{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:ZQX47IVFMPFOMHSKWZAIDYRPCP","short_pith_number":"pith:ZQX47IVF","schema_version":"1.0","canonical_sha256":"cc2fcfa2a563cae61e4ab64081e22f13c05d940334e60571d445e1a69d4bf059","source":{"kind":"arxiv","id":"1704.08795","version":2},"attestation_state":"computed","paper":{"title":"Mapping Instructions and Visual Observations to Actions with Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dipendra Misra, John Langford, Yoav Artzi","submitted_at":"2017-04-28T03:12:57Z","abstract_excerpt":"We propose to directly map raw visual observations and text input to actions for instruction execution. While existing approaches assume access to structured environment representations or use a pipeline of separately trained models, we learn a single model to jointly reason about linguistic and visual input. We use reinforcement learning in a contextual bandit setting to train a neural network agent. To guide the agent's exploration, we use reward shaping with different forms of supervision. Our approach does not require intermediate representations, planning procedures, or training different"},"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":"1704.08795","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-04-28T03:12:57Z","cross_cats_sorted":[],"title_canon_sha256":"8e34a3c7f9fb07066a09b3a6a5df381e64d8d554a8b380a3ab8126950827be8a","abstract_canon_sha256":"47c8849d09eb0d85ad3bd474abeb22858f068445c1b133f2fcc662b42fda2f11"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:39:46.269390Z","signature_b64":"2q3O9vmuHZPGDvLqPPxJ9B2mqJg/04S0JmkoZEudOXi2kRKsypgBmM6wqtcgzXDu5Mk47KqigoC5GYgB+b5HCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cc2fcfa2a563cae61e4ab64081e22f13c05d940334e60571d445e1a69d4bf059","last_reissued_at":"2026-05-18T00:39:46.268677Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:39:46.268677Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Mapping Instructions and Visual Observations to Actions with Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dipendra Misra, John Langford, Yoav Artzi","submitted_at":"2017-04-28T03:12:57Z","abstract_excerpt":"We propose to directly map raw visual observations and text input to actions for instruction execution. While existing approaches assume access to structured environment representations or use a pipeline of separately trained models, we learn a single model to jointly reason about linguistic and visual input. We use reinforcement learning in a contextual bandit setting to train a neural network agent. To guide the agent's exploration, we use reward shaping with different forms of supervision. Our approach does not require intermediate representations, planning procedures, or training different"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1704.08795","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":""},"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":"1704.08795","created_at":"2026-05-18T00:39:46.268778+00:00"},{"alias_kind":"arxiv_version","alias_value":"1704.08795v2","created_at":"2026-05-18T00:39:46.268778+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1704.08795","created_at":"2026-05-18T00:39:46.268778+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZQX47IVFMPFO","created_at":"2026-05-18T12:31:59.375834+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZQX47IVFMPFOMHSK","created_at":"2026-05-18T12:31:59.375834+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZQX47IVF","created_at":"2026-05-18T12:31:59.375834+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2209.07753","citing_title":"Code as Policies: Language Model Programs for Embodied Control","ref_index":41,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZQX47IVFMPFOMHSKWZAIDYRPCP","json":"https://pith.science/pith/ZQX47IVFMPFOMHSKWZAIDYRPCP.json","graph_json":"https://pith.science/api/pith-number/ZQX47IVFMPFOMHSKWZAIDYRPCP/graph.json","events_json":"https://pith.science/api/pith-number/ZQX47IVFMPFOMHSKWZAIDYRPCP/events.json","paper":"https://pith.science/paper/ZQX47IVF"},"agent_actions":{"view_html":"https://pith.science/pith/ZQX47IVFMPFOMHSKWZAIDYRPCP","download_json":"https://pith.science/pith/ZQX47IVFMPFOMHSKWZAIDYRPCP.json","view_paper":"https://pith.science/paper/ZQX47IVF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1704.08795&json=true","fetch_graph":"https://pith.science/api/pith-number/ZQX47IVFMPFOMHSKWZAIDYRPCP/graph.json","fetch_events":"https://pith.science/api/pith-number/ZQX47IVFMPFOMHSKWZAIDYRPCP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZQX47IVFMPFOMHSKWZAIDYRPCP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZQX47IVFMPFOMHSKWZAIDYRPCP/action/storage_attestation","attest_author":"https://pith.science/pith/ZQX47IVFMPFOMHSKWZAIDYRPCP/action/author_attestation","sign_citation":"https://pith.science/pith/ZQX47IVFMPFOMHSKWZAIDYRPCP/action/citation_signature","submit_replication":"https://pith.science/pith/ZQX47IVFMPFOMHSKWZAIDYRPCP/action/replication_record"}},"created_at":"2026-05-18T00:39:46.268778+00:00","updated_at":"2026-05-18T00:39:46.268778+00:00"}