{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2013:URPXXJEB6GTUBHHQPAMF5M3LRD","short_pith_number":"pith:URPXXJEB","canonical_record":{"source":{"id":"1305.1027","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2013-05-05T16:59:58Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"aec5b353688311c6c1bce280c05fb6df7c67b37c2af11bc282c4ff73d6a55455","abstract_canon_sha256":"7c407a723bf8bd190e688a94b8b428c1b2cdc0cab178154ff849e2c6d5c070d3"},"schema_version":"1.0"},"canonical_sha256":"a45f7ba481f1a7409cf078185eb36b88c573d8bc9bc2e9278fa9837a0f7d3b54","source":{"kind":"arxiv","id":"1305.1027","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1305.1027","created_at":"2026-05-18T03:18:08Z"},{"alias_kind":"arxiv_version","alias_value":"1305.1027v2","created_at":"2026-05-18T03:18:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1305.1027","created_at":"2026-05-18T03:18:08Z"},{"alias_kind":"pith_short_12","alias_value":"URPXXJEB6GTU","created_at":"2026-05-18T12:28:02Z"},{"alias_kind":"pith_short_16","alias_value":"URPXXJEB6GTUBHHQ","created_at":"2026-05-18T12:28:02Z"},{"alias_kind":"pith_short_8","alias_value":"URPXXJEB","created_at":"2026-05-18T12:28:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2013:URPXXJEB6GTUBHHQPAMF5M3LRD","target":"record","payload":{"canonical_record":{"source":{"id":"1305.1027","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2013-05-05T16:59:58Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"aec5b353688311c6c1bce280c05fb6df7c67b37c2af11bc282c4ff73d6a55455","abstract_canon_sha256":"7c407a723bf8bd190e688a94b8b428c1b2cdc0cab178154ff849e2c6d5c070d3"},"schema_version":"1.0"},"canonical_sha256":"a45f7ba481f1a7409cf078185eb36b88c573d8bc9bc2e9278fa9837a0f7d3b54","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:18:08.816516Z","signature_b64":"12TFGMeuxX5KSngZl8N2nrjkEex3Mx+zX6j7+MxDjAFJ9C+XjCI5daEp//RmDbN2iR3vj/ZOg9wNvY5tTvhKBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a45f7ba481f1a7409cf078185eb36b88c573d8bc9bc2e9278fa9837a0f7d3b54","last_reissued_at":"2026-05-18T03:18:08.816014Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:18:08.816014Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1305.1027","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":"2026-05-18T03:18:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XqQb2iTjsnC5GpmINTJYaHuA/WfFUafy4RcFMbIATpxKFDCXztWbBvK9OcCXEWSMn8QbBKVqF3NqFNAE0IrlBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T05:10:14.400371Z"},"content_sha256":"cf16bac8650672408cd5e1eaf7e9d98b7b2467fd6d6ecdff9ab65c4db22f4fed","schema_version":"1.0","event_id":"sha256:cf16bac8650672408cd5e1eaf7e9d98b7b2467fd6d6ecdff9ab65c4db22f4fed"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2013:URPXXJEB6GTUBHHQPAMF5M3LRD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Regret Bounds for Reinforcement Learning with Policy Advice","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Alessandro Lazaric, Emma Brunskill, Mohammad Gheshlaghi Azar","submitted_at":"2013-05-05T16:59:58Z","abstract_excerpt":"In some reinforcement learning problems an agent may be provided with a set of input policies, perhaps learned from prior experience or provided by advisors. We present a reinforcement learning with policy advice (RLPA) algorithm which leverages this input set and learns to use the best policy in the set for the reinforcement learning task at hand. We prove that RLPA has a sub-linear regret of \\tilde O(\\sqrt{T}) relative to the best input policy, and that both this regret and its computational complexity are independent of the size of the state and action space. Our empirical simulations suppo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1305.1027","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":"2026-05-18T03:18:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aIJB7Ecz01OXLXIMOtoL0VEssUBGPaAwhbAQ0RgfugySUhH8cbG5Zbalye3ySLg6ndHg0aH9mZ5h+fuaBamTCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T05:10:14.400715Z"},"content_sha256":"df2fb2d5ae3ad9c27857ee12feb2562e324cf65453884d8b206a32dfaab5ca32","schema_version":"1.0","event_id":"sha256:df2fb2d5ae3ad9c27857ee12feb2562e324cf65453884d8b206a32dfaab5ca32"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/URPXXJEB6GTUBHHQPAMF5M3LRD/bundle.json","state_url":"https://pith.science/pith/URPXXJEB6GTUBHHQPAMF5M3LRD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/URPXXJEB6GTUBHHQPAMF5M3LRD/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":"2026-07-07T05:10:14Z","links":{"resolver":"https://pith.science/pith/URPXXJEB6GTUBHHQPAMF5M3LRD","bundle":"https://pith.science/pith/URPXXJEB6GTUBHHQPAMF5M3LRD/bundle.json","state":"https://pith.science/pith/URPXXJEB6GTUBHHQPAMF5M3LRD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/URPXXJEB6GTUBHHQPAMF5M3LRD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2013:URPXXJEB6GTUBHHQPAMF5M3LRD","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":"7c407a723bf8bd190e688a94b8b428c1b2cdc0cab178154ff849e2c6d5c070d3","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2013-05-05T16:59:58Z","title_canon_sha256":"aec5b353688311c6c1bce280c05fb6df7c67b37c2af11bc282c4ff73d6a55455"},"schema_version":"1.0","source":{"id":"1305.1027","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1305.1027","created_at":"2026-05-18T03:18:08Z"},{"alias_kind":"arxiv_version","alias_value":"1305.1027v2","created_at":"2026-05-18T03:18:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1305.1027","created_at":"2026-05-18T03:18:08Z"},{"alias_kind":"pith_short_12","alias_value":"URPXXJEB6GTU","created_at":"2026-05-18T12:28:02Z"},{"alias_kind":"pith_short_16","alias_value":"URPXXJEB6GTUBHHQ","created_at":"2026-05-18T12:28:02Z"},{"alias_kind":"pith_short_8","alias_value":"URPXXJEB","created_at":"2026-05-18T12:28:02Z"}],"graph_snapshots":[{"event_id":"sha256:df2fb2d5ae3ad9c27857ee12feb2562e324cf65453884d8b206a32dfaab5ca32","target":"graph","created_at":"2026-05-18T03:18:08Z","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"},"paper":{"abstract_excerpt":"In some reinforcement learning problems an agent may be provided with a set of input policies, perhaps learned from prior experience or provided by advisors. We present a reinforcement learning with policy advice (RLPA) algorithm which leverages this input set and learns to use the best policy in the set for the reinforcement learning task at hand. We prove that RLPA has a sub-linear regret of \\tilde O(\\sqrt{T}) relative to the best input policy, and that both this regret and its computational complexity are independent of the size of the state and action space. Our empirical simulations suppo","authors_text":"Alessandro Lazaric, Emma Brunskill, Mohammad Gheshlaghi Azar","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2013-05-05T16:59:58Z","title":"Regret Bounds for Reinforcement Learning with Policy Advice"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1305.1027","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:cf16bac8650672408cd5e1eaf7e9d98b7b2467fd6d6ecdff9ab65c4db22f4fed","target":"record","created_at":"2026-05-18T03:18:08Z","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":"7c407a723bf8bd190e688a94b8b428c1b2cdc0cab178154ff849e2c6d5c070d3","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2013-05-05T16:59:58Z","title_canon_sha256":"aec5b353688311c6c1bce280c05fb6df7c67b37c2af11bc282c4ff73d6a55455"},"schema_version":"1.0","source":{"id":"1305.1027","kind":"arxiv","version":2}},"canonical_sha256":"a45f7ba481f1a7409cf078185eb36b88c573d8bc9bc2e9278fa9837a0f7d3b54","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a45f7ba481f1a7409cf078185eb36b88c573d8bc9bc2e9278fa9837a0f7d3b54","first_computed_at":"2026-05-18T03:18:08.816014Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:18:08.816014Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"12TFGMeuxX5KSngZl8N2nrjkEex3Mx+zX6j7+MxDjAFJ9C+XjCI5daEp//RmDbN2iR3vj/ZOg9wNvY5tTvhKBw==","signature_status":"signed_v1","signed_at":"2026-05-18T03:18:08.816516Z","signed_message":"canonical_sha256_bytes"},"source_id":"1305.1027","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cf16bac8650672408cd5e1eaf7e9d98b7b2467fd6d6ecdff9ab65c4db22f4fed","sha256:df2fb2d5ae3ad9c27857ee12feb2562e324cf65453884d8b206a32dfaab5ca32"],"state_sha256":"3f57ab78c2cf2861625565a2d8c858bed2739b0934e541366012ddbb43dada21"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vlU8QL7LFaTPvUc6quajfvlz/KZhDBIh+f3G8EXM8QBAQ16ZC4s2/EGeq+F/34/Ucggxb0B6ol9izeJzXPI3CA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T05:10:14.402573Z","bundle_sha256":"1bb7f4466aae8f45440c8186bb6b61e256fb625b6685bf34983d9f8afd51b4e6"}}