{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:MVFMVDAAGASB6UZ6MJ5Z7VYMVP","short_pith_number":"pith:MVFMVDAA","schema_version":"1.0","canonical_sha256":"654aca8c0030241f533e627b9fd70cabec3f4bbd8ec6c65aa2176f9e386f0887","source":{"kind":"arxiv","id":"2004.05097","version":2},"attestation_state":"computed","paper":{"title":"Residual Policy Learning for Shared Autonomy","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Charles Schaff, Matthew R. Walter","submitted_at":"2020-04-10T16:31:15Z","abstract_excerpt":"Shared autonomy provides an effective framework for human-robot collaboration that takes advantage of the complementary strengths of humans and robots to achieve common goals. Many existing approaches to shared autonomy make restrictive assumptions that the goal space, environment dynamics, or human policy are known a priori, or are limited to discrete action spaces, preventing those methods from scaling to complicated real world environments. We propose a model-free, residual policy learning algorithm for shared autonomy that alleviates the need for these assumptions. Our agents are trained t"},"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":"2004.05097","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2020-04-10T16:31:15Z","cross_cats_sorted":[],"title_canon_sha256":"515b9c662bb3a41619a1e857eb6a796e7678e68a41fafed0aaf8a2548462f1a5","abstract_canon_sha256":"1a8966128e1b808afb9e5b051de9f388e41559c34004886c751a7efc7e9f1a90"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:17:40.633007Z","signature_b64":"esQJk6nDLCh4611w2bfoQENS9SxhybIW0cW9K9IV6Q7PDdYopDh7Lr7WMnvjuGXzcEF1Eui196D5W0vCRI0mCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"654aca8c0030241f533e627b9fd70cabec3f4bbd8ec6c65aa2176f9e386f0887","last_reissued_at":"2026-07-05T01:17:40.632579Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:17:40.632579Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Residual Policy Learning for Shared Autonomy","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Charles Schaff, Matthew R. Walter","submitted_at":"2020-04-10T16:31:15Z","abstract_excerpt":"Shared autonomy provides an effective framework for human-robot collaboration that takes advantage of the complementary strengths of humans and robots to achieve common goals. Many existing approaches to shared autonomy make restrictive assumptions that the goal space, environment dynamics, or human policy are known a priori, or are limited to discrete action spaces, preventing those methods from scaling to complicated real world environments. We propose a model-free, residual policy learning algorithm for shared autonomy that alleviates the need for these assumptions. Our agents are trained t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.05097","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/2004.05097/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":"2004.05097","created_at":"2026-07-05T01:17:40.632636+00:00"},{"alias_kind":"arxiv_version","alias_value":"2004.05097v2","created_at":"2026-07-05T01:17:40.632636+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.05097","created_at":"2026-07-05T01:17:40.632636+00:00"},{"alias_kind":"pith_short_12","alias_value":"MVFMVDAAGASB","created_at":"2026-07-05T01:17:40.632636+00:00"},{"alias_kind":"pith_short_16","alias_value":"MVFMVDAAGASB6UZ6","created_at":"2026-07-05T01:17:40.632636+00:00"},{"alias_kind":"pith_short_8","alias_value":"MVFMVDAA","created_at":"2026-07-05T01:17:40.632636+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.06461","citing_title":"Flow-based Policy Adaptation without Policy Updates","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02410","citing_title":"Shared Autonomy Assisted by Impedance-Driven Anisotropic Guidance Field","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MVFMVDAAGASB6UZ6MJ5Z7VYMVP","json":"https://pith.science/pith/MVFMVDAAGASB6UZ6MJ5Z7VYMVP.json","graph_json":"https://pith.science/api/pith-number/MVFMVDAAGASB6UZ6MJ5Z7VYMVP/graph.json","events_json":"https://pith.science/api/pith-number/MVFMVDAAGASB6UZ6MJ5Z7VYMVP/events.json","paper":"https://pith.science/paper/MVFMVDAA"},"agent_actions":{"view_html":"https://pith.science/pith/MVFMVDAAGASB6UZ6MJ5Z7VYMVP","download_json":"https://pith.science/pith/MVFMVDAAGASB6UZ6MJ5Z7VYMVP.json","view_paper":"https://pith.science/paper/MVFMVDAA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2004.05097&json=true","fetch_graph":"https://pith.science/api/pith-number/MVFMVDAAGASB6UZ6MJ5Z7VYMVP/graph.json","fetch_events":"https://pith.science/api/pith-number/MVFMVDAAGASB6UZ6MJ5Z7VYMVP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MVFMVDAAGASB6UZ6MJ5Z7VYMVP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MVFMVDAAGASB6UZ6MJ5Z7VYMVP/action/storage_attestation","attest_author":"https://pith.science/pith/MVFMVDAAGASB6UZ6MJ5Z7VYMVP/action/author_attestation","sign_citation":"https://pith.science/pith/MVFMVDAAGASB6UZ6MJ5Z7VYMVP/action/citation_signature","submit_replication":"https://pith.science/pith/MVFMVDAAGASB6UZ6MJ5Z7VYMVP/action/replication_record"}},"created_at":"2026-07-05T01:17:40.632636+00:00","updated_at":"2026-07-05T01:17:40.632636+00:00"}