{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:JMV2FC4BBJQNY7DP5CRC7LL7WO","short_pith_number":"pith:JMV2FC4B","schema_version":"1.0","canonical_sha256":"4b2ba28b810a60dc7c6fe8a22fad7fb390d9e8980f9b15c318639c9d5a97e16e","source":{"kind":"arxiv","id":"2110.02414","version":2},"attestation_state":"computed","paper":{"title":"Imaginary Hindsight Experience Replay: Curious Model-based Learning for Sparse Reward Tasks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.LG","authors_text":"Qiang Wang, Robert McCarthy, Stephen J. Redmond","submitted_at":"2021-10-05T23:38:31Z","abstract_excerpt":"Model-based reinforcement learning is a promising learning strategy for practical robotic applications due to its improved data-efficiency versus model-free counterparts. However, current state-of-the-art model-based methods rely on shaped reward signals, which can be difficult to design and implement. To remedy this, we propose a simple model-based method tailored for sparse-reward multi-goal tasks that foregoes the need for complicated reward engineering. This approach, termed Imaginary Hindsight Experience Replay, minimises real-world interactions by incorporating imaginary data into policy"},"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":"2110.02414","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-10-05T23:38:31Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"c2ef1274c31f3e2088e834a1101c5c33d599e5811563eca773d68815b4a5f777","abstract_canon_sha256":"0e387be2a45d021c3462ba4dadecc232d64c7dcffec4f5487ff6dfffc0e13391"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:39:28.751238Z","signature_b64":"NDX5p6dMk5dnpBvD5b/bSbd2R4hoZNTzvShBQhL3VarcZh1MwWMRgwYJvfhKIQcfkdyvzuUs/qVfzkBOHQb9Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4b2ba28b810a60dc7c6fe8a22fad7fb390d9e8980f9b15c318639c9d5a97e16e","last_reissued_at":"2026-07-05T06:39:28.750723Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:39:28.750723Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Imaginary Hindsight Experience Replay: Curious Model-based Learning for Sparse Reward Tasks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.LG","authors_text":"Qiang Wang, Robert McCarthy, Stephen J. Redmond","submitted_at":"2021-10-05T23:38:31Z","abstract_excerpt":"Model-based reinforcement learning is a promising learning strategy for practical robotic applications due to its improved data-efficiency versus model-free counterparts. However, current state-of-the-art model-based methods rely on shaped reward signals, which can be difficult to design and implement. To remedy this, we propose a simple model-based method tailored for sparse-reward multi-goal tasks that foregoes the need for complicated reward engineering. This approach, termed Imaginary Hindsight Experience Replay, minimises real-world interactions by incorporating imaginary data into policy"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.02414","kind":"arxiv","version":2},"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/2110.02414/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":"2110.02414","created_at":"2026-07-05T06:39:28.750780+00:00"},{"alias_kind":"arxiv_version","alias_value":"2110.02414v2","created_at":"2026-07-05T06:39:28.750780+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.02414","created_at":"2026-07-05T06:39:28.750780+00:00"},{"alias_kind":"pith_short_12","alias_value":"JMV2FC4BBJQN","created_at":"2026-07-05T06:39:28.750780+00:00"},{"alias_kind":"pith_short_16","alias_value":"JMV2FC4BBJQNY7DP","created_at":"2026-07-05T06:39:28.750780+00:00"},{"alias_kind":"pith_short_8","alias_value":"JMV2FC4B","created_at":"2026-07-05T06:39:28.750780+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/JMV2FC4BBJQNY7DP5CRC7LL7WO","json":"https://pith.science/pith/JMV2FC4BBJQNY7DP5CRC7LL7WO.json","graph_json":"https://pith.science/api/pith-number/JMV2FC4BBJQNY7DP5CRC7LL7WO/graph.json","events_json":"https://pith.science/api/pith-number/JMV2FC4BBJQNY7DP5CRC7LL7WO/events.json","paper":"https://pith.science/paper/JMV2FC4B"},"agent_actions":{"view_html":"https://pith.science/pith/JMV2FC4BBJQNY7DP5CRC7LL7WO","download_json":"https://pith.science/pith/JMV2FC4BBJQNY7DP5CRC7LL7WO.json","view_paper":"https://pith.science/paper/JMV2FC4B","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2110.02414&json=true","fetch_graph":"https://pith.science/api/pith-number/JMV2FC4BBJQNY7DP5CRC7LL7WO/graph.json","fetch_events":"https://pith.science/api/pith-number/JMV2FC4BBJQNY7DP5CRC7LL7WO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JMV2FC4BBJQNY7DP5CRC7LL7WO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JMV2FC4BBJQNY7DP5CRC7LL7WO/action/storage_attestation","attest_author":"https://pith.science/pith/JMV2FC4BBJQNY7DP5CRC7LL7WO/action/author_attestation","sign_citation":"https://pith.science/pith/JMV2FC4BBJQNY7DP5CRC7LL7WO/action/citation_signature","submit_replication":"https://pith.science/pith/JMV2FC4BBJQNY7DP5CRC7LL7WO/action/replication_record"}},"created_at":"2026-07-05T06:39:28.750780+00:00","updated_at":"2026-07-05T06:39:28.750780+00:00"}