{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:C4WC5LH6U6A7SPIGC5OGATNVXM","short_pith_number":"pith:C4WC5LH6","canonical_record":{"source":{"id":"2010.12914","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-24T15:29:02Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"93683b28c84643df5b10cb837af7117658279e725004b2436700f9a0355c2f02","abstract_canon_sha256":"34a877aaa0ea77ae482ffd6704d6b592caac9431bc48084c3fc30903f9c453d3"},"schema_version":"1.0"},"canonical_sha256":"172c2eacfea781f93d06175c604db5bb177f007ad24e435779a8a71d0944a08d","source":{"kind":"arxiv","id":"2010.12914","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2010.12914","created_at":"2026-07-05T02:52:00Z"},{"alias_kind":"arxiv_version","alias_value":"2010.12914v3","created_at":"2026-07-05T02:52:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.12914","created_at":"2026-07-05T02:52:00Z"},{"alias_kind":"pith_short_12","alias_value":"C4WC5LH6U6A7","created_at":"2026-07-05T02:52:00Z"},{"alias_kind":"pith_short_16","alias_value":"C4WC5LH6U6A7SPIG","created_at":"2026-07-05T02:52:00Z"},{"alias_kind":"pith_short_8","alias_value":"C4WC5LH6","created_at":"2026-07-05T02:52:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:C4WC5LH6U6A7SPIGC5OGATNVXM","target":"record","payload":{"canonical_record":{"source":{"id":"2010.12914","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-24T15:29:02Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"93683b28c84643df5b10cb837af7117658279e725004b2436700f9a0355c2f02","abstract_canon_sha256":"34a877aaa0ea77ae482ffd6704d6b592caac9431bc48084c3fc30903f9c453d3"},"schema_version":"1.0"},"canonical_sha256":"172c2eacfea781f93d06175c604db5bb177f007ad24e435779a8a71d0944a08d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:52:00.065531Z","signature_b64":"35ReAnh0jr/4+4E3dNaFQVhLpddq+9pxoTD9J5KD9pcOkuHQZFekGp2GjV8xMUm8h/WMJ/t2XGp2RF3dUnlZBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"172c2eacfea781f93d06175c604db5bb177f007ad24e435779a8a71d0944a08d","last_reissued_at":"2026-07-05T02:52:00.064971Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:52:00.064971Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2010.12914","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:52:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"K9fPB8wuwpMTVdjk+XXaVQPG7fI0IWaAp3Ii6vuTvvnIvknOx03VNxC/DeReCR2EZMveDQ3G4Pq15xI/OkuMCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T13:30:43.525167Z"},"content_sha256":"1d26175ebeef35a37c690b8db4fc4dce55aeedde6e561c94e75057eb9ad04109","schema_version":"1.0","event_id":"sha256:1d26175ebeef35a37c690b8db4fc4dce55aeedde6e561c94e75057eb9ad04109"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:C4WC5LH6U6A7SPIGC5OGATNVXM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Planning with Exploration: Addressing Dynamics Bottleneck in Model-based Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Junge Zhang, Qiyue Yin, Wenzhen Huang, Xiyao Wang","submitted_at":"2020-10-24T15:29:02Z","abstract_excerpt":"Model-based reinforcement learning (MBRL) is believed to have higher sample efficiency compared with model-free reinforcement learning (MFRL). However, MBRL is plagued by dynamics bottleneck dilemma. Dynamics bottleneck dilemma is the phenomenon that the performance of the algorithm falls into the local optimum instead of increasing when the interaction step with the environment increases, which means more data can not bring better performance. In this paper, we find that the trajectory reward estimation error is the main reason that causes dynamics bottleneck dilemma through theoretical analy"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.12914","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/2010.12914/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":"2026-07-05T02:52:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6V2ez87oDuP5OLQGFTh/O8brHgeqNqozT78zM7k5pALs7Jw/+pxcuOdEuljRYXT0urkHzjNbIsLoqT5j97VXCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T13:30:43.525619Z"},"content_sha256":"a1314fef94f4700aa8f1773d1dbfaddd4f174ae5ee7d361eb62e913605f2d2bb","schema_version":"1.0","event_id":"sha256:a1314fef94f4700aa8f1773d1dbfaddd4f174ae5ee7d361eb62e913605f2d2bb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/C4WC5LH6U6A7SPIGC5OGATNVXM/bundle.json","state_url":"https://pith.science/pith