{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:3YKXGW4HWLIG3CV4I5KCORDO2E","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":"93965ddd84a21ac4db9d50346255487f809bde116c9939f512a523c3ccb36f8d","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2020-11-11T15:45:17Z","title_canon_sha256":"120a952581053c803a04049ed8eeb6170b09ed60328d7e2d94ce62ecfc5b8862"},"schema_version":"1.0","source":{"id":"2011.05857","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2011.05857","created_at":"2026-07-05T04:00:12Z"},{"alias_kind":"arxiv_version","alias_value":"2011.05857v2","created_at":"2026-07-05T04:00:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.05857","created_at":"2026-07-05T04:00:12Z"},{"alias_kind":"pith_short_12","alias_value":"3YKXGW4HWLIG","created_at":"2026-07-05T04:00:12Z"},{"alias_kind":"pith_short_16","alias_value":"3YKXGW4HWLIG3CV4","created_at":"2026-07-05T04:00:12Z"},{"alias_kind":"pith_short_8","alias_value":"3YKXGW4H","created_at":"2026-07-05T04:00:12Z"}],"graph_snapshots":[{"event_id":"sha256:28ce597d6dd43caf25c95df2542994c76adfc1c5cc67898e42a7f301d25117a2","target":"graph","created_at":"2026-07-05T04:00:12Z","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/2011.05857/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We consider real-world reinforcement learning (RL) of robotic manipulation tasks that involve both visuomotor skills and contact-rich skills. We aim to train a policy that maps multimodal sensory observations (vision and force) to a manipulator's joint velocities under practical considerations. We propose to use offline samples to learn a set of general value functions (GVFs) that make counterfactual predictions from the visual inputs. We show that combining the offline learned counterfactual predictions with force feedbacks in online policy learning allows efficient reinforcement learning giv","authors_text":"Cameron Haigh, Daniel Graves, Jun Jin, Jun Luo, Martin Jagersand","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2020-11-11T15:45:17Z","title":"Offline Learning of Counterfactual Predictions for Real-World Robotic Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.05857","kind":"arxiv","version":2},"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":"sha256:3cb3b086684190aeadae107ccdfcc5d1d8b437e68563b73fb534805ee37f6b47","target":"record","created_at":"2026-07-05T04:00:12Z","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":"93965ddd84a21ac4db9d50346255487f809bde116c9939f512a523c3ccb36f8d","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2020-11-11T15:45:17Z","title_canon_sha256":"120a952581053c803a04049ed8eeb6170b09ed60328d7e2d94ce62ecfc5b8862"},"schema_version":"1.0","source":{"id":"2011.05857","kind":"arxiv","version":2}},"canonical_sha256":"de15735b87b2d06d8abc475427446ed1364ef5bd3a743644037744e7de1f27d7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"de15735b87b2d06d8abc475427446ed1364ef5bd3a743644037744e7de1f27d7","first_computed_at":"2026-07-05T04:00:12.298811Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:00:12.298811Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"am4f7bq1pUP1zzvXNhRwPRNpw30vtUt7Jbg0ieENZW3Vkiob91JzGUCk05A2kkosApPOlpSWi3UEvxydcJmsDg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:00:12.299226Z","signed_message":"canonical_sha256_bytes"},"source_id":"2011.05857","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3cb3b086684190aeadae107ccdfcc5d1d8b437e68563b73fb534805ee37f6b47","sha256:28ce597d6dd43caf25c95df2542994c76adfc1c5cc67898e42a7f301d25117a2"],"state_sha256":"3e8200607c3ee0704c9f936416730f4f04fdfb7b53e2a7f37c94092b2a8312dd"}