{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:LB5HLZ4MCQ3Y32RWEKV5RM246I","short_pith_number":"pith:LB5HLZ4M","canonical_record":{"source":{"id":"2010.07968","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2020-10-15T18:19:35Z","cross_cats_sorted":["cs.LG","cs.RO"],"title_canon_sha256":"dbabbfb230744382eb2ccc4932edc51393e017cf92aeb8fcf8efb7d3e96e739e","abstract_canon_sha256":"87b72166e8981af41d1135727ebbce37745becafd2184e2b91c7ddf111bb4e97"},"schema_version":"1.0"},"canonical_sha256":"587a75e78c14378dea3622abd8b35cf231566cae17b16104adb409344621fbe5","source":{"kind":"arxiv","id":"2010.07968","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2010.07968","created_at":"2026-07-05T02:20:42Z"},{"alias_kind":"arxiv_version","alias_value":"2010.07968v2","created_at":"2026-07-05T02:20:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.07968","created_at":"2026-07-05T02:20:42Z"},{"alias_kind":"pith_short_12","alias_value":"LB5HLZ4MCQ3Y","created_at":"2026-07-05T02:20:42Z"},{"alias_kind":"pith_short_16","alias_value":"LB5HLZ4MCQ3Y32RW","created_at":"2026-07-05T02:20:42Z"},{"alias_kind":"pith_short_8","alias_value":"LB5HLZ4M","created_at":"2026-07-05T02:20:42Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:LB5HLZ4MCQ3Y32RWEKV5RM246I","target":"record","payload":{"canonical_record":{"source":{"id":"2010.07968","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2020-10-15T18:19:35Z","cross_cats_sorted":["cs.LG","cs.RO"],"title_canon_sha256":"dbabbfb230744382eb2ccc4932edc51393e017cf92aeb8fcf8efb7d3e96e739e","abstract_canon_sha256":"87b72166e8981af41d1135727ebbce37745becafd2184e2b91c7ddf111bb4e97"},"schema_version":"1.0"},"canonical_sha256":"587a75e78c14378dea3622abd8b35cf231566cae17b16104adb409344621fbe5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:20:42.377242Z","signature_b64":"D3Ih8c002QosLfHucdvKgjsm8+yWh4sfu8mbqFKciQly71Is4ds4taoKBr+rUjkmvUJLhScnSUkk6WSWd0iVCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"587a75e78c14378dea3622abd8b35cf231566cae17b16104adb409344621fbe5","last_reissued_at":"2026-07-05T02:20:42.376799Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:20:42.376799Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2010.07968","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":"2026-07-05T02:20:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qEyqsvHPVs4lhE+GKeqJIourqho3HnHnOtp0RjHQL6FY8ol3xc65kBOUfbXS4UN1hgzzUW1yy6C3d8pcZvIqCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T01:29:02.286704Z"},"content_sha256":"57f718f1f54391a668317440b6f4d9de6440a71fe04f3371693c1db730cf720a","schema_version":"1.0","event_id":"sha256:57f718f1f54391a668317440b6f4d9de6440a71fe04f3371693c1db730cf720a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:LB5HLZ4MCQ3Y32RWEKV5RM246I","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Constrained Model-based Reinforcement Learning with Robust Cross-Entropy Method","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.RO"],"primary_cat":"cs.AI","authors_text":"Baiming Chen, Ding Zhao, Hongyi Zhou, Martial Hebert, Sicheng Zhong, Zuxin Liu","submitted_at":"2020-10-15T18:19:35Z","abstract_excerpt":"This paper studies the constrained/safe reinforcement learning (RL) problem with sparse indicator signals for constraint violations. We propose a model-based approach to enable RL agents to effectively explore the environment with unknown system dynamics and environment constraints given a significantly small number of violation budgets. We employ the neural network ensemble model to estimate the prediction uncertainty and use model predictive control as the basic control framework. We propose the robust cross-entropy method to optimize the control sequence considering the model uncertainty an"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.07968","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/2010.07968/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":"2026-07-05T02:20:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FRRZknHY2oKfog25hqItwtSr6iimOGLe8jqqnTNaZZ157TlLcTsKVBsJxOUZ7zqOsLlgHhQjUcJ6rdkcIEqhCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T01:29:02.287217Z"},"content_sha256":"d9f6de9352dd8ab170157a58daf442d345f0984cde30d45fac4da4a53a3e976c","schema_version":"1.0","event_id":"sha256:d9f6de9352dd8ab170157a58daf442d345f0984cde30d45fac4da4a53a3e976c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LB5HLZ4MCQ3Y32RWEKV5RM246I/bundle.json","state_url":"https://pith.science/pith