{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:ZNCI6NSIJS3Y63ZKCVXVEESCI3","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":"c00b515c39b8243b3758c8eb5e4e51ed9b5d27ef23ce65754fef8fd3c6e57333","cross_cats_sorted":["cs.AI","cs.NE","cs.RO","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-26T18:57:05Z","title_canon_sha256":"156d30e746cecac55ea3a52c849bfb374d0525aef0c4c95f0597511e6b14b1e9"},"schema_version":"1.0","source":{"id":"2002.11708","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2002.11708","created_at":"2026-07-05T00:44:04Z"},{"alias_kind":"arxiv_version","alias_value":"2002.11708v1","created_at":"2026-07-05T00:44:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.11708","created_at":"2026-07-05T00:44:04Z"},{"alias_kind":"pith_short_12","alias_value":"ZNCI6NSIJS3Y","created_at":"2026-07-05T00:44:04Z"},{"alias_kind":"pith_short_16","alias_value":"ZNCI6NSIJS3Y63ZK","created_at":"2026-07-05T00:44:04Z"},{"alias_kind":"pith_short_8","alias_value":"ZNCI6NSI","created_at":"2026-07-05T00:44:04Z"}],"graph_snapshots":[{"event_id":"sha256:402f24c7d5f46355bfae25b15182d21f63c4e4ffc0955a80d57ee4ad24cbac8a","target":"graph","created_at":"2026-07-05T00:44:04Z","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/2002.11708/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"One of the key reasons for the high sample complexity in reinforcement learning (RL) is the inability to transfer knowledge from one task to another. In standard multi-task RL settings, low-reward data collected while trying to solve one task provides little to no signal for solving that particular task and is hence effectively wasted. However, we argue that this data, which is uninformative for one task, is likely a rich source of information for other tasks. To leverage this insight and efficiently reuse data, we present Generalized Hindsight: an approximate inverse reinforcement learning te","authors_text":"Alexander C. Li, Lerrel Pinto, Pieter Abbeel","cross_cats":["cs.AI","cs.NE","cs.RO","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-26T18:57:05Z","title":"Generalized Hindsight for Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.11708","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":"sha256:0f7c0f5c476bf1acff9ce298190e24f289d22b20ef1ed825051a265b29d0908b","target":"record","created_at":"2026-07-05T00:44:04Z","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":"c00b515c39b8243b3758c8eb5e4e51ed9b5d27ef23ce65754fef8fd3c6e57333","cross_cats_sorted":["cs.AI","cs.NE","cs.RO","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-26T18:57:05Z","title_canon_sha256":"156d30e746cecac55ea3a52c849bfb374d0525aef0c4c95f0597511e6b14b1e9"},"schema_version":"1.0","source":{"id":"2002.11708","kind":"arxiv","version":1}},"canonical_sha256":"cb448f36484cb78f6f2a156f52124246c9635ca2093a8f89e624837acab5f8a3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cb448f36484cb78f6f2a156f52124246c9635ca2093a8f89e624837acab5f8a3","first_computed_at":"2026-07-05T00:44:04.891932Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:44:04.891932Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hODgCoA4vZFSVUO62HEmUxtDbfHXvyaV5I5QYHeuqDimKmv7gz78Cj/g3HBv37BmVW7L2RwipWamDai9SlciDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T00:44:04.892263Z","signed_message":"canonical_sha256_bytes"},"source_id":"2002.11708","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0f7c0f5c476bf1acff9ce298190e24f289d22b20ef1ed825051a265b29d0908b","sha256:402f24c7d5f46355bfae25b15182d21f63c4e4ffc0955a80d57ee4ad24cbac8a"],"state_sha256":"36baa9952a9dd8095475d2aa3f2a648ba245a6b580c8196ad86cbd37df41995b"}