{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:RZCSRWG26TO6RBVKWLYQLJZNH7","short_pith_number":"pith:RZCSRWG2","canonical_record":{"source":{"id":"2210.01800","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-10-01T17:38:19Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"56a43b53596d0be73f098071c6d152ec8ce38085c3a39b0fd18b3c641b7e4e24","abstract_canon_sha256":"607389779de435982dd7354dbaf7303ec9d402c79809698ed2b7ee3bd44925b1"},"schema_version":"1.0"},"canonical_sha256":"8e4528d8daf4dde886aab2f105a72d3fdc3f2972b7341a98fbb4cebd8c2790f8","source":{"kind":"arxiv","id":"2210.01800","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.01800","created_at":"2026-07-05T05:03:40Z"},{"alias_kind":"arxiv_version","alias_value":"2210.01800v1","created_at":"2026-07-05T05:03:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.01800","created_at":"2026-07-05T05:03:40Z"},{"alias_kind":"pith_short_12","alias_value":"RZCSRWG26TO6","created_at":"2026-07-05T05:03:40Z"},{"alias_kind":"pith_short_16","alias_value":"RZCSRWG26TO6RBVK","created_at":"2026-07-05T05:03:40Z"},{"alias_kind":"pith_short_8","alias_value":"RZCSRWG2","created_at":"2026-07-05T05:03:40Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:RZCSRWG26TO6RBVKWLYQLJZNH7","target":"record","payload":{"canonical_record":{"source":{"id":"2210.01800","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-10-01T17:38:19Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"56a43b53596d0be73f098071c6d152ec8ce38085c3a39b0fd18b3c641b7e4e24","abstract_canon_sha256":"607389779de435982dd7354dbaf7303ec9d402c79809698ed2b7ee3bd44925b1"},"schema_version":"1.0"},"canonical_sha256":"8e4528d8daf4dde886aab2f105a72d3fdc3f2972b7341a98fbb4cebd8c2790f8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:03:40.253872Z","signature_b64":"oI9UT04CIyPtq5DQ0VjJzD/gOduc3BiiUtlmQCrCpf7BEDGHFRUR/BIJTwGvK7RCD5Uh7XisdwJeW+xarkxXDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8e4528d8daf4dde886aab2f105a72d3fdc3f2972b7341a98fbb4cebd8c2790f8","last_reissued_at":"2026-07-05T05:03:40.253404Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:03:40.253404Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2210.01800","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":"2026-07-05T05:03:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"quaDBEF4tbASUNS+wQ6Us4Bf+1LV9+LxostLTjRltC2oklSofjYRj1TWpuiZquqgna9bml/YmVmVSxwxIwPFAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T06:46:30.475025Z"},"content_sha256":"fef5edd871820c5d538fac8e4963f4ac215e8fc96612a0c1fc3998e6bd2ffe90","schema_version":"1.0","event_id":"sha256:fef5edd871820c5d538fac8e4963f4ac215e8fc96612a0c1fc3998e6bd2ffe90"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:RZCSRWG26TO6RBVKWLYQLJZNH7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Bayesian Q-learning With Imperfect Expert Demonstrations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"David Meger, Doina Precup, Fengdi Che, Gregory Dudek, Xiru Zhu","submitted_at":"2022-10-01T17:38:19Z","abstract_excerpt":"Guided exploration with expert demonstrations improves data efficiency for reinforcement learning, but current algorithms often overuse expert information. We propose a novel algorithm to speed up Q-learning with the help of a limited amount of imperfect expert demonstrations. The algorithm avoids excessive reliance on expert data by relaxing the optimal expert assumption and gradually reducing the usage of uninformative expert data. Experimentally, we evaluate our approach on a sparse-reward chain environment and six more complicated Atari games with delayed rewards. With the proposed methods"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.01800","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/2210.01800/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":"2026-07-05T05:03:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BP4F4bSwRFiADfrv1DnJrdtreQ5bssgkmD6uzTm4o2ku7AJczxiVKOnMZqBw5xtQ2yijzK6omYHabM8jN4uFBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T06:46:30.475521Z"},"content_sha256":"4636fe5133dcfd5f0431c1675d62bb3622662800ae4d655a664d2a666ca3a0c0","schema_version":"1.0","event_id":"sha256:4636fe5133dcfd5f0431c1675d62bb3622662800ae4d655a664d2a666ca3a0c0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RZCSRWG26TO6RBVKWLYQLJZNH7/bundle.json","state_url":"https://