{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:JMV2FC4BBJQNY7DP5CRC7LL7WO","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":"0e387be2a45d021c3462ba4dadecc232d64c7dcffec4f5487ff6dfffc0e13391","cross_cats_sorted":["cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-10-05T23:38:31Z","title_canon_sha256":"c2ef1274c31f3e2088e834a1101c5c33d599e5811563eca773d68815b4a5f777"},"schema_version":"1.0","source":{"id":"2110.02414","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.02414","created_at":"2026-07-05T06:39:28Z"},{"alias_kind":"arxiv_version","alias_value":"2110.02414v2","created_at":"2026-07-05T06:39:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.02414","created_at":"2026-07-05T06:39:28Z"},{"alias_kind":"pith_short_12","alias_value":"JMV2FC4BBJQN","created_at":"2026-07-05T06:39:28Z"},{"alias_kind":"pith_short_16","alias_value":"JMV2FC4BBJQNY7DP","created_at":"2026-07-05T06:39:28Z"},{"alias_kind":"pith_short_8","alias_value":"JMV2FC4B","created_at":"2026-07-05T06:39:28Z"}],"graph_snapshots":[{"event_id":"sha256:25eabbf8d5f164c1935ab2326281ded915e774194edef52a7b9a6981f3896b5c","target":"graph","created_at":"2026-07-05T06:39:28Z","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/2110.02414/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Qiang Wang, Robert McCarthy, Stephen J. Redmond","cross_cats":["cs.RO"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-10-05T23:38:31Z","title":"Imaginary Hindsight Experience Replay: Curious Model-based Learning for Sparse Reward Tasks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.02414","kind":"arxiv","version":2},"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":"sha256:925ad801af025236438b85f2dc8f593e66a95e7f4fc3620dcfd96cde954015a8","target":"record","created_at":"2026-07-05T06:39:28Z","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":"0e387be2a45d021c3462ba4dadecc232d64c7dcffec4f5487ff6dfffc0e13391","cross_cats_sorted":["cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-10-05T23:38:31Z","title_canon_sha256":"c2ef1274c31f3e2088e834a1101c5c33d599e5811563eca773d68815b4a5f777"},"schema_version":"1.0","source":{"id":"2110.02414","kind":"arxiv","version":2}},"canonical_sha256":"4b2ba28b810a60dc7c6fe8a22fad7fb390d9e8980f9b15c318639c9d5a97e16e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4b2ba28b810a60dc7c6fe8a22fad7fb390d9e8980f9b15c318639c9d5a97e16e","first_computed_at":"2026-07-05T06:39:28.750723Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:39:28.750723Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NDX5p6dMk5dnpBvD5b/bSbd2R4hoZNTzvShBQhL3VarcZh1MwWMRgwYJvfhKIQcfkdyvzuUs/qVfzkBOHQb9Cw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:39:28.751238Z","signed_message":"canonical_sha256_bytes"},"source_id":"2110.02414","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:925ad801af025236438b85f2dc8f593e66a95e7f4fc3620dcfd96cde954015a8","sha256:25eabbf8d5f164c1935ab2326281ded915e774194edef52a7b9a6981f3896b5c"],"state_sha256":"be8cb1526f3a0f26fb0b06ab860fbb382f2c37fdf938bfe01dac5f0a45d0a8d0"}