{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:V4HTRK3FDJ67H6RKQL5WYOLFRW","short_pith_number":"pith:V4HTRK3F","schema_version":"1.0","canonical_sha256":"af0f38ab651a7df3fa2a82fb6c39658da7d3a9761a9f817a18809a8d924b6ad6","source":{"kind":"arxiv","id":"2303.05069","version":1},"attestation_state":"computed","paper":{"title":"Conceptual Reinforcement Learning for Language-Conditioned Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jiaming Guo, Ling Li, Qi Guo, Qi Yi, Rui Zhang, Ruizhi Chen, Shaohui Peng, Xing Hu, Yunji Chen, Zidong Du","submitted_at":"2023-03-09T07:01:06Z","abstract_excerpt":"Despite the broad application of deep reinforcement learning (RL), transferring and adapting the policy to unseen but similar environments is still a significant challenge. Recently, the language-conditioned policy is proposed to facilitate policy transfer through learning the joint representation of observation and text that catches the compact and invariant information across environments. Existing studies of language-conditioned RL methods often learn the joint representation as a simple latent layer for the given instances (episode-specific observation and text), which inevitably includes "},"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":"2303.05069","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-03-09T07:01:06Z","cross_cats_sorted":[],"title_canon_sha256":"ef47c082f04e1e1d306685428e3e36556e4a5a49e9a1fac5f40accd24a5d0b20","abstract_canon_sha256":"3c52a168be7bd54b414f321141d2f416de9dbb5eda12e150e7b59b6cd95f1017"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:49:36.965823Z","signature_b64":"Kzn1dN4Y6/Nk36MvSgVtcbSjOnDFo/3rjU2MFF0DXq5PnCWwS9WTQxSJzKs5N93aqmcTz3mpExhzxuOcDGzjBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"af0f38ab651a7df3fa2a82fb6c39658da7d3a9761a9f817a18809a8d924b6ad6","last_reissued_at":"2026-07-05T05:49:36.965484Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:49:36.965484Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Conceptual Reinforcement Learning for Language-Conditioned Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jiaming Guo, Ling Li, Qi Guo, Qi Yi, Rui Zhang, Ruizhi Chen, Shaohui Peng, Xing Hu, Yunji Chen, Zidong Du","submitted_at":"2023-03-09T07:01:06Z","abstract_excerpt":"Despite the broad application of deep reinforcement learning (RL), transferring and adapting the policy to unseen but similar environments is still a significant challenge. Recently, the language-conditioned policy is proposed to facilitate policy transfer through learning the joint representation of observation and text that catches the compact and invariant information across environments. Existing studies of language-conditioned RL methods often learn the joint representation as a simple latent layer for the given instances (episode-specific observation and text), which inevitably includes "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.05069","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/2303.05069/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":"2303.05069","created_at":"2026-07-05T05:49:36.965533+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.05069v1","created_at":"2026-07-05T05:49:36.965533+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.05069","created_at":"2026-07-05T05:49:36.965533+00:00"},{"alias_kind":"pith_short_12","alias_value":"V4HTRK3FDJ67","created_at":"2026-07-05T05:49:36.965533+00:00"},{"alias_kind":"pith_short_16","alias_value":"V4HTRK3FDJ67H6RK","created_at":"2026-07-05T05:49:36.965533+00:00"},{"alias_kind":"pith_short_8","alias_value":"V4HTRK3F","created_at":"2026-07-05T05:49:36.965533+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/V4HTRK3FDJ67H6RKQL5WYOLFRW","json":"https://pith.science/pith/V4HTRK3FDJ67H6RKQL5WYOLFRW.json","graph_json":"https://pith.science/api/pith-number/V4HTRK3FDJ67H6RKQL5WYOLFRW/graph.json","events_json":"https://pith.science/api/pith-number/V4HTRK3FDJ67H6RKQL5WYOLFRW/events.json","paper":"https://pith.science/paper/V4HTRK3F"},"agent_actions":{"view_html":"https://pith.science/pith/V4HTRK3FDJ67H6RKQL5WYOLFRW","download_json":"https://pith.science/pith/V4HTRK3FDJ67H6RKQL5WYOLFRW.json","view_paper":"https://pith.science/paper/V4HTRK3F","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.05069&json=true","fetch_graph":"https://pith.science/api/pith-number/V4HTRK3FDJ67H6RKQL5WYOLFRW/graph.json","fetch_events":"https://pith.science/api/pith-number/V4HTRK3FDJ67H6RKQL5WYOLFRW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/V4HTRK3FDJ67H6RKQL5WYOLFRW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/V4HTRK3FDJ67H6RKQL5WYOLFRW/action/storage_attestation","attest_author":"https://pith.science/pith/V4HTRK3FDJ67H6RKQL5WYOLFRW/action/author_attestation","sign_citation":"https://pith.science/pith/V4HTRK3FDJ67H6RKQL5WYOLFRW/action/citation_signature","submit_replication":"https://pith.science/pith/V4HTRK3FDJ67H6RKQL5WYOLFRW/action/replication_record"}},"created_at":"2026-07-05T05:49:36.965533+00:00","updated_at":"2026-07-05T05:49:36.965533+00:00"}