{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:PN6GBG72AFX6FMKCEWBESAFK7O","short_pith_number":"pith:PN6GBG72","canonical_record":{"source":{"id":"1905.10389","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-24T18:02:39Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"6e6e9a7d744f6bbe52bb2937c1f0d02b33cc9894aa71753fc818f6e0d83ca3b5","abstract_canon_sha256":"6ed6bbd56405a7e33e310813eca364d6a5e9a4508e685e2026b85fec22029ee9"},"schema_version":"1.0"},"canonical_sha256":"7b7c609bfa016fe2b14225824900aafb92392c178f26c68e318dbcab2d090e4f","source":{"kind":"arxiv","id":"1905.10389","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.10389","created_at":"2026-05-17T23:43:27Z"},{"alias_kind":"arxiv_version","alias_value":"1905.10389v2","created_at":"2026-05-17T23:43:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.10389","created_at":"2026-05-17T23:43:27Z"},{"alias_kind":"pith_short_12","alias_value":"PN6GBG72AFX6","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_16","alias_value":"PN6GBG72AFX6FMKC","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_8","alias_value":"PN6GBG72","created_at":"2026-05-18T12:33:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:PN6GBG72AFX6FMKCEWBESAFK7O","target":"record","payload":{"canonical_record":{"source":{"id":"1905.10389","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-24T18:02:39Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"6e6e9a7d744f6bbe52bb2937c1f0d02b33cc9894aa71753fc818f6e0d83ca3b5","abstract_canon_sha256":"6ed6bbd56405a7e33e310813eca364d6a5e9a4508e685e2026b85fec22029ee9"},"schema_version":"1.0"},"canonical_sha256":"7b7c609bfa016fe2b14225824900aafb92392c178f26c68e318dbcab2d090e4f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:43:27.586223Z","signature_b64":"CrW3u9n1kfKPK6Z1MFwHvd3V13vJGUAu4ycJ21u7CgUYq53b0p7VxzrbPBmWQFhwD4yevFSO1Jlc3ql0Ia15DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7b7c609bfa016fe2b14225824900aafb92392c178f26c68e318dbcab2d090e4f","last_reissued_at":"2026-05-17T23:43:27.585808Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:43:27.585808Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1905.10389","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:43:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"v30fOfcrQvkTzg+4Ehp8KEy94TTQZ9YWaL+QwXLbQ/M1JXa2bZWnAwSeED0zEP7l4WYg8pjk8nwmdyM0K9FoAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T00:15:13.296564Z"},"content_sha256":"52a29453015bf52559d10f0a34c200e030d548b7d0554b19cdceaf4317850060","schema_version":"1.0","event_id":"sha256:52a29453015bf52559d10f0a34c200e030d548b7d0554b19cdceaf4317850060"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:PN6GBG72AFX6FMKCEWBESAFK7O","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Reinforcement Learning in Feature Space: Matrix Bandit, Kernels, and Regret Bound","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Lin F. Yang, Mengdi Wang","submitted_at":"2019-05-24T18:02:39Z","abstract_excerpt":"Exploration in reinforcement learning (RL) suffers from the curse of dimensionality when the state-action space is large. A common practice is to parameterize the high-dimensional value and policy functions using given features. However existing methods either have no theoretical guarantee or suffer a regret that is exponential in the planning horizon $H$. In this paper, we propose an online RL algorithm, namely the MatrixRL, that leverages ideas from linear bandit to learn a low-dimensional representation of the probability transition model while carefully balancing the exploitation-explorati"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.10389","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":""},"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":"2026-05-17T23:43:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"o3ArNjFGZJn58HWGCErT8wxsXGjYH8WNOlRygKBJygXIlSHadVYeed5xXGm73IBKjr8XLSkNgSbcIiAW9JaFDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T00:15:13.297250Z"},"content_sha256":"1f62d3b95209d05c61e517d73f864d01da170e7ad8e0f1c884bc7a00020b1b10","schema_version":"1.0","event_id":"sha256:1f62d3b95209d05c61e517d73f864d01da170e7ad8e0f1c884bc7a00020b1b10"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PN6GBG72AFX6FMKCEWBESAFK7O/bundle.json","state_url":"https://