{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:WVUADCQI5TERUIXV5IZR5T44AX","short_pith_number":"pith:WVUADCQI","canonical_record":{"source":{"id":"1905.06274","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-15T16:21:05Z","cross_cats_sorted":["cs.RO","stat.ML"],"title_canon_sha256":"bc6ed150467f4798504046b6b5c81b31ca051da85a5ee171464971453723652c","abstract_canon_sha256":"342763bf6eb480db4ddc4feb7412747cef25fb28f54acaba228adf40eeaa6979"},"schema_version":"1.0"},"canonical_sha256":"b568018a08ecc91a22f5ea331ecf9c05de27c00baa306d9867bf2b691c70af6e","source":{"kind":"arxiv","id":"1905.06274","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.06274","created_at":"2026-05-17T23:46:06Z"},{"alias_kind":"arxiv_version","alias_value":"1905.06274v1","created_at":"2026-05-17T23:46:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.06274","created_at":"2026-05-17T23:46:06Z"},{"alias_kind":"pith_short_12","alias_value":"WVUADCQI5TER","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"WVUADCQI5TERUIXV","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"WVUADCQI","created_at":"2026-05-18T12:33:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:WVUADCQI5TERUIXV5IZR5T44AX","target":"record","payload":{"canonical_record":{"source":{"id":"1905.06274","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-15T16:21:05Z","cross_cats_sorted":["cs.RO","stat.ML"],"title_canon_sha256":"bc6ed150467f4798504046b6b5c81b31ca051da85a5ee171464971453723652c","abstract_canon_sha256":"342763bf6eb480db4ddc4feb7412747cef25fb28f54acaba228adf40eeaa6979"},"schema_version":"1.0"},"canonical_sha256":"b568018a08ecc91a22f5ea331ecf9c05de27c00baa306d9867bf2b691c70af6e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:46:06.991354Z","signature_b64":"cPK8ET/Xxv9TuGT2QU5T+pvX74Q5pin1UGdFboqSvHptsCHyw+1MDaNEzLFk+85q7qfad6J6r+7aUhrjcCBVCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b568018a08ecc91a22f5ea331ecf9c05de27c00baa306d9867bf2b691c70af6e","last_reissued_at":"2026-05-17T23:46:06.990439Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:46:06.990439Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1905.06274","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:46:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"f8MZC1fUIrWth3RPbaj7Xstxi7ZgCni9hFW/qBfDnnjVSjuDSgDHE6vm5XRFD9UQW0CW+dm1u2d7yZeSiRTZCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T08:36:29.031860Z"},"content_sha256":"a37dec19fe2c7f95dc553c7009f2cce99e7da7d44e9abe035931e66e6a4915dc","schema_version":"1.0","event_id":"sha256:a37dec19fe2c7f95dc553c7009f2cce99e7da7d44e9abe035931e66e6a4915dc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:WVUADCQI5TERUIXV5IZR5T44AX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Reinforcement Learning for Robotics and Control with Active Uncertainty Reduction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO","stat.ML"],"primary_cat":"cs.LG","authors_text":"Narendra Patwardhan, Zequn Wang","submitted_at":"2019-05-15T16:21:05Z","abstract_excerpt":"Model-free reinforcement learning based methods such as Proximal Policy Optimization, or Q-learning typically require thousands of interactions with the environment to approximate the optimum controller which may not always be feasible in robotics due to safety and time consumption. Model-based methods such as PILCO or BlackDrops, while data-efficient, provide solutions with limited robustness and complexity. To address this tradeoff, we introduce active uncertainty reduction-based virtual environments, which are formed through limited trials conducted in the original environment. We provide a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.06274","kind":"arxiv","version":1},"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":"2026-05-17T23:46:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"r2zNy7d9arq1wYXVXKoxty7N4DSOApF61M3KwKIyYlJ51gGlB1VnCIc64vi9+wnnlczMNZBS8l4c9snXNCv+BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T08:36:29.032204Z"},"content_sha256":"53b6ddaebc7aef4eaf333d06465737638e6f41dffb058fead6fd00e10687a74a","schema_version":"1.0","event_id":"sha256:53b6ddaebc7aef4eaf333d06465737638e6f41dffb058fead6fd00e10687a74a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WVUADCQI5TERUIXV5IZR5T44AX/bundle.json","state_url":"https://