{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:GWJB2FMEIR5UDEOJ4JSKY3C62L","short_pith_number":"pith:GWJB2FME","canonical_record":{"source":{"id":"2107.01825","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-07-05T07:18:20Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"bdbb67575ed81d2725f7676d330bc981e4f3435731b6f0f8272c4d9e1f9fa1dd","abstract_canon_sha256":"24643a7b26eb06aaa57fbf193640b79783445a622ceb7101d617311949b3dc78"},"schema_version":"1.0"},"canonical_sha256":"35921d1584447b4191c9e264ac6c5ed2c5a814ad7e42a4990d00ba04d2c5fa85","source":{"kind":"arxiv","id":"2107.01825","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2107.01825","created_at":"2026-07-05T02:55:01Z"},{"alias_kind":"arxiv_version","alias_value":"2107.01825v1","created_at":"2026-07-05T02:55:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.01825","created_at":"2026-07-05T02:55:01Z"},{"alias_kind":"pith_short_12","alias_value":"GWJB2FMEIR5U","created_at":"2026-07-05T02:55:01Z"},{"alias_kind":"pith_short_16","alias_value":"GWJB2FMEIR5UDEOJ","created_at":"2026-07-05T02:55:01Z"},{"alias_kind":"pith_short_8","alias_value":"GWJB2FME","created_at":"2026-07-05T02:55:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:GWJB2FMEIR5UDEOJ4JSKY3C62L","target":"record","payload":{"canonical_record":{"source":{"id":"2107.01825","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-07-05T07:18:20Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"bdbb67575ed81d2725f7676d330bc981e4f3435731b6f0f8272c4d9e1f9fa1dd","abstract_canon_sha256":"24643a7b26eb06aaa57fbf193640b79783445a622ceb7101d617311949b3dc78"},"schema_version":"1.0"},"canonical_sha256":"35921d1584447b4191c9e264ac6c5ed2c5a814ad7e42a4990d00ba04d2c5fa85","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:55:01.025359Z","signature_b64":"25ocCab7UAhtn0SUW3oNkzl84Jk/4uWMuDUmyF7zIlUcne5ALsX/li+CvhF0F2y6AWfMhnN8tJvnRzRsfsYLAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"35921d1584447b4191c9e264ac6c5ed2c5a814ad7e42a4990d00ba04d2c5fa85","last_reissued_at":"2026-07-05T02:55:01.024894Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:55:01.024894Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2107.01825","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:55:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZQtCYfX+QetlbcjTS7NXfYRPKAasdEHWn/Lhp8+25QOtbq4K4z0GladJUMfOvIz9YOUpD9v9OYUWqr3tP+/RDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T13:20:31.536095Z"},"content_sha256":"de27471bcb4ad1a54677712b56f6a8ea297a8800f3a36c45ebabb5bb6a52afba","schema_version":"1.0","event_id":"sha256:de27471bcb4ad1a54677712b56f6a8ea297a8800f3a36c45ebabb5bb6a52afba"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:GWJB2FMEIR5UDEOJ4JSKY3C62L","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Sample Efficient Reinforcement Learning via Model-Ensemble Exploration and Exploitation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Dijun Luo, Li Xiao, Wanpeng Zhang, Yao Yao, Zhicheng An","submitted_at":"2021-07-05T07:18:20Z","abstract_excerpt":"Model-based deep reinforcement learning has achieved success in various domains that require high sample efficiencies, such as Go and robotics. However, there are some remaining issues, such as planning efficient explorations to learn more accurate dynamic models, evaluating the uncertainty of the learned models, and more rational utilization of models. To mitigate these issues, we present MEEE, a model-ensemble method that consists of optimistic exploration and weighted exploitation. During exploration, unlike prior methods directly selecting the optimal action that maximizes the expected acc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.01825","kind":"arxiv","version":1},"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/2107.01825/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":"2026-07-05T02:55:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jtEBMOR4XjFrj8tawq3aZYuDgHflerUJRpzBNqFB1p6e8kxAqkt3cdIpaLszDuPQxO7elk1dk5fEuQH9PVtXDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T13:20:31.536592Z"},"content_sha256":"9b834d531fdeaa9c158ec0e4f4c0f0e7827f5951499d5e18aedd372ca25b05fb","schema_version":"1.0","event_id":"sha256:9b834d531fdeaa9c158ec0e4f4c0f0e7827f5951499d5e18aedd372ca25b05fb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GWJB2FMEIR5UDEOJ4JSKY3C62L/bundle.json","state_url":"https://pith.science/pith