{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:PTEVKBKGA2SGFCZ4RJETJXGOOW","short_pith_number":"pith:PTEVKBKG","schema_version":"1.0","canonical_sha256":"7cc955054606a4628b3c8a4934dcce75b66c6cfefed8c13fc429c9ffffc22255","source":{"kind":"arxiv","id":"2011.00517","version":3},"attestation_state":"computed","paper":{"title":"Ask Your Humans: Using Human Instructions to Improve Generalization in Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Abhinav Gupta, Kenneth Marino, Valerie Chen","submitted_at":"2020-11-01T14:39:46Z","abstract_excerpt":"Complex, multi-task problems have proven to be difficult to solve efficiently in a sparse-reward reinforcement learning setting. In order to be sample efficient, multi-task learning requires reuse and sharing of low-level policies. To facilitate the automatic decomposition of hierarchical tasks, we propose the use of step-by-step human demonstrations in the form of natural language instructions and action trajectories. We introduce a dataset of such demonstrations in a crafting-based grid world. Our model consists of a high-level language generator and low-level policy, conditioned on language"},"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":"2011.00517","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2020-11-01T14:39:46Z","cross_cats_sorted":[],"title_canon_sha256":"e935d29fa2daab510cca93d322ef87bfba44b1c534a329fb93e723518c2d000f","abstract_canon_sha256":"bfe37d6cb2e4468e5b75d7a70d7c76e2574151fa504428f979cdaf2cd5eebc5b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:17:29.264884Z","signature_b64":"CzQUa962fLMdwITbNdbLyV3RGRm1hFERnCLNWofLkXG8Tre3IA/kgIX7WAUfybtqs/FgmtbiDFHKqVvCVF2lAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7cc955054606a4628b3c8a4934dcce75b66c6cfefed8c13fc429c9ffffc22255","last_reissued_at":"2026-07-05T03:17:29.264479Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:17:29.264479Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Ask Your Humans: Using Human Instructions to Improve Generalization in Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Abhinav Gupta, Kenneth Marino, Valerie Chen","submitted_at":"2020-11-01T14:39:46Z","abstract_excerpt":"Complex, multi-task problems have proven to be difficult to solve efficiently in a sparse-reward reinforcement learning setting. In order to be sample efficient, multi-task learning requires reuse and sharing of low-level policies. To facilitate the automatic decomposition of hierarchical tasks, we propose the use of step-by-step human demonstrations in the form of natural language instructions and action trajectories. We introduce a dataset of such demonstrations in a crafting-based grid world. Our model consists of a high-level language generator and low-level policy, conditioned on language"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.00517","kind":"arxiv","version":3},"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/2011.00517/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":"2011.00517","created_at":"2026-07-05T03:17:29.264534+00:00"},{"alias_kind":"arxiv_version","alias_value":"2011.00517v3","created_at":"2026-07-05T03:17:29.264534+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.00517","created_at":"2026-07-05T03:17:29.264534+00:00"},{"alias_kind":"pith_short_12","alias_value":"PTEVKBKGA2SG","created_at":"2026-07-05T03:17:29.264534+00:00"},{"alias_kind":"pith_short_16","alias_value":"PTEVKBKGA2SGFCZ4","created_at":"2026-07-05T03:17:29.264534+00:00"},{"alias_kind":"pith_short_8","alias_value":"PTEVKBKG","created_at":"2026-07-05T03:17:29.264534+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2602.06974","citing_title":"FeudalNav: A Simple Framework for Visual Navigation","ref_index":16,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PTEVKBKGA2SGFCZ4RJETJXGOOW","json":"https://pith.science/pith/PTEVKBKGA2SGFCZ4RJETJXGOOW.json","graph_json":"https://pith.science/api/pith-number/PTEVKBKGA2SGFCZ4RJETJXGOOW/graph.json","events_json":"https://pith.science/api/pith-number/PTEVKBKGA2SGFCZ4RJETJXGOOW/events.json","paper":"https://pith.science/paper/PTEVKBKG"},"agent_actions":{"view_html":"https://pith.science/pith/PTEVKBKGA2SGFCZ4RJETJXGOOW","download_json":"https://pith.science/pith/PTEVKBKGA2SGFCZ4RJETJXGOOW.json","view_paper":"https://pith.science/paper/PTEVKBKG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2011.00517&json=true","fetch_graph":"https://pith.science/api/pith-number/PTEVKBKGA2SGFCZ4RJETJXGOOW/graph.json","fetch_events":"https://pith.science/api/pith-number/PTEVKBKGA2SGFCZ4RJETJXGOOW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PTEVKBKGA2SGFCZ4RJETJXGOOW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PTEVKBKGA2SGFCZ4RJETJXGOOW/action/storage_attestation","attest_author":"https://pith.science/pith/PTEVKBKGA2SGFCZ4RJETJXGOOW/action/author_attestation","sign_citation":"https://pith.science/pith/PTEVKBKGA2SGFCZ4RJETJXGOOW/action/citation_signature","submit_replication":"https://pith.science/pith/PTEVKBKGA2SGFCZ4RJETJXGOOW/action/replication_record"}},"created_at":"2026-07-05T03:17:29.264534+00:00","updated_at":"2026-07-05T03:17:29.264534+00:00"}