{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:OD7HCS2EESJFOYR6NPBF7GG6V5","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":"4e5cb3f529617ca406515af19d6183ce72dad256963b472732110ef38e02877a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-15T11:16:49Z","title_canon_sha256":"4579dcc12e7ac6a4c3f9b5ad3af651264533ad2302bb33a8b12b51ac7e6cc9dc"},"schema_version":"1.0","source":{"id":"2106.08050","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.08050","created_at":"2026-07-05T02:49:37Z"},{"alias_kind":"arxiv_version","alias_value":"2106.08050v1","created_at":"2026-07-05T02:49:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.08050","created_at":"2026-07-05T02:49:37Z"},{"alias_kind":"pith_short_12","alias_value":"OD7HCS2EESJF","created_at":"2026-07-05T02:49:37Z"},{"alias_kind":"pith_short_16","alias_value":"OD7HCS2EESJFOYR6","created_at":"2026-07-05T02:49:37Z"},{"alias_kind":"pith_short_8","alias_value":"OD7HCS2E","created_at":"2026-07-05T02:49:37Z"}],"graph_snapshots":[{"event_id":"sha256:4b9effc059fb9c4e99c753f0410a4766214fbf13685b86eeae138123dc55c412","target":"graph","created_at":"2026-07-05T02:49:37Z","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/2106.08050/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Residual reinforcement learning (RL) has been proposed as a way to solve challenging robotic tasks by adapting control actions from a conventional feedback controller to maximize a reward signal. We extend the residual formulation to learn from visual inputs and sparse rewards using demonstrations. Learning from images, proprioceptive inputs and a sparse task-completion reward relaxes the requirement of accessing full state features, such as object and target positions. In addition, replacing the base controller with a policy learned from demonstrations removes the dependency on a hand-enginee","authors_text":"Cordelia Schmid, Gabriel Dulac-Arnold, Jean Ponce (WILLOW), Julien Mairal (Thoth), Minttu Alakuijala (WILLOW, Thoth)","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-15T11:16:49Z","title":"Residual Reinforcement Learning from Demonstrations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.08050","kind":"arxiv","version":1},"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":"sha256:6b23cf25dc9306213493a427746dde5bc64b3708029ae86be86da463597e80d7","target":"record","created_at":"2026-07-05T02:49:37Z","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":"4e5cb3f529617ca406515af19d6183ce72dad256963b472732110ef38e02877a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-15T11:16:49Z","title_canon_sha256":"4579dcc12e7ac6a4c3f9b5ad3af651264533ad2302bb33a8b12b51ac7e6cc9dc"},"schema_version":"1.0","source":{"id":"2106.08050","kind":"arxiv","version":1}},"canonical_sha256":"70fe714b44249257623e6bc25f98deaf731716161f53c1afcef3cacbc59aea10","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"70fe714b44249257623e6bc25f98deaf731716161f53c1afcef3cacbc59aea10","first_computed_at":"2026-07-05T02:49:37.273310Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:49:37.273310Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"X7k7s3zIn30/4YqJEnMJRu87TIa6gfIBoyLDc1/cFyfE2/jzLuLBFzgcPzd5BzDQdUGgYGlFDnltWzxfE6+rBg==","signature_status":"signed_v1","signed_at":"2026-07-05T02:49:37.273808Z","signed_message":"canonical_sha256_bytes"},"source_id":"2106.08050","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6b23cf25dc9306213493a427746dde5bc64b3708029ae86be86da463597e80d7","sha256:4b9effc059fb9c4e99c753f0410a4766214fbf13685b86eeae138123dc55c412"],"state_sha256":"b0e4f1680dfbcff9eab36be64eb03a63d7bbf8b69465b41e46e98ccc40be4a47"}