pith.science/pith/WVUADCQI5TERUIXV5IZR5T44AX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WVUADCQI5TERUIXV5IZR5T44AX/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":"2026-07-07T08:36:29Z","links":{"resolver":"https://pith.science/pith/WVUADCQI5TERUIXV5IZR5T44AX","bundle":"https://pith.science/pith/WVUADCQI5TERUIXV5IZR5T44AX/bundle.json","state":"https://pith.science/pith/WVUADCQI5TERUIXV5IZR5T44AX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WVUADCQI5TERUIXV5IZR5T44AX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:WVUADCQI5TERUIXV5IZR5T44AX","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":"342763bf6eb480db4ddc4feb7412747cef25fb28f54acaba228adf40eeaa6979","cross_cats_sorted":["cs.RO","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-15T16:21:05Z","title_canon_sha256":"bc6ed150467f4798504046b6b5c81b31ca051da85a5ee171464971453723652c"},"schema_version":"1.0","source":{"id":"1905.06274","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.06274","created_at":"2026-05-17T23:46:06Z"},{"alias_kind":"arxiv_version","alias_value":"1905.06274v1","created_at":"2026-05-17T23:46:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.06274","created_at":"2026-05-17T23:46:06Z"},{"alias_kind":"pith_short_12","alias_value":"WVUADCQI5TER","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"WVUADCQI5TERUIXV","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"WVUADCQI","created_at":"2026-05-18T12:33:33Z"}],"graph_snapshots":[{"event_id":"sha256:53b6ddaebc7aef4eaf333d06465737638e6f41dffb058fead6fd00e10687a74a","target":"graph","created_at":"2026-05-17T23:46:06Z","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":"Model-free reinforcement learning based methods such as Proximal Policy Optimization, or Q-learning typically require thousands of interactions with the environment to approximate the optimum controller which may not always be feasible in robotics due to safety and time consumption. Model-based methods such as PILCO or BlackDrops, while data-efficient, provide solutions with limited robustness and complexity. To address this tradeoff, we introduce active uncertainty reduction-based virtual environments, which are formed through limited trials conducted in the original environment. We provide a","authors_text":"Narendra Patwardhan, Zequn Wang","cross_cats":["cs.RO","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-15T16:21:05Z","title":"Reinforcement Learning for Robotics and Control with Active Uncertainty Reduction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.06274","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:a37dec19fe2c7f95dc553c7009f2cce99e7da7d44e9abe035931e66e6a4915dc","target":"record","created_at":"2026-05-17T23:46:06Z","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":"342763bf6eb480db4ddc4feb7412747cef25fb28f54acaba228adf40eeaa6979","cross_cats_sorted":["cs.RO","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-15T16:21:05Z","title_canon_sha256":"bc6ed150467f4798504046b6b5c81b31ca051da85a5ee171464971453723652c"},"schema_version":"1.0","source":{"id":"1905.06274","kind":"arxiv","version":1}},"canonical_sha256":"b568018a08ecc91a22f5ea331ecf9c05de27c00baa306d9867bf2b691c70af6e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b568018a08ecc91a22f5ea331ecf9c05de27c00baa306d9867bf2b691c70af6e","first_computed_at":"2026-05-17T23:46:06.990439Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:46:06.990439Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cPK8ET/Xxv9TuGT2QU5T+pvX74Q5pin1UGdFboqSvHptsCHyw+1MDaNEzLFk+85q7qfad6J6r+7aUhrjcCBVCA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:46:06.991354Z","signed_message":"canonical_sha256_bytes"},"source_id":"1905.06274","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a37dec19fe2c7f95dc553c7009f2cce99e7da7d44e9abe035931e66e6a4915dc","sha256:53b6ddaebc7aef4eaf333d06465737638e6f41dffb058fead6fd00e10687a74a"],"state_sha256":"45f4ca42ecef17be9bd7b536591263b547c54d9d46c67a77ad4a7da103d65f76"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xNvlUdfmzpcN9cjpf9C1Ce/oZkzciLZKNpnyGs6eTu+w2BbrdWA8+skmpAECrNiTpXmXosdEKhDDCrgnH0hyDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T08:36:29.034084Z","bundle_sha256":"823c226ba7e929ba066a82abcaa74e28ae08cb02e368b11b92c0a548af08d2fe"}}