{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:RRCJ2VPYCTMBOCQ65IAJUVAJ43","short_pith_number":"pith:RRCJ2VPY","canonical_record":{"source":{"id":"2006.13165","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-23T17:08:54Z","cross_cats_sorted":["cs.AI","math.OC","stat.ML"],"title_canon_sha256":"adbada39412da2441912cf2db962b72a3d93152e6ca65e0821aa3cadba82dd49","abstract_canon_sha256":"4bb6986e9f0ef21e9af18c4efffc411ba3a4f9ab596fb44c31a7a35b828364e4"},"schema_version":"1.0"},"canonical_sha256":"8c449d55f814d8170a1eea009a5409e6f91754d0c657e85b4a699971879f8e3c","source":{"kind":"arxiv","id":"2006.13165","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.13165","created_at":"2026-07-05T02:17:08Z"},{"alias_kind":"arxiv_version","alias_value":"2006.13165v4","created_at":"2026-07-05T02:17:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.13165","created_at":"2026-07-05T02:17:08Z"},{"alias_kind":"pith_short_12","alias_value":"RRCJ2VPYCTMB","created_at":"2026-07-05T02:17:08Z"},{"alias_kind":"pith_short_16","alias_value":"RRCJ2VPYCTMBOCQ6","created_at":"2026-07-05T02:17:08Z"},{"alias_kind":"pith_short_8","alias_value":"RRCJ2VPY","created_at":"2026-07-05T02:17:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:RRCJ2VPYCTMBOCQ65IAJUVAJ43","target":"record","payload":{"canonical_record":{"source":{"id":"2006.13165","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-23T17:08:54Z","cross_cats_sorted":["cs.AI","math.OC","stat.ML"],"title_canon_sha256":"adbada39412da2441912cf2db962b72a3d93152e6ca65e0821aa3cadba82dd49","abstract_canon_sha256":"4bb6986e9f0ef21e9af18c4efffc411ba3a4f9ab596fb44c31a7a35b828364e4"},"schema_version":"1.0"},"canonical_sha256":"8c449d55f814d8170a1eea009a5409e6f91754d0c657e85b4a699971879f8e3c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:17:08.480674Z","signature_b64":"oMKeC/OKk0oHQjkYrToMtcEYU02mhdxKe8JkTZ4G3lHHlBDJNNJpNsGGf08vsae+Rlc33rUzxNhevBgzUspcAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8c449d55f814d8170a1eea009a5409e6f91754d0c657e85b4a699971879f8e3c","last_reissued_at":"2026-07-05T02:17:08.480234Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:17:08.480234Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2006.13165","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:17:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4fBtj3YyUG87L5WJLAiH9tfW4dcptotxzZWW4UfaKBpENVp7omjzh+0bXCx8+fW15vRulgB2JnCVuSoxZmXlAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T07:25:34.738018Z"},"content_sha256":"2bf1b2fdaeaee5f55106602090353c35aff23f5b25f9a521f669c67ed1f079f6","schema_version":"1.0","event_id":"sha256:2bf1b2fdaeaee5f55106602090353c35aff23f5b25f9a521f669c67ed1f079f6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:RRCJ2VPYCTMBOCQ65IAJUVAJ43","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Provably Efficient Reinforcement Learning for Discounted MDPs with Feature Mapping","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Dongruo Zhou, Jiafan He, Quanquan Gu","submitted_at":"2020-06-23T17:08:54Z","abstract_excerpt":"Modern tasks in reinforcement learning have large state and action spaces. To deal with them efficiently, one often uses predefined feature mapping to represent states and actions in a low-dimensional space. In this paper, we study reinforcement learning for discounted Markov Decision Processes (MDPs), where the transition kernel can be parameterized as a linear function of certain feature mapping. We propose a novel algorithm that makes use of the feature mapping and obtains a $\\tilde O(d\\sqrt{T}/(1-\\gamma)^2)$ regret, where $d$ is the dimension of the feature space, $T$ is the time horizon a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.13165","kind":"arxiv","version":4},"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/2006.13165/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:17:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cYAL/Ci83Fzkrbmv9gB/z9irQVNr6o9OfbadD0HvpfTdmZyBGHvGZ4yLgt61Jx8Tvr3FjmeL2QlnzWYMwduHBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T07:25:34.738419Z"},"content_sha256":"1c57ebe6cabdc8f98118d3d6afab38ef2ac5fa6ad1c7802c1e2030262de88b3f","schema_version":"1.0","event_id":"sha256:1c57ebe6cabdc8f98118d3d6afab38ef2ac5fa6ad1c7802c1e2030262de88b3f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RRCJ2VPYCTMBOCQ65IAJUVAJ43/bundle.json","state_url":"https://pith.science/pith/RRCJ2VPYCTMBOCQ65IAJUVAJ43/