{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:BLNJ5VXE4THV4Y4NUVVT7DGEAZ","short_pith_number":"pith:BLNJ5VXE","canonical_record":{"source":{"id":"2010.09546","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-19T14:19:42Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"a88837a206ef5c086e1538ae75d2602831e10586a577e5bacce9ea42ee068eac","abstract_canon_sha256":"b4521ac5f1166588394f2cdad2a2c117b5c22d8b4099e9ffd77fc648ed156c62"},"schema_version":"1.0"},"canonical_sha256":"0ada9ed6e4e4cf5e638da56b3f8cc406679927de95c1c5e069c39078ec868c00","source":{"kind":"arxiv","id":"2010.09546","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2010.09546","created_at":"2026-07-05T01:47:15Z"},{"alias_kind":"arxiv_version","alias_value":"2010.09546v2","created_at":"2026-07-05T01:47:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.09546","created_at":"2026-07-05T01:47:15Z"},{"alias_kind":"pith_short_12","alias_value":"BLNJ5VXE4THV","created_at":"2026-07-05T01:47:15Z"},{"alias_kind":"pith_short_16","alias_value":"BLNJ5VXE4THV4Y4N","created_at":"2026-07-05T01:47:15Z"},{"alias_kind":"pith_short_8","alias_value":"BLNJ5VXE","created_at":"2026-07-05T01:47:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:BLNJ5VXE4THV4Y4NUVVT7DGEAZ","target":"record","payload":{"canonical_record":{"source":{"id":"2010.09546","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-19T14:19:42Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"a88837a206ef5c086e1538ae75d2602831e10586a577e5bacce9ea42ee068eac","abstract_canon_sha256":"b4521ac5f1166588394f2cdad2a2c117b5c22d8b4099e9ffd77fc648ed156c62"},"schema_version":"1.0"},"canonical_sha256":"0ada9ed6e4e4cf5e638da56b3f8cc406679927de95c1c5e069c39078ec868c00","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:47:15.637076Z","signature_b64":"HY7fOvtBhgl4eO9w5hlJMNXlPfIDbCzfQwD5mTic7f3TMP7/BrqEyWoDQSIdlYn1SZQwMGP0CgVhkquO6F8GCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0ada9ed6e4e4cf5e638da56b3f8cc406679927de95c1c5e069c39078ec868c00","last_reissued_at":"2026-07-05T01:47:15.636684Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:47:15.636684Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2010.09546","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":"2026-07-05T01:47:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Bl7ESu6jNKVRXiojk7XTypl+FsI+waKYGHgfmRDhVKjgckQEuKAQzMdVQpD3uZsYvYvI03vKCZum5xJ+n0txAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T09:07:34.513538Z"},"content_sha256":"a73192440faec14aec511e151913b8536eb74817c3db2b6b05775e846fa03beb","schema_version":"1.0","event_id":"sha256:a73192440faec14aec511e151913b8536eb74817c3db2b6b05775e846fa03beb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:BLNJ5VXE4THV4Y4NUVVT7DGEAZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Model-based Policy Optimization with Unsupervised Model Adaptation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Han Zhao, Jian Shen, Weinan Zhang, Yong Yu","submitted_at":"2020-10-19T14:19:42Z","abstract_excerpt":"Model-based reinforcement learning methods learn a dynamics model with real data sampled from the environment and leverage it to generate simulated data to derive an agent. However, due to the potential distribution mismatch between simulated data and real data, this could lead to degraded performance. Despite much effort being devoted to reducing this distribution mismatch, existing methods fail to solve it explicitly. In this paper, we investigate how to bridge the gap between real and simulated data due to inaccurate model estimation for better policy optimization. To begin with, we first d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.09546","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/2010.09546/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":"2026-07-05T01:47:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MoZUHXo32On7NzadIckZDAdKwdRfzfLUI2ZKMDBeU1nRZxziKXX11q9ivJZKm2/CoBu1XXnqM3ajqNhRNyFjDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T09:07:34.513914Z"},"content_sha256":"7e3238203e3424678e8c5e58156fcac541b4ebee2f360957edea15a24ff55b5a","schema_version":"1.0","event_id":"sha256:7e3238203e3424678e8c5e58156fcac541b4ebee2f360957edea15a24ff55b5a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BLNJ5VXE4THV4Y4NUVVT7DGEAZ/bundle.json","state_url":"https://pith.science