{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:GI2RDMRRFZB6B55VLEY265PXSW","short_pith_number":"pith:GI2RDMRR","canonical_record":{"source":{"id":"1802.09564","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2018-02-26T19:25:25Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"884622fe68dfa1add77f6410528a76347d6f70456fe191a3b095ea4b2ca8dae0","abstract_canon_sha256":"d78694b4812f27ea62ecab805c97497f1ef028f522848852d6fa891e787cc03d"},"schema_version":"1.0"},"canonical_sha256":"323511b2312e43e0f7b55931af75f7959061930d87c62cbaed8e3e4e24ae4259","source":{"kind":"arxiv","id":"1802.09564","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.09564","created_at":"2026-05-18T00:14:53Z"},{"alias_kind":"arxiv_version","alias_value":"1802.09564v2","created_at":"2026-05-18T00:14:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.09564","created_at":"2026-05-18T00:14:53Z"},{"alias_kind":"pith_short_12","alias_value":"GI2RDMRRFZB6","created_at":"2026-05-18T12:32:25Z"},{"alias_kind":"pith_short_16","alias_value":"GI2RDMRRFZB6B55V","created_at":"2026-05-18T12:32:25Z"},{"alias_kind":"pith_short_8","alias_value":"GI2RDMRR","created_at":"2026-05-18T12:32:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:GI2RDMRRFZB6B55VLEY265PXSW","target":"record","payload":{"canonical_record":{"source":{"id":"1802.09564","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2018-02-26T19:25:25Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"884622fe68dfa1add77f6410528a76347d6f70456fe191a3b095ea4b2ca8dae0","abstract_canon_sha256":"d78694b4812f27ea62ecab805c97497f1ef028f522848852d6fa891e787cc03d"},"schema_version":"1.0"},"canonical_sha256":"323511b2312e43e0f7b55931af75f7959061930d87c62cbaed8e3e4e24ae4259","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:14:53.738299Z","signature_b64":"j/ZK5vPjxXt6lH+54UZ4behx8qi8VthfExAUUhc523gdr3Mtw7MabvFS+sJw3komMluve0iV2aj7snVNXA31AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"323511b2312e43e0f7b55931af75f7959061930d87c62cbaed8e3e4e24ae4259","last_reissued_at":"2026-05-18T00:14:53.737790Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:14:53.737790Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1802.09564","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:14:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FfjEFWmQu0/wl0M94MviD3p4FiV5xNhHZ1pgZbxcP9n95vQr84d3KcX2omuK7j1aVzWdjs6bvcjNps9v+uoBAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-18T21:31:12.849178Z"},"content_sha256":"f36598b1923fedefdecd35620d0e83ccd656bc2dae2531fc310ddc40c74a085c","schema_version":"1.0","event_id":"sha256:f36598b1923fedefdecd35620d0e83ccd656bc2dae2531fc310ddc40c74a085c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:GI2RDMRRFZB6B55VLEY265PXSW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Reinforcement and Imitation Learning for Diverse Visuomotor Skills","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"Andrei Rusu, J\\'anos Kram\\'ar, Josh Merel, Nando de Freitas, Nicolas Heess, Raia Hadsell, Saran Tunyasuvunakool, Serkan Cabi, Tom Erez, Yuke Zhu, Ziyu Wang","submitted_at":"2018-02-26T19:25:25Z","abstract_excerpt":"We propose a model-free deep reinforcement learning method that leverages a small amount of demonstration data to assist a reinforcement learning agent. We apply this approach to robotic manipulation tasks and train end-to-end visuomotor policies that map directly from RGB camera inputs to joint velocities. We demonstrate that our approach can solve a wide variety of visuomotor tasks, for which engineering a scripted controller would be laborious. In experiments, our reinforcement and imitation agent achieves significantly better performances than agents trained with reinforcement learning or "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.09564","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":""},"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:14:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WRXXfSpchD6MFPxcLSOFxBPxGk3oCdgBU+QABXn59aiTBvkVJQtYQJ8i3GTxQCIJtRB/ZZLuxBwLWJb+4q8TBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-18T21:31:12.849849Z"},"content_sha256":"c3777c44bad2c13947cc76bd3d07e530cf9d114dfb734498b7ab93c35a688639","schema_version":"1.0","event_id":"sha256:c3777c44bad2c13947cc76bd3d07e530cf9d114dfb734498b7ab93c35a688639"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GI2RDMRRFZB6B55VLEY265PXSW/bundle.json","state_url":"https://