{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:CQQASSKLIKG4LZFHGZUTP753NA","short_pith_number":"pith:CQQASSKL","schema_version":"1.0","canonical_sha256":"142009494b428dc5e4a7366937ffbb681bcb924ab8732feef22778db5701d635","source":{"kind":"arxiv","id":"2403.19462","version":1},"attestation_state":"computed","paper":{"title":"Offline Imitation Learning from Multiple Baselines with Applications to Compiler Optimization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.PL"],"primary_cat":"cs.LG","authors_text":"Alekh Agarwal, Mircea Trofin, Teodor V. Marinov","submitted_at":"2024-03-28T14:34:02Z","abstract_excerpt":"This work studies a Reinforcement Learning (RL) problem in which we are given a set of trajectories collected with K baseline policies. Each of these policies can be quite suboptimal in isolation, and have strong performance in complementary parts of the state space. The goal is to learn a policy which performs as well as the best combination of baselines on the entire state space. We propose a simple imitation learning based algorithm, show a sample complexity bound on its accuracy and prove that the the algorithm is minimax optimal by showing a matching lower bound. Further, we apply the alg"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2403.19462","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-03-28T14:34:02Z","cross_cats_sorted":["cs.PL"],"title_canon_sha256":"bb78a8268be84c0887da3c089047e9ee7733ad9be2e58a02bb151ff421aedaa2","abstract_canon_sha256":"1ca6a5b01b2f2ddb3052ac10a6627b8b2ed898d63c614c2d79c0c318a8119cd8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:01:49.238848Z","signature_b64":"N/eHFdoRMKStLa9jR1TqMQIEPw3NdPRJxWXNm+iFc4DP9+79JJOTs79kGnkvYGt+/HraG6nUWEACd8dhr9/XAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"142009494b428dc5e4a7366937ffbb681bcb924ab8732feef22778db5701d635","last_reissued_at":"2026-07-05T08:01:49.238374Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:01:49.238374Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Offline Imitation Learning from Multiple Baselines with Applications to Compiler Optimization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.PL"],"primary_cat":"cs.LG","authors_text":"Alekh Agarwal, Mircea Trofin, Teodor V. Marinov","submitted_at":"2024-03-28T14:34:02Z","abstract_excerpt":"This work studies a Reinforcement Learning (RL) problem in which we are given a set of trajectories collected with K baseline policies. Each of these policies can be quite suboptimal in isolation, and have strong performance in complementary parts of the state space. The goal is to learn a policy which performs as well as the best combination of baselines on the entire state space. We propose a simple imitation learning based algorithm, show a sample complexity bound on its accuracy and prove that the the algorithm is minimax optimal by showing a matching lower bound. Further, we apply the alg"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.19462","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/2403.19462/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2403.19462","created_at":"2026-07-05T08:01:49.238433+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.19462v1","created_at":"2026-07-05T08:01:49.238433+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.19462","created_at":"2026-07-05T08:01:49.238433+00:00"},{"alias_kind":"pith_short_12","alias_value":"CQQASSKLIKG4","created_at":"2026-07-05T08:01:49.238433+00:00"},{"alias_kind":"pith_short_16","alias_value":"CQQASSKLIKG4LZFH","created_at":"2026-07-05T08:01:49.238433+00:00"},{"alias_kind":"pith_short_8","alias_value":"CQQASSKL","created_at":"2026-07-05T08:01:49.238433+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.12960","citing_title":"A Deep RL based Framework for Targeted White Matter Tractography","ref_index":73,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CQQASSKLIKG4LZFHGZUTP753NA","json":"https://pith.science/pith/CQQASSKLIKG4LZFHGZUTP753NA.json","graph_json":"https://pith.science/api/pith-number/CQQASSKLIKG4LZFHGZUTP753NA/graph.json","events_json":"https://pith.science/api/pith-number/CQQASSKLIKG4LZFHGZUTP753NA/events.json","paper":"https://pith.science/paper/CQQASSKL"},"agent_actions":{"view_html":"https://pith.science/pith/CQQASSKLIKG4LZFHGZUTP753NA","download_json":"https://pith.science/pith/CQQASSKLIKG4LZFHGZUTP753NA.json","view_paper":"https://pith.science/paper/CQQASSKL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.19462&json=true","fetch_graph":"https://pith.science/api/pith-number/CQQASSKLIKG4LZFHGZUTP753NA/graph.json","fetch_events":"https://pith.science/api/pith-number/CQQASSKLIKG4LZFHGZUTP753NA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CQQASSKLIKG4LZFHGZUTP753NA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CQQASSKLIKG4LZFHGZUTP753NA/action/storage_attestation","attest_author":"https://pith.science/pith/CQQASSKLIKG4LZFHGZUTP753NA/action/author_attestation","sign_citation":"https://pith.science/pith/CQQASSKLIKG4LZFHGZUTP753NA/action/citation_signature","submit_replication":"https://pith.science/pith/CQQASSKLIKG4LZFHGZUTP753NA/action/replication_record"}},"created_at":"2026-07-05T08:01:49.238433+00:00","updated_at":"2026-07-05T08:01:49.238433+00:00"}