{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:VN2IPSBTDE2DC4Y2MDCR5NZIFT","short_pith_number":"pith:VN2IPSBT","schema_version":"1.0","canonical_sha256":"ab7487c833193431731a60c51eb7282ce1a24f8820b437dc2de06db5b68f2bae","source":{"kind":"arxiv","id":"2404.03578","version":2},"attestation_state":"computed","paper":{"title":"Distributionally Robust Reinforcement Learning with Interactive Data Collection: Fundamental Hardness and Near-Optimal Algorithm","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Han Zhong, Jose Blanchet, Miao Lu, Tong Zhang","submitted_at":"2024-04-04T16:40:22Z","abstract_excerpt":"The sim-to-real gap, which represents the disparity between training and testing environments, poses a significant challenge in reinforcement learning (RL). A promising approach to addressing this challenge is distributionally robust RL, often framed as a robust Markov decision process (RMDP). In this framework, the objective is to find a robust policy that achieves good performance under the worst-case scenario among all environments within a pre-specified uncertainty set centered around the training environment. Unlike previous work, which relies on a generative model or a pre-collected offl"},"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":"2404.03578","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-04-04T16:40:22Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"8cf7bc7233a50272b1f9fed0c12b0132482c0a410e61b0051c0562d09780d917","abstract_canon_sha256":"7bde8ddfe2f4d663d9cbafccf868a9d9f0f1e3250117ef3e5bf97cd85e787a31"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:30:12.154145Z","signature_b64":"+xEeVMRVRsBEMnYCDRFfZWdFomBpe487yyicqBqTlfh3qmvgLKAbM/dYUhGIdVfek6yGVHuMFCXYoR1a2XRbDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ab7487c833193431731a60c51eb7282ce1a24f8820b437dc2de06db5b68f2bae","last_reissued_at":"2026-07-05T09:30:12.153708Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:30:12.153708Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Distributionally Robust Reinforcement Learning with Interactive Data Collection: Fundamental Hardness and Near-Optimal Algorithm","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Han Zhong, Jose Blanchet, Miao Lu, Tong Zhang","submitted_at":"2024-04-04T16:40:22Z","abstract_excerpt":"The sim-to-real gap, which represents the disparity between training and testing environments, poses a significant challenge in reinforcement learning (RL). A promising approach to addressing this challenge is distributionally robust RL, often framed as a robust Markov decision process (RMDP). In this framework, the objective is to find a robust policy that achieves good performance under the worst-case scenario among all environments within a pre-specified uncertainty set centered around the training environment. Unlike previous work, which relies on a generative model or a pre-collected offl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.03578","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/2404.03578/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":"2404.03578","created_at":"2026-07-05T09:30:12.153766+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.03578v2","created_at":"2026-07-05T09:30:12.153766+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.03578","created_at":"2026-07-05T09:30:12.153766+00:00"},{"alias_kind":"pith_short_12","alias_value":"VN2IPSBTDE2D","created_at":"2026-07-05T09:30:12.153766+00:00"},{"alias_kind":"pith_short_16","alias_value":"VN2IPSBTDE2DC4Y2","created_at":"2026-07-05T09:30:12.153766+00:00"},{"alias_kind":"pith_short_8","alias_value":"VN2IPSBT","created_at":"2026-07-05T09:30:12.153766+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2506.12622","citing_title":"DR-SAC: Distributionally Robust Soft Actor-Critic for Reinforcement Learning under Uncertainty","ref_index":28,"is_internal_anchor":true},{"citing_arxiv_id":"2605.03125","citing_title":"Taming the Curses of Multiagency in Robust Markov Games with Large State Space through Linear Function Approximation","ref_index":15,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VN2IPSBTDE2DC4Y2MDCR5NZIFT","json":"https://pith.science/pith/VN2IPSBTDE2DC4Y2MDCR5NZIFT.json","graph_json":"https://pith.science/api/pith-number/VN2IPSBTDE2DC4Y2MDCR5NZIFT/graph.json","events_json":"https://pith.science/api/pith-number/VN2IPSBTDE2DC4Y2MDCR5NZIFT/events.json","paper":"https://pith.science/paper/VN2IPSBT"},"agent_actions":{"view_html":"https://pith.science/pith/VN2IPSBTDE2DC4Y2MDCR5NZIFT","download_json":"https://pith.science/pith/VN2IPSBTDE2DC4Y2MDCR5NZIFT.json","view_paper":"https://pith.science/paper/VN2IPSBT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.03578&json=true","fetch_graph":"https://pith.science/api/pith-number/VN2IPSBTDE2DC4Y2MDCR5NZIFT/graph.json","fetch_events":"https://pith.science/api/pith-number/VN2IPSBTDE2DC4Y2MDCR5NZIFT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VN2IPSBTDE2DC4Y2MDCR5NZIFT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VN2IPSBTDE2DC4Y2MDCR5NZIFT/action/storage_attestation","attest_author":"https://pith.science/pith/VN2IPSBTDE2DC4Y2MDCR5NZIFT/action/author_attestation","sign_citation":"https://pith.science/pith/VN2IPSBTDE2DC4Y2MDCR5NZIFT/action/citation_signature","submit_replication":"https://pith.science/pith/VN2IPSBTDE2DC4Y2MDCR5NZIFT/action/replication_record"}},"created_at":"2026-07-05T09:30:12.153766+00:00","updated_at":"2026-07-05T09:30:12.153766+00:00"}