning (RL) agents. Large Language Models (LLMs), with a wealth of world knowledge, can help RL agents learn quickly and adapt to distribution shifts. In this work, we introduce Language Guided Exploration (LGE) framework, which uses a pre-trained language model (called GUIDE ) to provide decision-level guidance to an RL agent (called EXPLORER). We observe that on ScienceWorld (Wang et al."},"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":"2403.03141","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-05T17:26:41Z","cross_cats_sorted":[],"title_canon_sha256":"5102f5471f9ad6324e491571a43d7acd6261a059529c2efa73104d7d8c0b9ae2","abstract_canon_sha256":"0e93e8ef22252a298bbb8fc2208d212bee3be68716ec11bfaba09b76d87f2a75"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:52:36.527893Z","signature_b64":"8I1npYdf7DjQ/ZLzHNoM546kX+6G5zQtfl4H65KgLDE8g/tJKHa4ttx9nGPxJDUlHEzhIHQ/SmbWHzyELt4sBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"505a796699df490c36b6816402d37d2f723dc8f9d58b56c1bf6b51f5d72bb140","last_reissued_at":"2026-07-05T07:52:36.527550Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:52:36.527550Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Language Guided Exploration for RL Agents in Text Environments","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dhruvesh Patel, Hitesh Golchha, Keerthiram Murugesan, Sahil Yerawar, Soham Dan","submitted_at":"2024-03-05T17:26:41Z","abstract_excerpt":"Real-world sequential decision making is characterized by sparse rewards and large decision spaces, posing significant difficulty for experiential learning systems like $\\textit{tabula rasa}$ reinforcement learning (RL) agents. Large Language Models (LLMs), with a wealth of world knowledge, can help RL agents learn quickly and adapt to distribution shifts. In this work, we introduce Language Guided Exploration (LGE) framework, which uses a pre-trained language model (called GUIDE ) to provide decision-level guidance to an RL agent (called EXPLORER). We observe that on ScienceWorld (Wang et al."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.03141","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2403.03141/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2403.03141","created_at":"2026-07-05T07:52:36.527606+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.03141v1","created_at":"2026-07-05T07:52:36.527606+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.03141","created_at":"2026-07-05T07:52:36.527606+00:00"},{"alias_kind":"pith_short_12","alias_value":"KBNHSZUZ35EQ","created_at":"2026-07-05T07:52:36.527606+00:00"},{"alias_kind":"pith_short_16","alias_value":"KBNHSZUZ35EQYNVW","created_at":"2026-07-05T07:52:36.527606+00:00"},{"alias_kind":"pith_short_8","alias_value":"KBNHSZUZ","created_at":"2026-07-05T07:52:36.527606+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.19532","citing_title":"Fox in the Henhouse: Supply-Chain Backdoor Attacks Against Reinforcement Learning","ref_index":19,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KBNHSZUZ35EQYNVWQFSAFU35F5","json":"https://pith.science/pith/KBNHSZUZ35EQYNVWQFSAFU35F5.json","graph_json":"https://pith.science/api/pith-number/KBNHSZUZ35EQYNVWQFSAFU35F5/graph.json","events_json":"https://pith.science/api/pith-number/KBNHSZUZ35EQYNVWQFSAFU35F5/events.json","paper":"https://pith.science/paper/KBNHSZUZ"},"agent_actions":{"view_html":"https://pith.science/pith/KBNHSZUZ35EQYNVWQFSAFU35F5","download_json":"https://pith.science/pith/KBNHSZUZ35EQYNVWQFSAFU35F5.json","view_paper":"https://pith.science/paper/KBNHSZUZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.03141&json=true","fetch_graph":"https://pith.science/api/pith-number/KBNHSZUZ35EQYNVWQFSAFU35F5/graph.json","fetch_events":"https://pith.science/api/pith-number/KBNHSZUZ35EQYNVWQFSAFU35F5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KBNHSZUZ35EQYNVWQFSAFU35F5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KBNHSZUZ35EQYNVWQFSAFU35F5/action/storage_attestation","attest_author":"https://pith.science/pith/KBNHSZUZ35EQYNVWQFSAFU35F5/action/author_attestation","sign_citation":"https://pith.science/pith/KBNHSZUZ35EQYNVWQFSAFU35F5/action/citation_signature","submit_replication":"https://pith.science/pith/KBNHSZUZ35EQYNVWQFSAFU35F5/action/replication_record"}},"created_at":"2026-07-05T07:52:36.527606+00:00","updated_at":"2026-07-05T07:52:36.527606+00:00"}