{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:ADYWB55JHSY2W427RD66YVWVG4","short_pith_number":"pith:ADYWB55J","schema_version":"1.0","canonical_sha256":"00f160f7a93cb1ab735f88fdec56d53733e074bd6e3d8472fa0c6378f963138d","source":{"kind":"arxiv","id":"1802.01744","version":2},"attestation_state":"computed","paper":{"title":"Shared Autonomy via Deep Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.HC","cs.RO"],"primary_cat":"cs.LG","authors_text":"Anca D. Dragan, Sergey Levine, Siddharth Reddy","submitted_at":"2018-02-06T00:45:12Z","abstract_excerpt":"In shared autonomy, user input is combined with semi-autonomous control to achieve a common goal. The goal is often unknown ex-ante, so prior work enables agents to infer the goal from user input and assist with the task. Such methods tend to assume some combination of knowledge of the dynamics of the environment, the user's policy given their goal, and the set of possible goals the user might target, which limits their application to real-world scenarios. We propose a deep reinforcement learning framework for model-free shared autonomy that lifts these assumptions. We use human-in-the-loop re"},"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":"1802.01744","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-06T00:45:12Z","cross_cats_sorted":["cs.HC","cs.RO"],"title_canon_sha256":"2fa228e82b1f8a74dd8a835530d9eef8e2cc2a6250f7511cc13d7080dec16453","abstract_canon_sha256":"404431db3013b57711e016849999f7cc802a72252665bc22549dbd760f931600"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:15:09.773995Z","signature_b64":"W41NdvMOFX2GXMZOgN6lrBpZi4njsduJiT1fyaEhqFmJSWWLbS05O+J4mnSzsUjCHrrV/3Q17kX+Dzjb06wuAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"00f160f7a93cb1ab735f88fdec56d53733e074bd6e3d8472fa0c6378f963138d","last_reissued_at":"2026-05-18T00:15:09.773478Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:15:09.773478Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Shared Autonomy via Deep Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.HC","cs.RO"],"primary_cat":"cs.LG","authors_text":"Anca D. Dragan, Sergey Levine, Siddharth Reddy","submitted_at":"2018-02-06T00:45:12Z","abstract_excerpt":"In shared autonomy, user input is combined with semi-autonomous control to achieve a common goal. The goal is often unknown ex-ante, so prior work enables agents to infer the goal from user input and assist with the task. Such methods tend to assume some combination of knowledge of the dynamics of the environment, the user's policy given their goal, and the set of possible goals the user might target, which limits their application to real-world scenarios. We propose a deep reinforcement learning framework for model-free shared autonomy that lifts these assumptions. We use human-in-the-loop re"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.01744","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":"1802.01744","created_at":"2026-05-18T00:15:09.773565+00:00"},{"alias_kind":"arxiv_version","alias_value":"1802.01744v2","created_at":"2026-05-18T00:15:09.773565+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.01744","created_at":"2026-05-18T00:15:09.773565+00:00"},{"alias_kind":"pith_short_12","alias_value":"ADYWB55JHSY2","created_at":"2026-05-18T12:32:13.499390+00:00"},{"alias_kind":"pith_short_16","alias_value":"ADYWB55JHSY2W427","created_at":"2026-05-18T12:32:13.499390+00:00"},{"alias_kind":"pith_short_8","alias_value":"ADYWB55J","created_at":"2026-05-18T12:32:13.499390+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":3,"sample":[{"citing_arxiv_id":"1906.12280","citing_title":"Learning Arbitration for Shared Autonomy by Hindsight Data Aggregation","ref_index":15,"is_internal_anchor":true},{"citing_arxiv_id":"2403.02290","citing_title":"Koopman-Assisted Reinforcement Learning","ref_index":9,"is_internal_anchor":true},{"citing_arxiv_id":"2605.20355","citing_title":"Proximal State Nudging: Reducing Skill Atrophy from AI Assistance","ref_index":13,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ADYWB55JHSY2W427RD66YVWVG4","json":"https://pith.science/pith/ADYWB55JHSY2W427RD66YVWVG4.json","graph_json":"https://pith.science/api/pith-number/ADYWB55JHSY2W427RD66YVWVG4/graph.json","events_json":"https://pith.science/api/pith-number/ADYWB55JHSY2W427RD66YVWVG4/events.json","paper":"https://pith.science/paper/ADYWB55J"},"agent_actions":{"view_html":"https://pith.science/pith/ADYWB55JHSY2W427RD66YVWVG4","download_json":"https://pith.science/pith/ADYWB55JHSY2W427RD66YVWVG4.json","view_paper":"https://pith.science/paper/ADYWB55J","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1802.01744&json=true","fetch_graph":"https://pith.science/api/pith-number/ADYWB55JHSY2W427RD66YVWVG4/graph.json","fetch_events":"https://pith.science/api/pith-number/ADYWB55JHSY2W427RD66YVWVG4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ADYWB55JHSY2W427RD66YVWVG4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ADYWB55JHSY2W427RD66YVWVG4/action/storage_attestation","attest_author":"https://pith.science/pith/ADYWB55JHSY2W427RD66YVWVG4/action/author_attestation","sign_citation":"https://pith.science/pith/ADYWB55JHSY2W427RD66YVWVG4/action/citation_signature","submit_replication":"https://pith.science/pith/ADYWB55JHSY2W427RD66YVWVG4/action/replication_record"}},"created_at":"2026-05-18T00:15:09.773565+00:00","updated_at":"2026-05-18T00:15:09.773565+00:00"}