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RRCJ2VPYCTMBOCQ65IAJUVAJ43/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-07T07:25:34Z","links":{"resolver":"https://pith.science/pith/RRCJ2VPYCTMBOCQ65IAJUVAJ43","bundle":"https://pith.science/pith/RRCJ2VPYCTMBOCQ65IAJUVAJ43/bundle.json","state":"https://pith.science/pith/RRCJ2VPYCTMBOCQ65IAJUVAJ43/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RRCJ2VPYCTMBOCQ65IAJUVAJ43/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:RRCJ2VPYCTMBOCQ65IAJUVAJ43","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":"4bb6986e9f0ef21e9af18c4efffc411ba3a4f9ab596fb44c31a7a35b828364e4","cross_cats_sorted":["cs.AI","math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-23T17:08:54Z","title_canon_sha256":"adbada39412da2441912cf2db962b72a3d93152e6ca65e0821aa3cadba82dd49"},"schema_version":"1.0","source":{"id":"2006.13165","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.13165","created_at":"2026-07-05T02:17:08Z"},{"alias_kind":"arxiv_version","alias_value":"2006.13165v4","created_at":"2026-07-05T02:17:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.13165","created_at":"2026-07-05T02:17:08Z"},{"alias_kind":"pith_short_12","alias_value":"RRCJ2VPYCTMB","created_at":"2026-07-05T02:17:08Z"},{"alias_kind":"pith_short_16","alias_value":"RRCJ2VPYCTMBOCQ6","created_at":"2026-07-05T02:17:08Z"},{"alias_kind":"pith_short_8","alias_value":"RRCJ2VPY","created_at":"2026-07-05T02:17:08Z"}],"graph_snapshots":[{"event_id":"sha256:1c57ebe6cabdc8f98118d3d6afab38ef2ac5fa6ad1c7802c1e2030262de88b3f","target":"graph","created_at":"2026-07-05T02:17:08Z","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/2006.13165/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Modern tasks in reinforcement learning have large state and action spaces. To deal with them efficiently, one often uses predefined feature mapping to represent states and actions in a low-dimensional space. In this paper, we study reinforcement learning for discounted Markov Decision Processes (MDPs), where the transition kernel can be parameterized as a linear function of certain feature mapping. We propose a novel algorithm that makes use of the feature mapping and obtains a $\\tilde O(d\\sqrt{T}/(1-\\gamma)^2)$ regret, where $d$ is the dimension of the feature space, $T$ is the time horizon a","authors_text":"Dongruo Zhou, Jiafan He, Quanquan Gu","cross_cats":["cs.AI","math.OC","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-23T17:08:54Z","title":"Provably Efficient Reinforcement Learning for Discounted MDPs with Feature Mapping"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.13165","kind":"arxiv","version":4},"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":"sha256:2bf1b2fdaeaee5f55106602090353c35aff23f5b25f9a521f669c67ed1f079f6","target":"record","created_at":"2026-07-05T02:17:08Z","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":"4bb6986e9f0ef21e9af18c4efffc411ba3a4f9ab596fb44c31a7a35b828364e4","cross_cats_sorted":["cs.AI","math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-23T17:08:54Z","title_canon_sha256":"adbada39412da2441912cf2db962b72a3d93152e6ca65e0821aa3cadba82dd49"},"schema_version":"1.0","source":{"id":"2006.13165","kind":"arxiv","version":4}},"canonical_sha256":"8c449d55f814d8170a1eea009a5409e6f91754d0c657e85b4a699971879f8e3c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8c449d55f814d8170a1eea009a5409e6f91754d0c657e85b4a699971879f8e3c","first_computed_at":"2026-07-05T02:17:08.480234Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:17:08.480234Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"oMKeC/OKk0oHQjkYrToMtcEYU02mhdxKe8JkTZ4G3lHHlBDJNNJpNsGGf08vsae+Rlc33rUzxNhevBgzUspcAg==","signature_status":"signed_v1","signed_at":"2026-07-05T02:17:08.480674Z","signed_message":"canonical_sha256_bytes"},"source_id":"2006.13165","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2bf1b2fdaeaee5f55106602090353c35aff23f5b25f9a521f669c67ed1f079f6","sha256:1c57ebe6cabdc8f98118d3d6afab38ef2ac5fa6ad1c7802c1e2030262de88b3f"],"state_sha256":"24fa104d23110aef056d55ee28f8040ff0b92266afdcf3e8f17f33f5c77e4fc2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mD8Flui/kOM6B145kMa/NxZiynP4XnA5S9MinkyAzeyNFJ9SQOFxW53pDKuO1JDlhjueTLR3dkUE5dUCC0AVDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T07:25:34.740719Z","bundle_sha256":"5c91d857938c4af5390c8af73ee4c4d57d9dcdaa1940b68c982e559c623043bf"}}