{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:NSOOKWX5B6PGTXURJZOJD7UX3Z","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"debb3dc864ddd8cd71c9c18bbf70dff1c51f4ff751ceb0e24c9a71a700aeb478","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-07-03T17:54:11Z","title_canon_sha256":"c24fcb37c795630a2ed12d66fa419dc9a12dadd6339247a10515d8d84be35355"},"schema_version":"1.0","source":{"id":"2407.03311","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.03311","created_at":"2026-07-05T12:11:13Z"},{"alias_kind":"arxiv_version","alias_value":"2407.03311v4","created_at":"2026-07-05T12:11:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.03311","created_at":"2026-07-05T12:11:13Z"},{"alias_kind":"pith_short_12","alias_value":"NSOOKWX5B6PG","created_at":"2026-07-05T12:11:13Z"},{"alias_kind":"pith_short_16","alias_value":"NSOOKWX5B6PGTXUR","created_at":"2026-07-05T12:11:13Z"},{"alias_kind":"pith_short_8","alias_value":"NSOOKWX5","created_at":"2026-07-05T12:11:13Z"}],"graph_snapshots":[{"event_id":"sha256:bc6ecc6efe2c0b59274c2e671d7abd630a439e3cd791cca83310a00434f752c2","target":"graph","created_at":"2026-07-05T12:11:13Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2407.03311/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Bryan Chan, Jayce Haoran Wang, Jonathan Kelly, Trevor Ablett","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-07-03T17:54:11Z","title":"Efficient Imitation Without Demonstrations via Value-Penalized Auxiliary Control from Examples"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.03311","kind":"arxiv","version":4},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:4afcd128daca08578e8762babc3da09a56222344abcdcb5a997135298b84c232","target":"record","created_at":"2026-07-05T12:11:13Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"debb3dc864ddd8cd71c9c18bbf70dff1c51f4ff751ceb0e24c9a71a700aeb478","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-07-03T17:54:11Z","title_canon_sha256":"c24fcb37c795630a2ed12d66fa419dc9a12dadd6339247a10515d8d84be35355"},"schema_version":"1.0","source":{"id":"2407.03311","kind":"arxiv","version":4}},"canonical_sha256":"6c9ce55afd0f9e69de914e5c91fe97de7fcdcf87be50ea3fe1d49b291ab0b27e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6c9ce55afd0f9e69de914e5c91fe97de7fcdcf87be50ea3fe1d49b291ab0b27e","first_computed_at":"2026-07-05T12:11:13.013733Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:11:13.013733Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kf0OXt4EvAklhRbfJWROrZnw6HMlB9UNYFiy/KodDHUAOLOkYpDA6nrPWZYZsoiABAWvaMbGm4UWx1lvbKL5CA==","signature_status":"signed_v1","signed_at":"2026-07-05T12:11:13.014282Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.03311","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4afcd128daca08578e8762babc3da09a56222344abcdcb5a997135298b84c232","sha256:bc6ecc6efe2c0b59274c2e671d7abd630a439e3cd791cca83310a00434f752c2"],"state_sha256":"6fbe58086cdbff4c4c3e0952ee9bb2516dbde949863c035ab57f7d64fc4b30e2"}