pith.science/pith/GI2RDMRRFZB6B55VLEY265PXSW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GI2RDMRRFZB6B55VLEY265PXSW/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-18T21:31:12Z","links":{"resolver":"https://pith.science/pith/GI2RDMRRFZB6B55VLEY265PXSW","bundle":"https://pith.science/pith/GI2RDMRRFZB6B55VLEY265PXSW/bundle.json","state":"https://pith.science/pith/GI2RDMRRFZB6B55VLEY265PXSW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GI2RDMRRFZB6B55VLEY265PXSW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:GI2RDMRRFZB6B55VLEY265PXSW","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":"d78694b4812f27ea62ecab805c97497f1ef028f522848852d6fa891e787cc03d","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2018-02-26T19:25:25Z","title_canon_sha256":"884622fe68dfa1add77f6410528a76347d6f70456fe191a3b095ea4b2ca8dae0"},"schema_version":"1.0","source":{"id":"1802.09564","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.09564","created_at":"2026-05-18T00:14:53Z"},{"alias_kind":"arxiv_version","alias_value":"1802.09564v2","created_at":"2026-05-18T00:14:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.09564","created_at":"2026-05-18T00:14:53Z"},{"alias_kind":"pith_short_12","alias_value":"GI2RDMRRFZB6","created_at":"2026-05-18T12:32:25Z"},{"alias_kind":"pith_short_16","alias_value":"GI2RDMRRFZB6B55V","created_at":"2026-05-18T12:32:25Z"},{"alias_kind":"pith_short_8","alias_value":"GI2RDMRR","created_at":"2026-05-18T12:32:25Z"}],"graph_snapshots":[{"event_id":"sha256:c3777c44bad2c13947cc76bd3d07e530cf9d114dfb734498b7ab93c35a688639","target":"graph","created_at":"2026-05-18T00:14:53Z","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"},"paper":{"abstract_excerpt":"We propose a model-free deep reinforcement learning method that leverages a small amount of demonstration data to assist a reinforcement learning agent. We apply this approach to robotic manipulation tasks and train end-to-end visuomotor policies that map directly from RGB camera inputs to joint velocities. We demonstrate that our approach can solve a wide variety of visuomotor tasks, for which engineering a scripted controller would be laborious. In experiments, our reinforcement and imitation agent achieves significantly better performances than agents trained with reinforcement learning or ","authors_text":"Andrei Rusu, J\\'anos Kram\\'ar, Josh Merel, Nando de Freitas, Nicolas Heess, Raia Hadsell, Saran Tunyasuvunakool, Serkan Cabi, Tom Erez, Yuke Zhu, Ziyu Wang","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2018-02-26T19:25:25Z","title":"Reinforcement and Imitation Learning for Diverse Visuomotor Skills"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.09564","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:f36598b1923fedefdecd35620d0e83ccd656bc2dae2531fc310ddc40c74a085c","target":"record","created_at":"2026-05-18T00:14:53Z","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":"d78694b4812f27ea62ecab805c97497f1ef028f522848852d6fa891e787cc03d","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2018-02-26T19:25:25Z","title_canon_sha256":"884622fe68dfa1add77f6410528a76347d6f70456fe191a3b095ea4b2ca8dae0"},"schema_version":"1.0","source":{"id":"1802.09564","kind":"arxiv","version":2}},"canonical_sha256":"323511b2312e43e0f7b55931af75f7959061930d87c62cbaed8e3e4e24ae4259","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"323511b2312e43e0f7b55931af75f7959061930d87c62cbaed8e3e4e24ae4259","first_computed_at":"2026-05-18T00:14:53.737790Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:14:53.737790Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"j/ZK5vPjxXt6lH+54UZ4behx8qi8VthfExAUUhc523gdr3Mtw7MabvFS+sJw3komMluve0iV2aj7snVNXA31AQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:14:53.738299Z","signed_message":"canonical_sha256_bytes"},"source_id":"1802.09564","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f36598b1923fedefdecd35620d0e83ccd656bc2dae2531fc310ddc40c74a085c","sha256:c3777c44bad2c13947cc76bd3d07e530cf9d114dfb734498b7ab93c35a688639"],"state_sha256":"e82ee5dc6cd8764e7e87e8c88dc5cfd049a6ab44e0eaf561bab8827cdc88c276"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hX4d5ZflJqjUysH5+gZwz0lcLwew2ESmk0CXD1TdNiUF17W1cljMloGdGDIEtEPEqz9l2uACgzvS66jpfC4sDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-18T21:31:12.851911Z","bundle_sha256":"6cbe92ec3c0161e246808c6f57f714d810ab0226753ae8a6cee5cd6c45034704"}}