{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:EOQKHRN2MFDN32I7NHP77RTJ7J","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":"47a014a3880d5da00a035f853fa4b6ce8c5566261b73a88b8174fc82696c5364","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-09T14:10:50Z","title_canon_sha256":"607735fe3c665d8d2e91030f7ced81809a549e83c20275711102cf428fba3a02"},"schema_version":"1.0","source":{"id":"2106.05091","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.05091","created_at":"2026-07-05T02:47:52Z"},{"alias_kind":"arxiv_version","alias_value":"2106.05091v1","created_at":"2026-07-05T02:47:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.05091","created_at":"2026-07-05T02:47:52Z"},{"alias_kind":"pith_short_12","alias_value":"EOQKHRN2MFDN","created_at":"2026-07-05T02:47:52Z"},{"alias_kind":"pith_short_16","alias_value":"EOQKHRN2MFDN32I7","created_at":"2026-07-05T02:47:52Z"},{"alias_kind":"pith_short_8","alias_value":"EOQKHRN2","created_at":"2026-07-05T02:47:52Z"}],"graph_snapshots":[{"event_id":"sha256:156d70bf1dd57a5dc8e77b1e60f4be94fc39624053d192d8b7caebb7b30c218e","target":"graph","created_at":"2026-07-05T02:47:52Z","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/2106.05091/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Conveying complex objectives to reinforcement learning (RL) agents can often be difficult, involving meticulous design of reward functions that are sufficiently informative yet easy enough to provide. Human-in-the-loop RL methods allow practitioners to instead interactively teach agents through tailored feedback; however, such approaches have been challenging to scale since human feedback is very expensive. In this work, we aim to make this process more sample- and feedback-efficient. We present an off-policy, interactive RL algorithm that capitalizes on the strengths of both feedback and off-","authors_text":"Kimin Lee, Laura Smith, Pieter Abbeel","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-09T14:10:50Z","title":"PEBBLE: Feedback-Efficient Interactive Reinforcement Learning via Relabeling Experience and Unsupervised Pre-training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.05091","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":"sha256:0871e694480b0eb7bae63de5d2591796b1837bc21543fc4f7ca13f057f2aae9a","target":"record","created_at":"2026-07-05T02:47:52Z","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":"47a014a3880d5da00a035f853fa4b6ce8c5566261b73a88b8174fc82696c5364","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-09T14:10:50Z","title_canon_sha256":"607735fe3c665d8d2e91030f7ced81809a549e83c20275711102cf428fba3a02"},"schema_version":"1.0","source":{"id":"2106.05091","kind":"arxiv","version":1}},"canonical_sha256":"23a0a3c5ba6146dde91f69dfffc669fa769d70180b11a091a9eab45b8481f161","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"23a0a3c5ba6146dde91f69dfffc669fa769d70180b11a091a9eab45b8481f161","first_computed_at":"2026-07-05T02:47:52.720053Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:47:52.720053Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VptA+NptwbQNXczdiZ8HXiXmMUQo0ljNrhzmGkHF2Sw2RjFAgqqd2sRNnkLksEqlchwMroxEQTKwTTFokoxBCg==","signature_status":"signed_v1","signed_at":"2026-07-05T02:47:52.720468Z","signed_message":"canonical_sha256_bytes"},"source_id":"2106.05091","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0871e694480b0eb7bae63de5d2591796b1837bc21543fc4f7ca13f057f2aae9a","sha256:156d70bf1dd57a5dc8e77b1e60f4be94fc39624053d192d8b7caebb7b30c218e"],"state_sha256":"63586757d4615b794fd0af26ec6ce02d87372574390c0e64e6056945bfb7440d"}