{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:WY7U2RU6GIR7XSTEOKNAYQVDEA","short_pith_number":"pith:WY7U2RU6","canonical_record":{"source":{"id":"2107.00306","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-07-01T08:52:45Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"09d17b4ad5a24e33b15159360a0924f12656ca2a89aea60e46f1489ebf9a4b5c","abstract_canon_sha256":"9d0c1b2f51264cbadb1cb701449094aa24772825930a8736370813f3af24730f"},"schema_version":"1.0"},"canonical_sha256":"b63f4d469e3223fbca64729a0c42a32035454e90423dd3dbd8f587575a6ca384","source":{"kind":"arxiv","id":"2107.00306","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2107.00306","created_at":"2026-07-05T03:35:29Z"},{"alias_kind":"arxiv_version","alias_value":"2107.00306v2","created_at":"2026-07-05T03:35:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.00306","created_at":"2026-07-05T03:35:29Z"},{"alias_kind":"pith_short_12","alias_value":"WY7U2RU6GIR7","created_at":"2026-07-05T03:35:29Z"},{"alias_kind":"pith_short_16","alias_value":"WY7U2RU6GIR7XSTE","created_at":"2026-07-05T03:35:29Z"},{"alias_kind":"pith_short_8","alias_value":"WY7U2RU6","created_at":"2026-07-05T03:35:29Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:WY7U2RU6GIR7XSTEOKNAYQVDEA","target":"record","payload":{"canonical_record":{"source":{"id":"2107.00306","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-07-01T08:52:45Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"09d17b4ad5a24e33b15159360a0924f12656ca2a89aea60e46f1489ebf9a4b5c","abstract_canon_sha256":"9d0c1b2f51264cbadb1cb701449094aa24772825930a8736370813f3af24730f"},"schema_version":"1.0"},"canonical_sha256":"b63f4d469e3223fbca64729a0c42a32035454e90423dd3dbd8f587575a6ca384","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:35:29.893862Z","signature_b64":"tu90YfWrALfyBl/Qe11nBy32ypxNKu/CFxD2qo+kQtdwktSXJUO0znEcNm4oQscUfc+hggKE8TRXacaeKhs7DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b63f4d469e3223fbca64729a0c42a32035454e90423dd3dbd8f587575a6ca384","last_reissued_at":"2026-07-05T03:35:29.893345Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:35:29.893345Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2107.00306","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:35:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kVHDSM+pXZXYt/HCNl/NOU/naW/6iOW7HKBVHBlqcIWE9/KvrvdaNwECQ4NLp3xyq3riny2QXsY12zgj+VCaBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T05:56:31.999095Z"},"content_sha256":"183e7c5b5ef29bd1fabd0edbc40541dc5cec41389091c1dbb02bb8515d3735a0","schema_version":"1.0","event_id":"sha256:183e7c5b5ef29bd1fabd0edbc40541dc5cec41389091c1dbb02bb8515d3735a0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:WY7U2RU6GIR7XSTEOKNAYQVDEA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MHER: Model-based Hindsight Experience Replay","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Feng Luo, Lei Han, Meng Fang, Rui Yang, Xiu Li, Yali Du","submitted_at":"2021-07-01T08:52:45Z","abstract_excerpt":"Solving multi-goal reinforcement learning (RL) problems with sparse rewards is generally challenging. Existing approaches have utilized goal relabeling on collected experiences to alleviate issues raised from sparse rewards. However, these methods are still limited in efficiency and cannot make full use of experiences. In this paper, we propose Model-based Hindsight Experience Replay (MHER), which exploits experiences more efficiently by leveraging environmental dynamics to generate virtual achieved goals. Replacing original goals with virtual goals generated from interaction with a trained dy"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.00306","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/2107.00306/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:35:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9zYcO4pJRtZEAx6TbVw5Oede9hMRLA6F+fAhTeFOzK3GXqJ2H5k2hU4TmR9SooYfkmml6T1lVwnizOQXU0+2DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T05:56:31.999508Z"},"content_sha256":"cfb829f20e9fc9ab7010edd532ff676dbe1a529146269eff535503bbff35ac12","schema_version":"1.0","event_id":"sha256:cfb829f20e9fc9ab7010edd532ff676dbe1a529146269eff535503bbff35ac12"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WY7U2RU6GIR7XSTEOKNAYQVDEA/bundle.json","state_url":"https://pith.science/pith/WY7U2RU6GIR7XSTEOKNAYQVDEA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WY7U2RU6GIR7XSTEOKNAYQVDEA/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-13T05:56:32Z","links":{"resolver":"https://pith.science/pith/WY7U2RU6GIR7XSTEOKNAYQVDEA","bundle":"https://pith.science/pith/WY7U2RU6GIR7XSTEOKNAYQVDEA/bundle.json","state":"https://pith.science/pith/WY7U2RU6GIR7XSTEOKNAYQVDEA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WY7U2RU6GIR7XSTEOKNAYQVDEA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:WY7U2RU6GIR7XSTEOKNAYQVDEA","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":"9d0c1b2f51264cbadb1cb701449094aa24772825930a8736370813f3af24730f","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-07-01T08:52:45Z","title_canon_sha256":"09d17b4ad5a24e33b15159360a0924f12656ca2a89aea60e46f1489ebf9a4b5c"},"schema_version":"1.0","source":{"id":"2107.00306","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2107.00306","created_at":"2026-07-05T03:35:29Z"},{"alias_kind":"arxiv_version","alias_value":"2107.00306v2","created_at":"2026-07-05T03:35:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.00306","created_at":"2026-07-05T03:35:29Z"},{"alias_kind":"pith_short_12","alias_value":"WY7U2RU6GIR7","created_at":"2026-07-05T03:35:29Z"},{"alias_kind":"pith_short_16","alias_value":"WY7U2RU6GIR7XSTE","created_at":"2026-07-05T03:35:29Z"},{"alias_kind":"pith_short_8","alias_value":"WY7U2RU6","created_at":"2026-07-05T03:35:29Z"}],"graph_snapshots":[{"event_id":"sha256:cfb829f20e9fc9ab7010edd532ff676dbe1a529146269eff535503bbff35ac12","target":"graph","created_at":"2026-07-05T03:35:29Z","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/2107.00306/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Solving multi-goal reinforcement learning (RL) problems with sparse rewards is generally challenging. Existing approaches have utilized goal relabeling on collected experiences to alleviate issues raised from sparse rewards. However, these methods are still limited in efficiency and cannot make full use of experiences. In this paper, we propose Model-based Hindsight Experience Replay (MHER), which exploits experiences more efficiently by leveraging environmental dynamics to generate virtual achieved goals. Replacing original goals with virtual goals generated from interaction with a trained dy","authors_text":"Feng Luo, Lei Han, Meng Fang, Rui Yang, Xiu Li, Yali Du","cross_cats":["cs.AI","cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-07-01T08:52:45Z","title":"MHER: Model-based Hindsight Experience Replay"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.00306","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":"sha256:183e7c5b5ef29bd1fabd0edbc40541dc5cec41389091c1dbb02bb8515d3735a0","target":"record","created_at":"2026-07-05T03:35:29Z","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":"9d0c1b2f51264cbadb1cb701449094aa24772825930a8736370813f3af24730f","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-07-01T08:52:45Z","title_canon_sha256":"09d17b4ad5a24e33b15159360a0924f12656ca2a89aea60e46f1489ebf9a4b5c"},"schema_version":"1.0","source":{"id":"2107.00306","kind":"arxiv","version":2}},"canonical_sha256":"b63f4d469e3223fbca64729a0c42a32035454e90423dd3dbd8f587575a6ca384","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b63f4d469e3223fbca64729a0c42a32035454e90423dd3dbd8f587575a6ca384","first_computed_at":"2026-07-05T03:35:29.893345Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:35:29.893345Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tu90YfWrALfyBl/Qe11nBy32ypxNKu/CFxD2qo+kQtdwktSXJUO0znEcNm4oQscUfc+hggKE8TRXacaeKhs7DA==","signature_status":"signed_v1","signed_at":"2026-07-05T03:35:29.893862Z","signed_message":"canonical_sha256_bytes"},"source_id":"2107.00306","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:183e7c5b5ef29bd1fabd0edbc40541dc5cec41389091c1dbb02bb8515d3735a0","sha256:cfb829f20e9fc9ab7010edd532ff676dbe1a529146269eff535503bbff35ac12"],"state_sha256":"1048477a82d1458f10b248911b718e703c630a56180daf7c5c5c2279b5de1370"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Jk23sG2x276sBxYRtxhOn/wt4Yhtk/L/LQxQwQhS9Lk85akrA8b3s/WP89IsaHlAQXkVf33Xj9bCCi062VwgDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-13T05:56:32.002369Z","bundle_sha256":"e6035a2105bcde0c8cf02841d45a436614eca71151b1060c2c8d7eb1c6bd034b"}}