{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:NSOOKWX5B6PGTXURJZOJD7UX3Z","short_pith_number":"pith:NSOOKWX5","schema_version":"1.0","canonical_sha256":"6c9ce55afd0f9e69de914e5c91fe97de7fcdcf87be50ea3fe1d49b291ab0b27e","source":{"kind":"arxiv","id":"2407.03311","version":4},"attestation_state":"computed","paper":{"title":"Efficient Imitation Without Demonstrations via Value-Penalized Auxiliary Control from Examples","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"Bryan Chan, Jayce Haoran Wang, Jonathan Kelly, Trevor Ablett","submitted_at":"2024-07-03T17:54:11Z","abstract_excerpt":"Common approaches to providing feedback in reinforcement learning are the use of hand-crafted rewards or full-trajectory expert demonstrations. Alternatively, one can use examples of completed tasks, but such an approach can be extremely sample inefficient. We introduce value-penalized auxiliary control from examples (VPACE), an algorithm that significantly improves exploration in example-based control by adding examples of simple auxiliary tasks and an above-success-level value penalty. Across both simulated and real robotic environments, we show that our approach substantially improves learn"},"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":"2407.03311","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-07-03T17:54:11Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"c24fcb37c795630a2ed12d66fa419dc9a12dadd6339247a10515d8d84be35355","abstract_canon_sha256":"debb3dc864ddd8cd71c9c18bbf70dff1c51f4ff751ceb0e24c9a71a700aeb478"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:11:13.014282Z","signature_b64":"kf0OXt4EvAklhRbfJWROrZnw6HMlB9UNYFiy/KodDHUAOLOkYpDA6nrPWZYZsoiABAWvaMbGm4UWx1lvbKL5CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6c9ce55afd0f9e69de914e5c91fe97de7fcdcf87be50ea3fe1d49b291ab0b27e","last_reissued_at":"2026-07-05T12:11:13.013733Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:11:13.013733Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Efficient Imitation Without Demonstrations via Value-Penalized Auxiliary Control from Examples","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"Bryan Chan, Jayce Haoran Wang, Jonathan Kelly, Trevor Ablett","submitted_at":"2024-07-03T17:54:11Z","abstract_excerpt":"Common approaches to providing feedback in reinforcement learning are the use of hand-crafted rewards or full-trajectory expert demonstrations. Alternatively, one can use examples of completed tasks, but such an approach can be extremely sample inefficient. We introduce value-penalized auxiliary control from examples (VPACE), an algorithm that significantly improves exploration in example-based control by adding examples of simple auxiliary tasks and an above-success-level value penalty. Across both simulated and real robotic environments, we show that our approach substantially improves learn"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.03311","kind":"arxiv","version":4},"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/2407.03311/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":"2407.03311","created_at":"2026-07-05T12:11:13.013794+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.03311v4","created_at":"2026-07-05T12:11:13.013794+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.03311","created_at":"2026-07-05T12:11:13.013794+00:00"},{"alias_kind":"pith_short_12","alias_value":"NSOOKWX5B6PG","created_at":"2026-07-05T12:11:13.013794+00:00"},{"alias_kind":"pith_short_16","alias_value":"NSOOKWX5B6PGTXUR","created_at":"2026-07-05T12:11:13.013794+00:00"},{"alias_kind":"pith_short_8","alias_value":"NSOOKWX5","created_at":"2026-07-05T12:11:13.013794+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/NSOOKWX5B6PGTXURJZOJD7UX3Z","json":"https://pith.science/pith/NSOOKWX5B6PGTXURJZOJD7UX3Z.json","graph_json":"https://pith.science/api/pith-number/NSOOKWX5B6PGTXURJZOJD7UX3Z/graph.json","events_json":"https://pith.science/api/pith-number/NSOOKWX5B6PGTXURJZOJD7UX3Z/events.json","paper":"https://pith.science/paper/NSOOKWX5"},"agent_actions":{"view_html":"https://pith.science/pith/NSOOKWX5B6PGTXURJZOJD7UX3Z","download_json":"https://pith.science/pith/NSOOKWX5B6PGTXURJZOJD7UX3Z.json","view_paper":"https://pith.science/paper/NSOOKWX5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.03311&json=true","fetch_graph":"https://pith.science/api/pith-number/NSOOKWX5B6PGTXURJZOJD7UX3Z/graph.json","fetch_events":"https://pith.science/api/pith-number/NSOOKWX5B6PGTXURJZOJD7UX3Z/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NSOOKWX5B6PGTXURJZOJD7UX3Z/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NSOOKWX5B6PGTXURJZOJD7UX3Z/action/storage_attestation","attest_author":"https://pith.science/pith/NSOOKWX5B6PGTXURJZOJD7UX3Z/action/author_attestation","sign_citation":"https://pith.science/pith/NSOOKWX5B6PGTXURJZOJD7UX3Z/action/citation_signature","submit_replication":"https://pith.science/pith/NSOOKWX5B6PGTXURJZOJD7UX3Z/action/replication_record"}},"created_at":"2026-07-05T12:11:13.013794+00:00","updated_at":"2026-07-05T12:11:13.013794+00:00"}