{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:OWJSG3PCTLTXFLMZRHSV4KKOSV","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":"53e4355784060dc518df9da0a4a6161b509d3e085dc8a7e1e5e10afe937f5edc","cross_cats_sorted":["cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-09-15T15:39:46Z","title_canon_sha256":"235ec71ad22b24981739860bc770fb4d6ca792110e09b7a1852bb16c7a4dbb94"},"schema_version":"1.0","source":{"id":"2109.07380","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2109.07380","created_at":"2026-07-05T03:14:48Z"},{"alias_kind":"arxiv_version","alias_value":"2109.07380v1","created_at":"2026-07-05T03:14:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.07380","created_at":"2026-07-05T03:14:48Z"},{"alias_kind":"pith_short_12","alias_value":"OWJSG3PCTLTX","created_at":"2026-07-05T03:14:48Z"},{"alias_kind":"pith_short_16","alias_value":"OWJSG3PCTLTXFLMZ","created_at":"2026-07-05T03:14:48Z"},{"alias_kind":"pith_short_8","alias_value":"OWJSG3PC","created_at":"2026-07-05T03:14:48Z"}],"graph_snapshots":[{"event_id":"sha256:4940d73d8f4f4c1a6b18a1d51767224b1f44f087fc00ac6184637c7d61c25825","target":"graph","created_at":"2026-07-05T03:14:48Z","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/2109.07380/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Deep reinforcement learning (RL) has shown great empirical successes, but suffers from brittleness and sample inefficiency. A potential remedy is to use a previously-trained policy as a source of supervision. In this work, we refer to these policies as teachers and study how to transfer their expertise to new student policies by focusing on data usage. We propose a framework, Data CUrriculum for Reinforcement learning (DCUR), which first trains teachers using online deep RL, and stores the logged environment interaction history. Then, students learn by running either offline RL or by using tea","authors_text":"Abhinav Gopal, Daniel Seita, John Canny, Zhao Mandi","cross_cats":["cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-09-15T15:39:46Z","title":"DCUR: Data Curriculum for Teaching via Samples with Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.07380","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":"sha256:4301c8ad28a5d9f6fe5542b6c214e712503ac2c3456f30d3603df1fbce73a4f1","target":"record","created_at":"2026-07-05T03:14:48Z","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":"53e4355784060dc518df9da0a4a6161b509d3e085dc8a7e1e5e10afe937f5edc","cross_cats_sorted":["cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-09-15T15:39:46Z","title_canon_sha256":"235ec71ad22b24981739860bc770fb4d6ca792110e09b7a1852bb16c7a4dbb94"},"schema_version":"1.0","source":{"id":"2109.07380","kind":"arxiv","version":1}},"canonical_sha256":"7593236de29ae772ad9989e55e294e9579850bfe7e40bf630f691c4d756544d6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7593236de29ae772ad9989e55e294e9579850bfe7e40bf630f691c4d756544d6","first_computed_at":"2026-07-05T03:14:48.506378Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:14:48.506378Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9AlFspElhgiv+JYIDpDKcy8LrWT3aI9Lipft/Ofzf/Xj/EtXELVGl+QV+Nrb8MOBfU5sUhwb9EK3J+yIYre6CQ==","signature_status":"signed_v1","signed_at":"2026-07-05T03:14:48.506909Z","signed_message":"canonical_sha256_bytes"},"source_id":"2109.07380","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4301c8ad28a5d9f6fe5542b6c214e712503ac2c3456f30d3603df1fbce73a4f1","sha256:4940d73d8f4f4c1a6b18a1d51767224b1f44f087fc00ac6184637c7d61c25825"],"state_sha256":"7b50febf0b7189676d58555ee83643b6a8854c53c2cddbdfe90124f2626d7615"}