{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:RF6SSLSNECZ5FB6IZXKI6P7YG4","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":"17847bdd143da7d903eff660934e9e0c6a6b8800eafcb208211fa845143e2978","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-10T21:21:18Z","title_canon_sha256":"d5349cc2c0ab488b57e091c502f2176d63564a6229c4838ed780f18f12a3aed9"},"schema_version":"1.0","source":{"id":"1906.04279","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.04279","created_at":"2026-07-05T00:26:57Z"},{"alias_kind":"arxiv_version","alias_value":"1906.04279v3","created_at":"2026-07-05T00:26:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.04279","created_at":"2026-07-05T00:26:57Z"},{"alias_kind":"pith_short_12","alias_value":"RF6SSLSNECZ5","created_at":"2026-07-05T00:26:57Z"},{"alias_kind":"pith_short_16","alias_value":"RF6SSLSNECZ5FB6I","created_at":"2026-07-05T00:26:57Z"},{"alias_kind":"pith_short_8","alias_value":"RF6SSLSN","created_at":"2026-07-05T00:26:57Z"}],"graph_snapshots":[{"event_id":"sha256:cd8022acc127f0a7ca12214ed498c3825d1864c11a595ae2fe6db0440b3d4544","target":"graph","created_at":"2026-07-05T00:26:57Z","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/1906.04279/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Goal-oriented reinforcement learning has recently been a practical framework for robotic manipulation tasks, in which an agent is required to reach a certain goal defined by a function on the state space. However, the sparsity of such reward definition makes traditional reinforcement learning algorithms very inefficient. Hindsight Experience Replay (HER), a recent advance, has greatly improved sample efficiency and practical applicability for such problems. It exploits previous replays by constructing imaginary goals in a simple heuristic way, acting like an implicit curriculum to alleviate th","authors_text":"Jian Peng, Kefan Dong, Qiang Liu, Yuan Zhou, Zhizhou Ren","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-10T21:21:18Z","title":"Exploration via Hindsight Goal Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.04279","kind":"arxiv","version":3},"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:f04b813fe825034629d27120260e269192b30a70f70fff90ba8a167257671f64","target":"record","created_at":"2026-07-05T00:26:57Z","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":"17847bdd143da7d903eff660934e9e0c6a6b8800eafcb208211fa845143e2978","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-10T21:21:18Z","title_canon_sha256":"d5349cc2c0ab488b57e091c502f2176d63564a6229c4838ed780f18f12a3aed9"},"schema_version":"1.0","source":{"id":"1906.04279","kind":"arxiv","version":3}},"canonical_sha256":"897d292e4d20b3d287c8cdd48f3ff8370ae6c727381f2d7d0942a8a63f46ec2b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"897d292e4d20b3d287c8cdd48f3ff8370ae6c727381f2d7d0942a8a63f46ec2b","first_computed_at":"2026-07-05T00:26:57.534258Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:26:57.534258Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/Y930WuyPwSd2tCIEI5DdPmtjhhLyOaSnJyjyWGDlNT7rK8w1cTNgbVOCaoSWdb6rpJA8KPbp4HZmq2/RRJGBA==","signature_status":"signed_v1","signed_at":"2026-07-05T00:26:57.534747Z","signed_message":"canonical_sha256_bytes"},"source_id":"1906.04279","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f04b813fe825034629d27120260e269192b30a70f70fff90ba8a167257671f64","sha256:cd8022acc127f0a7ca12214ed498c3825d1864c11a595ae2fe6db0440b3d4544"],"state_sha256":"39ea309eb9cf4c4a1a046eabe85e7a41afe9b1d7411e9d5ece43dbde13e975f3"}