/GWJB2FMEIR5UDEOJ4JSKY3C62L/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GWJB2FMEIR5UDEOJ4JSKY3C62L/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":"2026-08-05T13:20:31Z","links":{"resolver":"https://pith.science/pith/GWJB2FMEIR5UDEOJ4JSKY3C62L","bundle":"https://pith.science/pith/GWJB2FMEIR5UDEOJ4JSKY3C62L/bundle.json","state":"https://pith.science/pith/GWJB2FMEIR5UDEOJ4JSKY3C62L/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GWJB2FMEIR5UDEOJ4JSKY3C62L/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:GWJB2FMEIR5UDEOJ4JSKY3C62L","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":"24643a7b26eb06aaa57fbf193640b79783445a622ceb7101d617311949b3dc78","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-07-05T07:18:20Z","title_canon_sha256":"bdbb67575ed81d2725f7676d330bc981e4f3435731b6f0f8272c4d9e1f9fa1dd"},"schema_version":"1.0","source":{"id":"2107.01825","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2107.01825","created_at":"2026-07-05T02:55:01Z"},{"alias_kind":"arxiv_version","alias_value":"2107.01825v1","created_at":"2026-07-05T02:55:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.01825","created_at":"2026-07-05T02:55:01Z"},{"alias_kind":"pith_short_12","alias_value":"GWJB2FMEIR5U","created_at":"2026-07-05T02:55:01Z"},{"alias_kind":"pith_short_16","alias_value":"GWJB2FMEIR5UDEOJ","created_at":"2026-07-05T02:55:01Z"},{"alias_kind":"pith_short_8","alias_value":"GWJB2FME","created_at":"2026-07-05T02:55:01Z"}],"graph_snapshots":[{"event_id":"sha256:9b834d531fdeaa9c158ec0e4f4c0f0e7827f5951499d5e18aedd372ca25b05fb","target":"graph","created_at":"2026-07-05T02:55:01Z","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/2107.01825/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Model-based deep reinforcement learning has achieved success in various domains that require high sample efficiencies, such as Go and robotics. However, there are some remaining issues, such as planning efficient explorations to learn more accurate dynamic models, evaluating the uncertainty of the learned models, and more rational utilization of models. To mitigate these issues, we present MEEE, a model-ensemble method that consists of optimistic exploration and weighted exploitation. During exploration, unlike prior methods directly selecting the optimal action that maximizes the expected acc","authors_text":"Dijun Luo, Li Xiao, Wanpeng Zhang, Yao Yao, Zhicheng An","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-07-05T07:18:20Z","title":"Sample Efficient Reinforcement Learning via Model-Ensemble Exploration and Exploitation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.01825","kind":"arxiv","version":1},"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:de27471bcb4ad1a54677712b56f6a8ea297a8800f3a36c45ebabb5bb6a52afba","target":"record","created_at":"2026-07-05T02:55:01Z","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":"24643a7b26eb06aaa57fbf193640b79783445a622ceb7101d617311949b3dc78","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-07-05T07:18:20Z","title_canon_sha256":"bdbb67575ed81d2725f7676d330bc981e4f3435731b6f0f8272c4d9e1f9fa1dd"},"schema_version":"1.0","source":{"id":"2107.01825","kind":"arxiv","version":1}},"canonical_sha256":"35921d1584447b4191c9e264ac6c5ed2c5a814ad7e42a4990d00ba04d2c5fa85","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"35921d1584447b4191c9e264ac6c5ed2c5a814ad7e42a4990d00ba04d2c5fa85","first_computed_at":"2026-07-05T02:55:01.024894Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:55:01.024894Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"25ocCab7UAhtn0SUW3oNkzl84Jk/4uWMuDUmyF7zIlUcne5ALsX/li+CvhF0F2y6AWfMhnN8tJvnRzRsfsYLAg==","signature_status":"signed_v1","signed_at":"2026-07-05T02:55:01.025359Z","signed_message":"canonical_sha256_bytes"},"source_id":"2107.01825","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:de27471bcb4ad1a54677712b56f6a8ea297a8800f3a36c45ebabb5bb6a52afba","sha256:9b834d531fdeaa9c158ec0e4f4c0f0e7827f5951499d5e18aedd372ca25b05fb"],"state_sha256":"a2c410592d0bbcccc0ab087621068f9d26c7d159fcc2e68ada8cbfcafc783dfb"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SkDBPb5fAkn5OGaxRyvL55R/b/nSjyyZ13j/o2cmGY57gid0/Gor991Xr9v36mztHi6OtGwKGrv9/fqHdg0NCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T13:20:31.540665Z","bundle_sha256":"dca6a409a0f56d1a0f97faff288c22b97de70a59273bbffa98d0ad1e5655aaf9"}}