/LB5HLZ4MCQ3Y32RWEKV5RM246I/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LB5HLZ4MCQ3Y32RWEKV5RM246I/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":"2026-08-06T01:29:02Z","links":{"resolver":"https://pith.science/pith/LB5HLZ4MCQ3Y32RWEKV5RM246I","bundle":"https://pith.science/pith/LB5HLZ4MCQ3Y32RWEKV5RM246I/bundle.json","state":"https://pith.science/pith/LB5HLZ4MCQ3Y32RWEKV5RM246I/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LB5HLZ4MCQ3Y32RWEKV5RM246I/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:LB5HLZ4MCQ3Y32RWEKV5RM246I","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":"87b72166e8981af41d1135727ebbce37745becafd2184e2b91c7ddf111bb4e97","cross_cats_sorted":["cs.LG","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2020-10-15T18:19:35Z","title_canon_sha256":"dbabbfb230744382eb2ccc4932edc51393e017cf92aeb8fcf8efb7d3e96e739e"},"schema_version":"1.0","source":{"id":"2010.07968","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2010.07968","created_at":"2026-07-05T02:20:42Z"},{"alias_kind":"arxiv_version","alias_value":"2010.07968v2","created_at":"2026-07-05T02:20:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.07968","created_at":"2026-07-05T02:20:42Z"},{"alias_kind":"pith_short_12","alias_value":"LB5HLZ4MCQ3Y","created_at":"2026-07-05T02:20:42Z"},{"alias_kind":"pith_short_16","alias_value":"LB5HLZ4MCQ3Y32RW","created_at":"2026-07-05T02:20:42Z"},{"alias_kind":"pith_short_8","alias_value":"LB5HLZ4M","created_at":"2026-07-05T02:20:42Z"}],"graph_snapshots":[{"event_id":"sha256:d9f6de9352dd8ab170157a58daf442d345f0984cde30d45fac4da4a53a3e976c","target":"graph","created_at":"2026-07-05T02:20:42Z","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/2010.07968/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper studies the constrained/safe reinforcement learning (RL) problem with sparse indicator signals for constraint violations. We propose a model-based approach to enable RL agents to effectively explore the environment with unknown system dynamics and environment constraints given a significantly small number of violation budgets. We employ the neural network ensemble model to estimate the prediction uncertainty and use model predictive control as the basic control framework. We propose the robust cross-entropy method to optimize the control sequence considering the model uncertainty an","authors_text":"Baiming Chen, Ding Zhao, Hongyi Zhou, Martial Hebert, Sicheng Zhong, Zuxin Liu","cross_cats":["cs.LG","cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2020-10-15T18:19:35Z","title":"Constrained Model-based Reinforcement Learning with Robust Cross-Entropy Method"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.07968","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":"sha256:57f718f1f54391a668317440b6f4d9de6440a71fe04f3371693c1db730cf720a","target":"record","created_at":"2026-07-05T02:20:42Z","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":"87b72166e8981af41d1135727ebbce37745becafd2184e2b91c7ddf111bb4e97","cross_cats_sorted":["cs.LG","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2020-10-15T18:19:35Z","title_canon_sha256":"dbabbfb230744382eb2ccc4932edc51393e017cf92aeb8fcf8efb7d3e96e739e"},"schema_version":"1.0","source":{"id":"2010.07968","kind":"arxiv","version":2}},"canonical_sha256":"587a75e78c14378dea3622abd8b35cf231566cae17b16104adb409344621fbe5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"587a75e78c14378dea3622abd8b35cf231566cae17b16104adb409344621fbe5","first_computed_at":"2026-07-05T02:20:42.376799Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:20:42.376799Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"D3Ih8c002QosLfHucdvKgjsm8+yWh4sfu8mbqFKciQly71Is4ds4taoKBr+rUjkmvUJLhScnSUkk6WSWd0iVCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T02:20:42.377242Z","signed_message":"canonical_sha256_bytes"},"source_id":"2010.07968","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:57f718f1f54391a668317440b6f4d9de6440a71fe04f3371693c1db730cf720a","sha256:d9f6de9352dd8ab170157a58daf442d345f0984cde30d45fac4da4a53a3e976c"],"state_sha256":"0e01d6e32ce639c689ccdd305847dc708ddd33191e71bffa0dc955209e342d80"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"N+s0oYX+nNTdzg4WG1O+7jH1z0XW57odxcOhrhaQSQ3yNJtBSFP5w40Mc9uyveKMadd6Pit+s0YqsFfIjXGhAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T01:29:02.291215Z","bundle_sha256":"2216386461bce20e989f6d44697dd5795243e92fb0521cc86088bae5f3cd50df"}}