/pith/BLNJ5VXE4THV4Y4NUVVT7DGEAZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BLNJ5VXE4THV4Y4NUVVT7DGEAZ/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":"2026-07-05T09:07:34Z","links":{"resolver":"https://pith.science/pith/BLNJ5VXE4THV4Y4NUVVT7DGEAZ","bundle":"https://pith.science/pith/BLNJ5VXE4THV4Y4NUVVT7DGEAZ/bundle.json","state":"https://pith.science/pith/BLNJ5VXE4THV4Y4NUVVT7DGEAZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BLNJ5VXE4THV4Y4NUVVT7DGEAZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:BLNJ5VXE4THV4Y4NUVVT7DGEAZ","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":"b4521ac5f1166588394f2cdad2a2c117b5c22d8b4099e9ffd77fc648ed156c62","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-19T14:19:42Z","title_canon_sha256":"a88837a206ef5c086e1538ae75d2602831e10586a577e5bacce9ea42ee068eac"},"schema_version":"1.0","source":{"id":"2010.09546","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2010.09546","created_at":"2026-07-05T01:47:15Z"},{"alias_kind":"arxiv_version","alias_value":"2010.09546v2","created_at":"2026-07-05T01:47:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.09546","created_at":"2026-07-05T01:47:15Z"},{"alias_kind":"pith_short_12","alias_value":"BLNJ5VXE4THV","created_at":"2026-07-05T01:47:15Z"},{"alias_kind":"pith_short_16","alias_value":"BLNJ5VXE4THV4Y4N","created_at":"2026-07-05T01:47:15Z"},{"alias_kind":"pith_short_8","alias_value":"BLNJ5VXE","created_at":"2026-07-05T01:47:15Z"}],"graph_snapshots":[{"event_id":"sha256:7e3238203e3424678e8c5e58156fcac541b4ebee2f360957edea15a24ff55b5a","target":"graph","created_at":"2026-07-05T01:47:15Z","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/2010.09546/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Model-based reinforcement learning methods learn a dynamics model with real data sampled from the environment and leverage it to generate simulated data to derive an agent. However, due to the potential distribution mismatch between simulated data and real data, this could lead to degraded performance. Despite much effort being devoted to reducing this distribution mismatch, existing methods fail to solve it explicitly. In this paper, we investigate how to bridge the gap between real and simulated data due to inaccurate model estimation for better policy optimization. To begin with, we first d","authors_text":"Han Zhao, Jian Shen, Weinan Zhang, Yong Yu","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-19T14:19:42Z","title":"Model-based Policy Optimization with Unsupervised Model Adaptation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.09546","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:a73192440faec14aec511e151913b8536eb74817c3db2b6b05775e846fa03beb","target":"record","created_at":"2026-07-05T01:47:15Z","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":"b4521ac5f1166588394f2cdad2a2c117b5c22d8b4099e9ffd77fc648ed156c62","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-19T14:19:42Z","title_canon_sha256":"a88837a206ef5c086e1538ae75d2602831e10586a577e5bacce9ea42ee068eac"},"schema_version":"1.0","source":{"id":"2010.09546","kind":"arxiv","version":2}},"canonical_sha256":"0ada9ed6e4e4cf5e638da56b3f8cc406679927de95c1c5e069c39078ec868c00","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0ada9ed6e4e4cf5e638da56b3f8cc406679927de95c1c5e069c39078ec868c00","first_computed_at":"2026-07-05T01:47:15.636684Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:47:15.636684Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HY7fOvtBhgl4eO9w5hlJMNXlPfIDbCzfQwD5mTic7f3TMP7/BrqEyWoDQSIdlYn1SZQwMGP0CgVhkquO6F8GCA==","signature_status":"signed_v1","signed_at":"2026-07-05T01:47:15.637076Z","signed_message":"canonical_sha256_bytes"},"source_id":"2010.09546","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a73192440faec14aec511e151913b8536eb74817c3db2b6b05775e846fa03beb","sha256:7e3238203e3424678e8c5e58156fcac541b4ebee2f360957edea15a24ff55b5a"],"state_sha256":"c3792a0bad397d69b160f0e7a4311d25f7a058020632a06a6a55ab4212239f8d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fLsaKh7qoxKnuZL4Gj03WTVMM7V1aDn2Vq5AkRKwfVmt3LWst5HfkPkubpjxwWkVctGW34AFfTODh8PkNmbfCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-05T09:07:34.515927Z","bundle_sha256":"60cb958fec9c6080b904ddd58faa019f8a4e61ed905ee37598277e172b31b2e3"}}