{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:RF6SSLSNECZ5FB6IZXKI6P7YG4","short_pith_number":"pith:RF6SSLSN","schema_version":"1.0","canonical_sha256":"897d292e4d20b3d287c8cdd48f3ff8370ae6c727381f2d7d0942a8a63f46ec2b","source":{"kind":"arxiv","id":"1906.04279","version":3},"attestation_state":"computed","paper":{"title":"Exploration via Hindsight Goal Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Jian Peng, Kefan Dong, Qiang Liu, Yuan Zhou, Zhizhou Ren","submitted_at":"2019-06-10T21:21:18Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1906.04279","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-10T21:21:18Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"d5349cc2c0ab488b57e091c502f2176d63564a6229c4838ed780f18f12a3aed9","abstract_canon_sha256":"17847bdd143da7d903eff660934e9e0c6a6b8800eafcb208211fa845143e2978"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:26:57.534747Z","signature_b64":"/Y930WuyPwSd2tCIEI5DdPmtjhhLyOaSnJyjyWGDlNT7rK8w1cTNgbVOCaoSWdb6rpJA8KPbp4HZmq2/RRJGBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"897d292e4d20b3d287c8cdd48f3ff8370ae6c727381f2d7d0942a8a63f46ec2b","last_reissued_at":"2026-07-05T00:26:57.534258Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:26:57.534258Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Exploration via Hindsight Goal Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Jian Peng, Kefan Dong, Qiang Liu, Yuan Zhou, Zhizhou Ren","submitted_at":"2019-06-10T21:21:18Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.04279","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1906.04279/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1906.04279","created_at":"2026-07-05T00:26:57.534310+00:00"},{"alias_kind":"arxiv_version","alias_value":"1906.04279v3","created_at":"2026-07-05T00:26:57.534310+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.04279","created_at":"2026-07-05T00:26:57.534310+00:00"},{"alias_kind":"pith_short_12","alias_value":"RF6SSLSNECZ5","created_at":"2026-07-05T00:26:57.534310+00:00"},{"alias_kind":"pith_short_16","alias_value":"RF6SSLSNECZ5FB6I","created_at":"2026-07-05T00:26:57.534310+00:00"},{"alias_kind":"pith_short_8","alias_value":"RF6SSLSN","created_at":"2026-07-05T00:26:57.534310+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RF6SSLSNECZ5FB6IZXKI6P7YG4","json":"https://pith.science/pith/RF6SSLSNECZ5FB6IZXKI6P7YG4.json","graph_json":"https://pith.science/api/pith-number/RF6SSLSNECZ5FB6IZXKI6P7YG4/graph.json","events_json":"https://pith.science/api/pith-number/RF6SSLSNECZ5FB6IZXKI6P7YG4/events.json","paper":"https://pith.science/paper/RF6SSLSN"},"agent_actions":{"view_html":"https://pith.science/pith/RF6SSLSNECZ5FB6IZXKI6P7YG4","download_json":"https://pith.science/pith/RF6SSLSNECZ5FB6IZXKI6P7YG4.json","view_paper":"https://pith.science/paper/RF6SSLSN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1906.04279&json=true","fetch_graph":"https://pith.science/api/pith-number/RF6SSLSNECZ5FB6IZXKI6P7YG4/graph.json","fetch_events":"https://pith.science/api/pith-number/RF6SSLSNECZ5FB6IZXKI6P7YG4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RF6SSLSNECZ5FB6IZXKI6P7YG4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RF6SSLSNECZ5FB6IZXKI6P7YG4/action/storage_attestation","attest_author":"https://pith.science/pith/RF6SSLSNECZ5FB6IZXKI6P7YG4/action/author_attestation","sign_citation":"https://pith.science/pith/RF6SSLSNECZ5FB6IZXKI6P7YG4/action/citation_signature","submit_replication":"https://pith.science/pith/RF6SSLSNECZ5FB6IZXKI6P7YG4/action/replication_record"}},"created_at":"2026-07-05T00:26:57.534310+00:00","updated_at":"2026-07-05T00:26:57.534310+00:00"}