{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:FPFYB6CHDSFGZA73UELFIGRNZD","short_pith_number":"pith:FPFYB6CH","schema_version":"1.0","canonical_sha256":"2bcb80f8471c8a6c83fba116541a2dc8d12ff4b9f9f394b9649d30b55200e028","source":{"kind":"arxiv","id":"2102.07035","version":2},"attestation_state":"computed","paper":{"title":"Model-free Representation Learning and Exploration in Low-rank MDPs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Aditya Modi, Akshay Krishnamurthy, Alekh Agarwal, Jinglin Chen, Nan Jiang","submitted_at":"2021-02-14T00:06:54Z","abstract_excerpt":"The low rank MDP has emerged as an important model for studying representation learning and exploration in reinforcement learning. With a known representation, several model-free exploration strategies exist. In contrast, all algorithms for the unknown representation setting are model-based, thereby requiring the ability to model the full dynamics. In this work, we present the first model-free representation learning algorithms for low rank MDPs. The key algorithmic contribution is a new minimax representation learning objective, for which we provide variants with differing tradeoffs in their "},"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":"2102.07035","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-14T00:06:54Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"90b3e900bc861a9ad2deadac69217f04459472d82ef787f7572287f19db46940","abstract_canon_sha256":"f8f4dfb2fd7aa3aaf335488f002dcacd76c568d4d14a7b843243d3e9acecd427"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:33:49.961149Z","signature_b64":"7/EMKtsWRFhjpbJ01HATjL0O6CNib9pfK3A/cY2GI1ZMZ/ncLPMafdw+vnnNOJlGdD8AwkRWWsrBgfZ0B3zOBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2bcb80f8471c8a6c83fba116541a2dc8d12ff4b9f9f394b9649d30b55200e028","last_reissued_at":"2026-07-05T04:33:49.960685Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:33:49.960685Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Model-free Representation Learning and Exploration in Low-rank MDPs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Aditya Modi, Akshay Krishnamurthy, Alekh Agarwal, Jinglin Chen, Nan Jiang","submitted_at":"2021-02-14T00:06:54Z","abstract_excerpt":"The low rank MDP has emerged as an important model for studying representation learning and exploration in reinforcement learning. With a known representation, several model-free exploration strategies exist. In contrast, all algorithms for the unknown representation setting are model-based, thereby requiring the ability to model the full dynamics. In this work, we present the first model-free representation learning algorithms for low rank MDPs. The key algorithmic contribution is a new minimax representation learning objective, for which we provide variants with differing tradeoffs in their "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.07035","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/2102.07035/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":"2102.07035","created_at":"2026-07-05T04:33:49.960743+00:00"},{"alias_kind":"arxiv_version","alias_value":"2102.07035v2","created_at":"2026-07-05T04:33:49.960743+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.07035","created_at":"2026-07-05T04:33:49.960743+00:00"},{"alias_kind":"pith_short_12","alias_value":"FPFYB6CHDSFG","created_at":"2026-07-05T04:33:49.960743+00:00"},{"alias_kind":"pith_short_16","alias_value":"FPFYB6CHDSFGZA73","created_at":"2026-07-05T04:33:49.960743+00:00"},{"alias_kind":"pith_short_8","alias_value":"FPFYB6CH","created_at":"2026-07-05T04:33:49.960743+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.01242","citing_title":"Breaking the Computational Barrier: Provably Efficient Actor-Critic for Low-Rank MDPs","ref_index":40,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FPFYB6CHDSFGZA73UELFIGRNZD","json":"https://pith.science/pith/FPFYB6CHDSFGZA73UELFIGRNZD.json","graph_json":"https://pith.science/api/pith-number/FPFYB6CHDSFGZA73UELFIGRNZD/graph.json","events_json":"https://pith.science/api/pith-number/FPFYB6CHDSFGZA73UELFIGRNZD/events.json","paper":"https://pith.science/paper/FPFYB6CH"},"agent_actions":{"view_html":"https://pith.science/pith/FPFYB6CHDSFGZA73UELFIGRNZD","download_json":"https://pith.science/pith/FPFYB6CHDSFGZA73UELFIGRNZD.json","view_paper":"https://pith.science/paper/FPFYB6CH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2102.07035&json=true","fetch_graph":"https://pith.science/api/pith-number/FPFYB6CHDSFGZA73UELFIGRNZD/graph.json","fetch_events":"https://pith.science/api/pith-number/FPFYB6CHDSFGZA73UELFIGRNZD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FPFYB6CHDSFGZA73UELFIGRNZD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FPFYB6CHDSFGZA73UELFIGRNZD/action/storage_attestation","attest_author":"https://pith.science/pith/FPFYB6CHDSFGZA73UELFIGRNZD/action/author_attestation","sign_citation":"https://pith.science/pith/FPFYB6CHDSFGZA73UELFIGRNZD/action/citation_signature","submit_replication":"https://pith.science/pith/FPFYB6CHDSFGZA73UELFIGRNZD/action/replication_record"}},"created_at":"2026-07-05T04:33:49.960743+00:00","updated_at":"2026-07-05T04:33:49.960743+00:00"}