pith.science/pith/PN6GBG72AFX6FMKCEWBESAFK7O/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PN6GBG72AFX6FMKCEWBESAFK7O/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":"2026-05-31T00:15:13Z","links":{"resolver":"https://pith.science/pith/PN6GBG72AFX6FMKCEWBESAFK7O","bundle":"https://pith.science/pith/PN6GBG72AFX6FMKCEWBESAFK7O/bundle.json","state":"https://pith.science/pith/PN6GBG72AFX6FMKCEWBESAFK7O/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PN6GBG72AFX6FMKCEWBESAFK7O/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:PN6GBG72AFX6FMKCEWBESAFK7O","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":"6ed6bbd56405a7e33e310813eca364d6a5e9a4508e685e2026b85fec22029ee9","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-24T18:02:39Z","title_canon_sha256":"6e6e9a7d744f6bbe52bb2937c1f0d02b33cc9894aa71753fc818f6e0d83ca3b5"},"schema_version":"1.0","source":{"id":"1905.10389","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.10389","created_at":"2026-05-17T23:43:27Z"},{"alias_kind":"arxiv_version","alias_value":"1905.10389v2","created_at":"2026-05-17T23:43:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.10389","created_at":"2026-05-17T23:43:27Z"},{"alias_kind":"pith_short_12","alias_value":"PN6GBG72AFX6","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_16","alias_value":"PN6GBG72AFX6FMKC","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_8","alias_value":"PN6GBG72","created_at":"2026-05-18T12:33:24Z"}],"graph_snapshots":[{"event_id":"sha256:1f62d3b95209d05c61e517d73f864d01da170e7ad8e0f1c884bc7a00020b1b10","target":"graph","created_at":"2026-05-17T23:43:27Z","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"},"paper":{"abstract_excerpt":"Exploration in reinforcement learning (RL) suffers from the curse of dimensionality when the state-action space is large. A common practice is to parameterize the high-dimensional value and policy functions using given features. However existing methods either have no theoretical guarantee or suffer a regret that is exponential in the planning horizon $H$. In this paper, we propose an online RL algorithm, namely the MatrixRL, that leverages ideas from linear bandit to learn a low-dimensional representation of the probability transition model while carefully balancing the exploitation-explorati","authors_text":"Lin F. Yang, Mengdi Wang","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-24T18:02:39Z","title":"Reinforcement Learning in Feature Space: Matrix Bandit, Kernels, and Regret Bound"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.10389","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":"sha256:52a29453015bf52559d10f0a34c200e030d548b7d0554b19cdceaf4317850060","target":"record","created_at":"2026-05-17T23:43:27Z","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":"6ed6bbd56405a7e33e310813eca364d6a5e9a4508e685e2026b85fec22029ee9","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-24T18:02:39Z","title_canon_sha256":"6e6e9a7d744f6bbe52bb2937c1f0d02b33cc9894aa71753fc818f6e0d83ca3b5"},"schema_version":"1.0","source":{"id":"1905.10389","kind":"arxiv","version":2}},"canonical_sha256":"7b7c609bfa016fe2b14225824900aafb92392c178f26c68e318dbcab2d090e4f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7b7c609bfa016fe2b14225824900aafb92392c178f26c68e318dbcab2d090e4f","first_computed_at":"2026-05-17T23:43:27.585808Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:43:27.585808Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CrW3u9n1kfKPK6Z1MFwHvd3V13vJGUAu4ycJ21u7CgUYq53b0p7VxzrbPBmWQFhwD4yevFSO1Jlc3ql0Ia15DQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:43:27.586223Z","signed_message":"canonical_sha256_bytes"},"source_id":"1905.10389","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:52a29453015bf52559d10f0a34c200e030d548b7d0554b19cdceaf4317850060","sha256:1f62d3b95209d05c61e517d73f864d01da170e7ad8e0f1c884bc7a00020b1b10"],"state_sha256":"72d4973138b07d6d04f68dc2f439abcb3e396d8f04ee17325a574a99d06c7b00"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Fb8SsY8wyCs49zOZ0WZm9YIWon7wSYdD9YmcQONaMFW774s3bH8s2xulnUvXebxVFtGSIu27nfD9f7jlrbGqCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-31T00:15:13.301696Z","bundle_sha256":"474437ade0f568e8b85616e477dd5ad18ce9ac128f16f9c0db2048766de51b19"}}