{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:D4BTDPQZFGVHE6FJCSNHFONBNR","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":"3d0788d6b27592719a112f609a05f88a9c2735f0103f93e0f5a2f1fa89e0356c","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-09-20T03:46:04Z","title_canon_sha256":"4f6e645193b94b8999c6838ba91efeb6aa2876b3050684eac7884f72c16756a4"},"schema_version":"1.0","source":{"id":"2209.09446","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2209.09446","created_at":"2026-07-05T04:59:00Z"},{"alias_kind":"arxiv_version","alias_value":"2209.09446v1","created_at":"2026-07-05T04:59:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.09446","created_at":"2026-07-05T04:59:00Z"},{"alias_kind":"pith_short_12","alias_value":"D4BTDPQZFGVH","created_at":"2026-07-05T04:59:00Z"},{"alias_kind":"pith_short_16","alias_value":"D4BTDPQZFGVHE6FJ","created_at":"2026-07-05T04:59:00Z"},{"alias_kind":"pith_short_8","alias_value":"D4BTDPQZ","created_at":"2026-07-05T04:59:00Z"}],"graph_snapshots":[{"event_id":"sha256:7c689e90d9a83508bb5d96aa10136f4c6a5e0d71380442bcb99801914136bfdb","target":"graph","created_at":"2026-07-05T04:59:00Z","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/2209.09446/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In various control task domains, existing controllers provide a baseline level of performance that -- though possibly suboptimal -- should be maintained. Reinforcement learning (RL) algorithms that rely on extensive exploration of the state and action space can be used to optimize a control policy. However, fully exploratory RL algorithms may decrease performance below a baseline level during training. In this paper, we address the issue of online optimization of a control policy while minimizing regret w.r.t a baseline policy performance. We present a joint imitation-reinforcement learning fr","authors_text":"Guni Sharon, Josiah P. Hanna, Sheelabhadra Dey, Sumedh Pendurkar","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-09-20T03:46:04Z","title":"A Joint Imitation-Reinforcement Learning Framework for Reduced Baseline Regret"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.09446","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":"sha256:5b1acd5b2dade21dbb568c1e14a31ee78efaa4c65f0a5c6d258992050fb2890c","target":"record","created_at":"2026-07-05T04:59:00Z","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":"3d0788d6b27592719a112f609a05f88a9c2735f0103f93e0f5a2f1fa89e0356c","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-09-20T03:46:04Z","title_canon_sha256":"4f6e645193b94b8999c6838ba91efeb6aa2876b3050684eac7884f72c16756a4"},"schema_version":"1.0","source":{"id":"2209.09446","kind":"arxiv","version":1}},"canonical_sha256":"1f0331be1929aa7278a9149a72b9a16c7a77bf5719990519b20bf3c85c44e20c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1f0331be1929aa7278a9149a72b9a16c7a77bf5719990519b20bf3c85c44e20c","first_computed_at":"2026-07-05T04:59:00.088929Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:59:00.088929Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PdtFFSHh7ATkqJNIc1YX/He880NtLrRpb0Y2mfcnsjshawqMsn22+SMS/PkLj1GxwtDGB8K4rC1l2nOgk6M/Aw==","signature_status":"signed_v1","signed_at":"2026-07-05T04:59:00.089291Z","signed_message":"canonical_sha256_bytes"},"source_id":"2209.09446","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5b1acd5b2dade21dbb568c1e14a31ee78efaa4c65f0a5c6d258992050fb2890c","sha256:7c689e90d9a83508bb5d96aa10136f4c6a5e0d71380442bcb99801914136bfdb"],"state_sha256":"82699c33a818d4fea141daf0322cac96f5f301fde22584686104e25139d987ad"}