pith.science/pith/RZCSRWG26TO6RBVKWLYQLJZNH7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RZCSRWG26TO6RBVKWLYQLJZNH7/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":"2026-08-06T06:46:30Z","links":{"resolver":"https://pith.science/pith/RZCSRWG26TO6RBVKWLYQLJZNH7","bundle":"https://pith.science/pith/RZCSRWG26TO6RBVKWLYQLJZNH7/bundle.json","state":"https://pith.science/pith/RZCSRWG26TO6RBVKWLYQLJZNH7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RZCSRWG26TO6RBVKWLYQLJZNH7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:RZCSRWG26TO6RBVKWLYQLJZNH7","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":"607389779de435982dd7354dbaf7303ec9d402c79809698ed2b7ee3bd44925b1","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-10-01T17:38:19Z","title_canon_sha256":"56a43b53596d0be73f098071c6d152ec8ce38085c3a39b0fd18b3c641b7e4e24"},"schema_version":"1.0","source":{"id":"2210.01800","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.01800","created_at":"2026-07-05T05:03:40Z"},{"alias_kind":"arxiv_version","alias_value":"2210.01800v1","created_at":"2026-07-05T05:03:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.01800","created_at":"2026-07-05T05:03:40Z"},{"alias_kind":"pith_short_12","alias_value":"RZCSRWG26TO6","created_at":"2026-07-05T05:03:40Z"},{"alias_kind":"pith_short_16","alias_value":"RZCSRWG26TO6RBVK","created_at":"2026-07-05T05:03:40Z"},{"alias_kind":"pith_short_8","alias_value":"RZCSRWG2","created_at":"2026-07-05T05:03:40Z"}],"graph_snapshots":[{"event_id":"sha256:4636fe5133dcfd5f0431c1675d62bb3622662800ae4d655a664d2a666ca3a0c0","target":"graph","created_at":"2026-07-05T05:03:40Z","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/2210.01800/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Guided exploration with expert demonstrations improves data efficiency for reinforcement learning, but current algorithms often overuse expert information. We propose a novel algorithm to speed up Q-learning with the help of a limited amount of imperfect expert demonstrations. The algorithm avoids excessive reliance on expert data by relaxing the optimal expert assumption and gradually reducing the usage of uninformative expert data. Experimentally, we evaluate our approach on a sparse-reward chain environment and six more complicated Atari games with delayed rewards. With the proposed methods","authors_text":"David Meger, Doina Precup, Fengdi Che, Gregory Dudek, Xiru Zhu","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-10-01T17:38:19Z","title":"Bayesian Q-learning With Imperfect Expert Demonstrations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.01800","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:fef5edd871820c5d538fac8e4963f4ac215e8fc96612a0c1fc3998e6bd2ffe90","target":"record","created_at":"2026-07-05T05:03:40Z","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":"607389779de435982dd7354dbaf7303ec9d402c79809698ed2b7ee3bd44925b1","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-10-01T17:38:19Z","title_canon_sha256":"56a43b53596d0be73f098071c6d152ec8ce38085c3a39b0fd18b3c641b7e4e24"},"schema_version":"1.0","source":{"id":"2210.01800","kind":"arxiv","version":1}},"canonical_sha256":"8e4528d8daf4dde886aab2f105a72d3fdc3f2972b7341a98fbb4cebd8c2790f8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8e4528d8daf4dde886aab2f105a72d3fdc3f2972b7341a98fbb4cebd8c2790f8","first_computed_at":"2026-07-05T05:03:40.253404Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:03:40.253404Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"oI9UT04CIyPtq5DQ0VjJzD/gOduc3BiiUtlmQCrCpf7BEDGHFRUR/BIJTwGvK7RCD5Uh7XisdwJeW+xarkxXDA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:03:40.253872Z","signed_message":"canonical_sha256_bytes"},"source_id":"2210.01800","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fef5edd871820c5d538fac8e4963f4ac215e8fc96612a0c1fc3998e6bd2ffe90","sha256:4636fe5133dcfd5f0431c1675d62bb3622662800ae4d655a664d2a666ca3a0c0"],"state_sha256":"a750ba9eada50eb5722f6197296c69bbe928cfa3afeaf7d8b97cdb173a76a22d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qNRdTBzz8brBgI93eoMIUC8tYXQMyp5uewgIbTpNuUti9t+9lme35kHHU3cpO/MC9TEDLQTXG5lLcYicD2jsAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T06:46:30.479051Z","bundle_sha256":"937bcd92a0f53dc32633f652cd4e015d138419726500b02ef9edd315c4a303bc"}}