{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:EUZ32MFB2LY26WQJQUX2YYME3O","short_pith_number":"pith:EUZ32MFB","schema_version":"1.0","canonical_sha256":"2533bd30a1d2f1af5a09852fac6184db95b51d134812d076e3dd0ab1cdc81f86","source":{"kind":"arxiv","id":"2411.19787","version":2},"attestation_state":"computed","paper":{"title":"CAREL: Instruction-guided reinforcement learning with cross-modal auxiliary objectives","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Amirmohammad Izadi, Armin Saghafian, Mahdieh Soleymani Baghshah, Negin Hashemi Dijujin","submitted_at":"2024-11-29T15:49:06Z","abstract_excerpt":"Grounding the instruction in the environment is a key step in solving language-guided goal-reaching reinforcement learning problems. In automated reinforcement learning, a key concern is to enhance the model's ability to generalize across various tasks and environments. In goal-reaching scenarios, the agent must comprehend the different parts of the instructions within the environmental context in order to complete the overall task successfully. In this work, we propose CAREL (Cross-modal Auxiliary REinforcement Learning) as a new framework to solve this problem using auxiliary loss functions "},"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":"2411.19787","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-29T15:49:06Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"eabdda0ce17043bfd42a70c6a1f4074538f095a6d420e4b58e2ae93a265f60ea","abstract_canon_sha256":"2bc2fae2469867694a10e8fd15d461779c9b49a6eda29b14c77313baf7adb163"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:06:03.593433Z","signature_b64":"uwWLCrzpWAihkSqeFNZH+xarQ76QSszq2ew40fSEE2R9aE73ytllg1T3hXTghqYO7vMiprCyn3cc5vTu+bDwBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2533bd30a1d2f1af5a09852fac6184db95b51d134812d076e3dd0ab1cdc81f86","last_reissued_at":"2026-07-05T12:06:03.593009Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:06:03.593009Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CAREL: Instruction-guided reinforcement learning with cross-modal auxiliary objectives","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Amirmohammad Izadi, Armin Saghafian, Mahdieh Soleymani Baghshah, Negin Hashemi Dijujin","submitted_at":"2024-11-29T15:49:06Z","abstract_excerpt":"Grounding the instruction in the environment is a key step in solving language-guided goal-reaching reinforcement learning problems. In automated reinforcement learning, a key concern is to enhance the model's ability to generalize across various tasks and environments. In goal-reaching scenarios, the agent must comprehend the different parts of the instructions within the environmental context in order to complete the overall task successfully. In this work, we propose CAREL (Cross-modal Auxiliary REinforcement Learning) as a new framework to solve this problem using auxiliary loss functions "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.19787","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2411.19787/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":"2411.19787","created_at":"2026-07-05T12:06:03.593068+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.19787v2","created_at":"2026-07-05T12:06:03.593068+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.19787","created_at":"2026-07-05T12:06:03.593068+00:00"},{"alias_kind":"pith_short_12","alias_value":"EUZ32MFB2LY2","created_at":"2026-07-05T12:06:03.593068+00:00"},{"alias_kind":"pith_short_16","alias_value":"EUZ32MFB2LY26WQJ","created_at":"2026-07-05T12:06:03.593068+00:00"},{"alias_kind":"pith_short_8","alias_value":"EUZ32MFB","created_at":"2026-07-05T12:06:03.593068+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/EUZ32MFB2LY26WQJQUX2YYME3O","json":"https://pith.science/pith/EUZ32MFB2LY26WQJQUX2YYME3O.json","graph_json":"https://pith.science/api/pith-number/EUZ32MFB2LY26WQJQUX2YYME3O/graph.json","events_json":"https://pith.science/api/pith-number/EUZ32MFB2LY26WQJQUX2YYME3O/events.json","paper":"https://pith.science/paper/EUZ32MFB"},"agent_actions":{"view_html":"https://pith.science/pith/EUZ32MFB2LY26WQJQUX2YYME3O","download_json":"https://pith.science/pith/EUZ32MFB2LY26WQJQUX2YYME3O.json","view_paper":"https://pith.science/paper/EUZ32MFB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.19787&json=true","fetch_graph":"https://pith.science/api/pith-number/EUZ32MFB2LY26WQJQUX2YYME3O/graph.json","fetch_events":"https://pith.science/api/pith-number/EUZ32MFB2LY26WQJQUX2YYME3O/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EUZ32MFB2LY26WQJQUX2YYME3O/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EUZ32MFB2LY26WQJQUX2YYME3O/action/storage_attestation","attest_author":"https://pith.science/pith/EUZ32MFB2LY26WQJQUX2YYME3O/action/author_attestation","sign_citation":"https://pith.science/pith/EUZ32MFB2LY26WQJQUX2YYME3O/action/citation_signature","submit_replication":"https://pith.science/pith/EUZ32MFB2LY26WQJQUX2YYME3O/action/replication_record"}},"created_at":"2026-07-05T12:06:03.593068+00:00","updated_at":"2026-07-05T12:06:03.593068+00:00"}