{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:5P2NUIIRZ7XDZ7V6WS3JRM2IVK","short_pith_number":"pith:5P2NUIIR","schema_version":"1.0","canonical_sha256":"ebf4da2111cfee3cfebeb4b698b348aa894644907e43f1b5f36550c9dbd64cce","source":{"kind":"arxiv","id":"2404.16399","version":2},"attestation_state":"computed","paper":{"title":"Offline Reinforcement Learning with Behavioral Supervisor Tuning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Padmanaba Srinivasan, William Knottenbelt","submitted_at":"2024-04-25T08:22:47Z","abstract_excerpt":"Offline reinforcement learning (RL) algorithms are applied to learn performant, well-generalizing policies when provided with a static dataset of interactions. Many recent approaches to offline RL have seen substantial success, but with one key caveat: they demand substantial per-dataset hyperparameter tuning to achieve reported performance, which requires policy rollouts in the environment to evaluate; this can rapidly become cumbersome. Furthermore, substantial tuning requirements can hamper the adoption of these algorithms in practical domains. In this paper, we present TD3 with Behavioral "},"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":"2404.16399","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-04-25T08:22:47Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"263f15a727a5900ae7d078777abe75f74ec4e31b2dd39a3feb4c751533c5eca0","abstract_canon_sha256":"13d2e0b27982a9d787f72d9349bead2af39205fb36d378d307106a48654f3a3e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:49:09.963806Z","signature_b64":"QgrBB/c0f4ynlBFeIxhNd+KvRZ1N8hS9DZTZlACYKn9HMDg8b9rVws0VVwDS8pJrmQeRQFBk/AWF46tWs+2mDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ebf4da2111cfee3cfebeb4b698b348aa894644907e43f1b5f36550c9dbd64cce","last_reissued_at":"2026-07-05T08:49:09.963327Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:49:09.963327Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Offline Reinforcement Learning with Behavioral Supervisor Tuning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Padmanaba Srinivasan, William Knottenbelt","submitted_at":"2024-04-25T08:22:47Z","abstract_excerpt":"Offline reinforcement learning (RL) algorithms are applied to learn performant, well-generalizing policies when provided with a static dataset of interactions. Many recent approaches to offline RL have seen substantial success, but with one key caveat: they demand substantial per-dataset hyperparameter tuning to achieve reported performance, which requires policy rollouts in the environment to evaluate; this can rapidly become cumbersome. Furthermore, substantial tuning requirements can hamper the adoption of these algorithms in practical domains. In this paper, we present TD3 with Behavioral "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.16399","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/2404.16399/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":"2404.16399","created_at":"2026-07-05T08:49:09.963392+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.16399v2","created_at":"2026-07-05T08:49:09.963392+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.16399","created_at":"2026-07-05T08:49:09.963392+00:00"},{"alias_kind":"pith_short_12","alias_value":"5P2NUIIRZ7XD","created_at":"2026-07-05T08:49:09.963392+00:00"},{"alias_kind":"pith_short_16","alias_value":"5P2NUIIRZ7XDZ7V6","created_at":"2026-07-05T08:49:09.963392+00:00"},{"alias_kind":"pith_short_8","alias_value":"5P2NUIIR","created_at":"2026-07-05T08:49:09.963392+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5P2NUIIRZ7XDZ7V6WS3JRM2IVK","json":"https://pith.science/pith/5P2NUIIRZ7XDZ7V6WS3JRM2IVK.json","graph_json":"https://pith.science/api/pith-number/5P2NUIIRZ7XDZ7V6WS3JRM2IVK/graph.json","events_json":"https://pith.science/api/pith-number/5P2NUIIRZ7XDZ7V6WS3JRM2IVK/events.json","paper":"https://pith.science/paper/5P2NUIIR"},"agent_actions":{"view_html":"https://pith.science/pith/5P2NUIIRZ7XDZ7V6WS3JRM2IVK","download_json":"https://pith.science/pith/5P2NUIIRZ7XDZ7V6WS3JRM2IVK.json","view_paper":"https://pith.science/paper/5P2NUIIR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.16399&json=true","fetch_graph":"https://pith.science/api/pith-number/5P2NUIIRZ7XDZ7V6WS3JRM2IVK/graph.json","fetch_events":"https://pith.science/api/pith-number/5P2NUIIRZ7XDZ7V6WS3JRM2IVK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5P2NUIIRZ7XDZ7V6WS3JRM2IVK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5P2NUIIRZ7XDZ7V6WS3JRM2IVK/action/storage_attestation","attest_author":"https://pith.science/pith/5P2NUIIRZ7XDZ7V6WS3JRM2IVK/action/author_attestation","sign_citation":"https://pith.science/pith/5P2NUIIRZ7XDZ7V6WS3JRM2IVK/action/citation_signature","submit_replication":"https://pith.science/pith/5P2NUIIRZ7XDZ7V6WS3JRM2IVK/action/replication_record"}},"created_at":"2026-07-05T08:49:09.963392+00:00","updated_at":"2026-07-05T08:49:09.963392+00:00"}