{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:DRSOJL5TL5TVNSJEZPZWQ6M3UP","short_pith_number":"pith:DRSOJL5T","canonical_record":{"source":{"id":"2205.11019","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2022-05-23T03:36:24Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"ae106808fd1537cdb075bb44826bb19cbf2732f731a85a03ea8af3ecf49ffc21","abstract_canon_sha256":"e625cd3080bd9fb3eadf93eb772d106b3d3411fee0989efae101c66e89f01d4e"},"schema_version":"1.0"},"canonical_sha256":"1c64e4afb35f6756c924cbf368799ba3fbc7a469280c97b76332794873b64b87","source":{"kind":"arxiv","id":"2205.11019","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.11019","created_at":"2026-07-05T04:25:26Z"},{"alias_kind":"arxiv_version","alias_value":"2205.11019v1","created_at":"2026-07-05T04:25:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.11019","created_at":"2026-07-05T04:25:26Z"},{"alias_kind":"pith_short_12","alias_value":"DRSOJL5TL5TV","created_at":"2026-07-05T04:25:26Z"},{"alias_kind":"pith_short_16","alias_value":"DRSOJL5TL5TVNSJE","created_at":"2026-07-05T04:25:26Z"},{"alias_kind":"pith_short_8","alias_value":"DRSOJL5T","created_at":"2026-07-05T04:25:26Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:DRSOJL5TL5TVNSJEZPZWQ6M3UP","target":"record","payload":{"canonical_record":{"source":{"id":"2205.11019","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2022-05-23T03:36:24Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"ae106808fd1537cdb075bb44826bb19cbf2732f731a85a03ea8af3ecf49ffc21","abstract_canon_sha256":"e625cd3080bd9fb3eadf93eb772d106b3d3411fee0989efae101c66e89f01d4e"},"schema_version":"1.0"},"canonical_sha256":"1c64e4afb35f6756c924cbf368799ba3fbc7a469280c97b76332794873b64b87","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:25:26.384574Z","signature_b64":"L/KWAOOluvQ+7Ak2DtcvOux1Yr6taFCiN3nxFKu2f9goBX2O5FJ7P++MO0IquYM6DquNZVxXHcrK56uN6gKtBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1c64e4afb35f6756c924cbf368799ba3fbc7a469280c97b76332794873b64b87","last_reissued_at":"2026-07-05T04:25:26.384088Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:25:26.384088Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2205.11019","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":"2026-07-05T04:25:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SyFnhQKN+3eKZcKFve2Ujewpgqv4JEyafVqBwqN7AQmnl5k3ChWj30mPE4i70RRXwemO7FUwLVyM48Ssh/U9Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T20:18:47.515512Z"},"content_sha256":"0495b62b12a34c30ad38b84960aab47471905603df47727eae157d6e25aa6f3a","schema_version":"1.0","event_id":"sha256:0495b62b12a34c30ad38b84960aab47471905603df47727eae157d6e25aa6f3a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:DRSOJL5TL5TVNSJEZPZWQ6M3UP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Efficient Reinforcement Learning from Demonstration Using Local Ensemble and Reparameterization with Split and Merge of Expert Policies","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Fang Liu, Yu Wang","submitted_at":"2022-05-23T03:36:24Z","abstract_excerpt":"The current work on reinforcement learning (RL) from demonstrations often assumes the demonstrations are samples from an optimal policy, an unrealistic assumption in practice. When demonstrations are generated by sub-optimal policies or have sparse state-action pairs, policy learned from sub-optimal demonstrations may mislead an agent with incorrect or non-local action decisions. We propose a new method called Local Ensemble and Reparameterization with Split and Merge of expert policies (LEARN-SAM) to improve efficiency and make better use of the sub-optimal demonstrations. First, LEARN-SAM em"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.11019","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/2205.11019/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":"2026-07-05T04:25:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OhGeStjARmKuuMjmK+ZVbXeUUgsb1Rmihww08pk3MM3i7W4EbQRClpRMsrw+2v2NzNWbkuIdmMcl671bB08OAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T20:18:47.516068Z"},"content_sha256":"6a9d454d3f85bb21a19f1c7c7312f2a880d08120ac0a7bd3cf91f1b8dcc2f77d","schema_version":"1.0","event_id":"sha256:6a9d454d3f85bb21a19f1c7c7312f2a880d08120ac0a7bd3cf91f1b8dcc2f77d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DRSOJL5TL5TVNSJEZPZWQ6M3UP/bundle.json","state_url":"https://pith.science/pith/DRSOJL5TL5TVNSJEZPZWQ6M3UP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DRSOJL5TL5TVNSJEZPZWQ6M3UP/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":"2026-08-03T20:18:47Z","links":{"resolver":"https://pith.science/pith/DRSOJL5TL5TVNSJEZPZWQ6M3UP","bundle":"https://pith.science/pith/DRSOJL5TL5TVNSJEZPZWQ6M3UP/bundle.json","state":"https://pith.science/pith/DRSOJL5TL5TVNSJEZPZWQ6M3UP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DRSOJL5TL5TVNSJEZPZWQ6M3UP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:DRSOJL5TL5TVNSJEZPZWQ6M3UP","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":"e625cd3080bd9fb3eadf93eb772d106b3d3411fee0989efae101c66e89f01d4e","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2022-05-23T03:36:24Z","title_canon_sha256":"ae106808fd1537cdb075bb44826bb19cbf2732f731a85a03ea8af3ecf49ffc21"},"schema_version":"1.0","source":{"id":"2205.11019","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.11019","created_at":"2026-07-05T04:25:26Z"},{"alias_kind":"arxiv_version","alias_value":"2205.11019v1","created_at":"2026-07-05T04:25:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.11019","created_at":"2026-07-05T04:25:26Z"},{"alias_kind":"pith_short_12","alias_value":"DRSOJL5TL5TV","created_at":"2026-07-05T04:25:26Z"},{"alias_kind":"pith_short_16","alias_value":"DRSOJL5TL5TVNSJE","created_at":"2026-07-05T04:25:26Z"},{"alias_kind":"pith_short_8","alias_value":"DRSOJL5T","created_at":"2026-07-05T04:25:26Z"}],"graph_snapshots":[{"event_id":"sha256:6a9d454d3f85bb21a19f1c7c7312f2a880d08120ac0a7bd3cf91f1b8dcc2f77d","target":"graph","created_at":"2026-07-05T04:25:26Z","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/2205.11019/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The current work on reinforcement learning (RL) from demonstrations often assumes the demonstrations are samples from an optimal policy, an unrealistic assumption in practice. When demonstrations are generated by sub-optimal policies or have sparse state-action pairs, policy learned from sub-optimal demonstrations may mislead an agent with incorrect or non-local action decisions. We propose a new method called Local Ensemble and Reparameterization with Split and Merge of expert policies (LEARN-SAM) to improve efficiency and make better use of the sub-optimal demonstrations. First, LEARN-SAM em","authors_text":"Fang Liu, Yu Wang","cross_cats":["stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2022-05-23T03:36:24Z","title":"Efficient Reinforcement Learning from Demonstration Using Local Ensemble and Reparameterization with Split and Merge of Expert Policies"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.11019","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":"sha256:0495b62b12a34c30ad38b84960aab47471905603df47727eae157d6e25aa6f3a","target":"record","created_at":"2026-07-05T04:25:26Z","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":"e625cd3080bd9fb3eadf93eb772d106b3d3411fee0989efae101c66e89f01d4e","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2022-05-23T03:36:24Z","title_canon_sha256":"ae106808fd1537cdb075bb44826bb19cbf2732f731a85a03ea8af3ecf49ffc21"},"schema_version":"1.0","source":{"id":"2205.11019","kind":"arxiv","version":1}},"canonical_sha256":"1c64e4afb35f6756c924cbf368799ba3fbc7a469280c97b76332794873b64b87","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1c64e4afb35f6756c924cbf368799ba3fbc7a469280c97b76332794873b64b87","first_computed_at":"2026-07-05T04:25:26.384088Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:25:26.384088Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"L/KWAOOluvQ+7Ak2DtcvOux1Yr6taFCiN3nxFKu2f9goBX2O5FJ7P++MO0IquYM6DquNZVxXHcrK56uN6gKtBw==","signature_status":"signed_v1","signed_at":"2026-07-05T04:25:26.384574Z","signed_message":"canonical_sha256_bytes"},"source_id":"2205.11019","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0495b62b12a34c30ad38b84960aab47471905603df47727eae157d6e25aa6f3a","sha256:6a9d454d3f85bb21a19f1c7c7312f2a880d08120ac0a7bd3cf91f1b8dcc2f77d"],"state_sha256":"01e76ce03f8bf8512518f7751e3503f40acb675fc55459097af54febf33d7176"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pqDAJyC6qG2Abu9YGreASzBp/eEuBKXDcgajqoVUQUh7RLAh7amxl/uxeifWewT6H39GY63F+aqMQwuXxOVsAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T20:18:47.519490Z","bundle_sha256":"22110b9f1405c5d01905b7ced3963a30de9a5e926bedd2a1c3384a86a40b2f2a"}}