/C4WC5LH6U6A7SPIGC5OGATNVXM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/C4WC5LH6U6A7SPIGC5OGATNVXM/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":"2026-07-07T13:30:43Z","links":{"resolver":"https://pith.science/pith/C4WC5LH6U6A7SPIGC5OGATNVXM","bundle":"https://pith.science/pith/C4WC5LH6U6A7SPIGC5OGATNVXM/bundle.json","state":"https://pith.science/pith/C4WC5LH6U6A7SPIGC5OGATNVXM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/C4WC5LH6U6A7SPIGC5OGATNVXM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:C4WC5LH6U6A7SPIGC5OGATNVXM","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":"34a877aaa0ea77ae482ffd6704d6b592caac9431bc48084c3fc30903f9c453d3","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-24T15:29:02Z","title_canon_sha256":"93683b28c84643df5b10cb837af7117658279e725004b2436700f9a0355c2f02"},"schema_version":"1.0","source":{"id":"2010.12914","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2010.12914","created_at":"2026-07-05T02:52:00Z"},{"alias_kind":"arxiv_version","alias_value":"2010.12914v3","created_at":"2026-07-05T02:52:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.12914","created_at":"2026-07-05T02:52:00Z"},{"alias_kind":"pith_short_12","alias_value":"C4WC5LH6U6A7","created_at":"2026-07-05T02:52:00Z"},{"alias_kind":"pith_short_16","alias_value":"C4WC5LH6U6A7SPIG","created_at":"2026-07-05T02:52:00Z"},{"alias_kind":"pith_short_8","alias_value":"C4WC5LH6","created_at":"2026-07-05T02:52:00Z"}],"graph_snapshots":[{"event_id":"sha256:a1314fef94f4700aa8f1773d1dbfaddd4f174ae5ee7d361eb62e913605f2d2bb","target":"graph","created_at":"2026-07-05T02:52:00Z","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/2010.12914/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Model-based reinforcement learning (MBRL) is believed to have higher sample efficiency compared with model-free reinforcement learning (MFRL). However, MBRL is plagued by dynamics bottleneck dilemma. Dynamics bottleneck dilemma is the phenomenon that the performance of the algorithm falls into the local optimum instead of increasing when the interaction step with the environment increases, which means more data can not bring better performance. In this paper, we find that the trajectory reward estimation error is the main reason that causes dynamics bottleneck dilemma through theoretical analy","authors_text":"Junge Zhang, Qiyue Yin, Wenzhen Huang, Xiyao Wang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-24T15:29:02Z","title":"Planning with Exploration: Addressing Dynamics Bottleneck in Model-based Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.12914","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":"sha256:1d26175ebeef35a37c690b8db4fc4dce55aeedde6e561c94e75057eb9ad04109","target":"record","created_at":"2026-07-05T02:52:00Z","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":"34a877aaa0ea77ae482ffd6704d6b592caac9431bc48084c3fc30903f9c453d3","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-24T15:29:02Z","title_canon_sha256":"93683b28c84643df5b10cb837af7117658279e725004b2436700f9a0355c2f02"},"schema_version":"1.0","source":{"id":"2010.12914","kind":"arxiv","version":3}},"canonical_sha256":"172c2eacfea781f93d06175c604db5bb177f007ad24e435779a8a71d0944a08d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"172c2eacfea781f93d06175c604db5bb177f007ad24e435779a8a71d0944a08d","first_computed_at":"2026-07-05T02:52:00.064971Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:52:00.064971Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"35ReAnh0jr/4+4E3dNaFQVhLpddq+9pxoTD9J5KD9pcOkuHQZFekGp2GjV8xMUm8h/WMJ/t2XGp2RF3dUnlZBg==","signature_status":"signed_v1","signed_at":"2026-07-05T02:52:00.065531Z","signed_message":"canonical_sha256_bytes"},"source_id":"2010.12914","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1d26175ebeef35a37c690b8db4fc4dce55aeedde6e561c94e75057eb9ad04109","sha256:a1314fef94f4700aa8f1773d1dbfaddd4f174ae5ee7d361eb62e913605f2d2bb"],"state_sha256":"166709d3498810415133179793f7830b9672e6d679f91485d6f5cb30a546bc35"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ScZx2T5ieILpG0x1MBeU/CvX6pU3o63lhp3NFPZDWgxblpFmNYEp9EUGDD0oHphT6HjMwneILo8Oq8XIOR4qBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T13:30:43.527503Z","bundle_sha256":"fbd2743a0f75b2edcd2c5331ab503c1f935dbb2484102961e4c91b01a9fd3501"}}