{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:FPFYB6CHDSFGZA73UELFIGRNZD","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":"f8f4dfb2fd7aa3aaf335488f002dcacd76c568d4d14a7b843243d3e9acecd427","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-14T00:06:54Z","title_canon_sha256":"90b3e900bc861a9ad2deadac69217f04459472d82ef787f7572287f19db46940"},"schema_version":"1.0","source":{"id":"2102.07035","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2102.07035","created_at":"2026-07-05T04:33:49Z"},{"alias_kind":"arxiv_version","alias_value":"2102.07035v2","created_at":"2026-07-05T04:33:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.07035","created_at":"2026-07-05T04:33:49Z"},{"alias_kind":"pith_short_12","alias_value":"FPFYB6CHDSFG","created_at":"2026-07-05T04:33:49Z"},{"alias_kind":"pith_short_16","alias_value":"FPFYB6CHDSFGZA73","created_at":"2026-07-05T04:33:49Z"},{"alias_kind":"pith_short_8","alias_value":"FPFYB6CH","created_at":"2026-07-05T04:33:49Z"}],"graph_snapshots":[{"event_id":"sha256:1641b5b442e1a2b9aed549c5a7b1bb56f771c2d58f3162d62b7ba159a85d6128","target":"graph","created_at":"2026-07-05T04:33:49Z","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/2102.07035/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 ","authors_text":"Aditya Modi, Akshay Krishnamurthy, Alekh Agarwal, Jinglin Chen, Nan Jiang","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-14T00:06:54Z","title":"Model-free Representation Learning and Exploration in Low-rank MDPs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.07035","kind":"arxiv","version":2},"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:d4f62970286777328d2c6f6b161e32d24af4c8a8fbbf54cd31e1366dc2c71efe","target":"record","created_at":"2026-07-05T04:33:49Z","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":"f8f4dfb2fd7aa3aaf335488f002dcacd76c568d4d14a7b843243d3e9acecd427","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-14T00:06:54Z","title_canon_sha256":"90b3e900bc861a9ad2deadac69217f04459472d82ef787f7572287f19db46940"},"schema_version":"1.0","source":{"id":"2102.07035","kind":"arxiv","version":2}},"canonical_sha256":"2bcb80f8471c8a6c83fba116541a2dc8d12ff4b9f9f394b9649d30b55200e028","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2bcb80f8471c8a6c83fba116541a2dc8d12ff4b9f9f394b9649d30b55200e028","first_computed_at":"2026-07-05T04:33:49.960685Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:33:49.960685Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7/EMKtsWRFhjpbJ01HATjL0O6CNib9pfK3A/cY2GI1ZMZ/ncLPMafdw+vnnNOJlGdD8AwkRWWsrBgfZ0B3zOBg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:33:49.961149Z","signed_message":"canonical_sha256_bytes"},"source_id":"2102.07035","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d4f62970286777328d2c6f6b161e32d24af4c8a8fbbf54cd31e1366dc2c71efe","sha256:1641b5b442e1a2b9aed549c5a7b1bb56f771c2d58f3162d62b7ba159a85d6128"],"state_sha256":"d3f5b9f14a2918e459e88716c9c08ef0c121bc186aa0d83cebd2e1406567ae1a"}