{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:Y5VEIOBEYGJ7NTQ2EQNMM2XMCJ","short_pith_number":"pith:Y5VEIOBE","canonical_record":{"source":{"id":"1808.10552","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2018-08-31T00:00:22Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"5957c1c8a82305733788140287136d9838ea0c56c467d702c6ffd2ecaf9b7129","abstract_canon_sha256":"72b5d45c5a668f71ea974e0871f5e9e359789cf34e776f5bb6fa5331e1f91ee9"},"schema_version":"1.0"},"canonical_sha256":"c76a443824c193f6ce1a241ac66aec12606021d2e9ac74ed3429e0daeceec02d","source":{"kind":"arxiv","id":"1808.10552","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1808.10552","created_at":"2026-05-18T00:06:45Z"},{"alias_kind":"arxiv_version","alias_value":"1808.10552v1","created_at":"2026-05-18T00:06:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.10552","created_at":"2026-05-18T00:06:45Z"},{"alias_kind":"pith_short_12","alias_value":"Y5VEIOBEYGJ7","created_at":"2026-05-18T12:33:04Z"},{"alias_kind":"pith_short_16","alias_value":"Y5VEIOBEYGJ7NTQ2","created_at":"2026-05-18T12:33:04Z"},{"alias_kind":"pith_short_8","alias_value":"Y5VEIOBE","created_at":"2026-05-18T12:33:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:Y5VEIOBEYGJ7NTQ2EQNMM2XMCJ","target":"record","payload":{"canonical_record":{"source":{"id":"1808.10552","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2018-08-31T00:00:22Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"5957c1c8a82305733788140287136d9838ea0c56c467d702c6ffd2ecaf9b7129","abstract_canon_sha256":"72b5d45c5a668f71ea974e0871f5e9e359789cf34e776f5bb6fa5331e1f91ee9"},"schema_version":"1.0"},"canonical_sha256":"c76a443824c193f6ce1a241ac66aec12606021d2e9ac74ed3429e0daeceec02d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:06:45.387286Z","signature_b64":"fVFN2SEjty0X3gSGw4Cv23kSnj2pkPu8/3X2wZdvAN9fz5jn9GoWzqEhjYK6CWFdLtCoB/hw9DA9x2IqIEDFDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c76a443824c193f6ce1a241ac66aec12606021d2e9ac74ed3429e0daeceec02d","last_reissued_at":"2026-05-18T00:06:45.386660Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:06:45.386660Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1808.10552","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:06:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CzvXeOAOcUedV3Qgj2nlcxqgQE1NNLyo61AW9+ZoQpRBp5IJADmWJMZKTUGv0XMs6lmWEEagNXEDyXb36mO6DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T00:22:19.151137Z"},"content_sha256":"2d473cb6fb81c9d20965eb7d9fe9efc257f0aa7fe4dc72ae3f2ad25bea9d76db","schema_version":"1.0","event_id":"sha256:2d473cb6fb81c9d20965eb7d9fe9efc257f0aa7fe4dc72ae3f2ad25bea9d76db"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:Y5VEIOBEYGJ7NTQ2EQNMM2XMCJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Directed Exploration in PAC Model-Free Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Garud Iyengar, Min-hwan Oh","submitted_at":"2018-08-31T00:00:22Z","abstract_excerpt":"We study an exploration method for model-free RL that generalizes the counter-based exploration bonus methods and takes into account long term exploratory value of actions rather than a single step look-ahead. We propose a model-free RL method that modifies Delayed Q-learning and utilizes the long-term exploration bonus with provable efficiency. We show that our proposed method finds a near-optimal policy in polynomial time (PAC-MDP), and also provide experimental evidence that our proposed algorithm is an efficient exploration method."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.10552","kind":"arxiv","version":1},"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":"2026-05-18T00:06:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RsOFB3ACKZWnyd0vVzwVLOdOJ/HMpcIy7heQjqHcBeyCBMdXzzrL+BKuy/jH1CTSMnHBwynVmwJVAAP1Geh1Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T00:22:19.151503Z"},"content_sha256":"2700bbee5648c676e001148492406458befb7824f596cb199c652b51b8f76e25","schema_version":"1.0","event_id":"sha256:2700bbee5648c676e001148492406458befb7824f596cb199c652b51b8f76e25"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Y5VEIOBEYGJ7NTQ2EQNMM2XMCJ/bundle.json","state_url":"https://pith.science/pith/Y5VEIOBEYGJ7NTQ2EQNMM2XMCJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Y5VEIOBEYGJ7NTQ2EQNMM2XMCJ/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":"2026-06-02T00:22:19Z","links":{"resolver":"https://pith.science/pith/Y5VEIOBEYGJ7NTQ2EQNMM2XMCJ","bundle":"https://pith.science/pith/Y5VEIOBEYGJ7NTQ2EQNMM2XMCJ/bundle.json","state":"https://pith.science/pith/Y5VEIOBEYGJ7NTQ2EQNMM2XMCJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Y5VEIOBEYGJ7NTQ2EQNMM2XMCJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:Y5VEIOBEYGJ7NTQ2EQNMM2XMCJ","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":"72b5d45c5a668f71ea974e0871f5e9e359789cf34e776f5bb6fa5331e1f91ee9","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2018-08-31T00:00:22Z","title_canon_sha256":"5957c1c8a82305733788140287136d9838ea0c56c467d702c6ffd2ecaf9b7129"},"schema_version":"1.0","source":{"id":"1808.10552","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1808.10552","created_at":"2026-05-18T00:06:45Z"},{"alias_kind":"arxiv_version","alias_value":"1808.10552v1","created_at":"2026-05-18T00:06:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.10552","created_at":"2026-05-18T00:06:45Z"},{"alias_kind":"pith_short_12","alias_value":"Y5VEIOBEYGJ7","created_at":"2026-05-18T12:33:04Z"},{"alias_kind":"pith_short_16","alias_value":"Y5VEIOBEYGJ7NTQ2","created_at":"2026-05-18T12:33:04Z"},{"alias_kind":"pith_short_8","alias_value":"Y5VEIOBE","created_at":"2026-05-18T12:33:04Z"}],"graph_snapshots":[{"event_id":"sha256:2700bbee5648c676e001148492406458befb7824f596cb199c652b51b8f76e25","target":"graph","created_at":"2026-05-18T00:06:45Z","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":"We study an exploration method for model-free RL that generalizes the counter-based exploration bonus methods and takes into account long term exploratory value of actions rather than a single step look-ahead. We propose a model-free RL method that modifies Delayed Q-learning and utilizes the long-term exploration bonus with provable efficiency. We show that our proposed method finds a near-optimal policy in polynomial time (PAC-MDP), and also provide experimental evidence that our proposed algorithm is an efficient exploration method.","authors_text":"Garud Iyengar, Min-hwan Oh","cross_cats":["stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2018-08-31T00:00:22Z","title":"Directed Exploration in PAC Model-Free Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.10552","kind":"arxiv","version":1},"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":"sha256:2d473cb6fb81c9d20965eb7d9fe9efc257f0aa7fe4dc72ae3f2ad25bea9d76db","target":"record","created_at":"2026-05-18T00:06:45Z","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":"72b5d45c5a668f71ea974e0871f5e9e359789cf34e776f5bb6fa5331e1f91ee9","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2018-08-31T00:00:22Z","title_canon_sha256":"5957c1c8a82305733788140287136d9838ea0c56c467d702c6ffd2ecaf9b7129"},"schema_version":"1.0","source":{"id":"1808.10552","kind":"arxiv","version":1}},"canonical_sha256":"c76a443824c193f6ce1a241ac66aec12606021d2e9ac74ed3429e0daeceec02d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c76a443824c193f6ce1a241ac66aec12606021d2e9ac74ed3429e0daeceec02d","first_computed_at":"2026-05-18T00:06:45.386660Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:06:45.386660Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fVFN2SEjty0X3gSGw4Cv23kSnj2pkPu8/3X2wZdvAN9fz5jn9GoWzqEhjYK6CWFdLtCoB/hw9DA9x2IqIEDFDQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:06:45.387286Z","signed_message":"canonical_sha256_bytes"},"source_id":"1808.10552","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2d473cb6fb81c9d20965eb7d9fe9efc257f0aa7fe4dc72ae3f2ad25bea9d76db","sha256:2700bbee5648c676e001148492406458befb7824f596cb199c652b51b8f76e25"],"state_sha256":"06fa642f770df13f2da5b52b5a6e95c79c66cc67421cde083ade60fafe616674"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MOIUwk+/nmarGMNsJkZafUHPm4dVgbHXRSIDILcJVJEvi3kTvbAfhhHh/Q+5q8PD9uNEGRibUBAHbn7jrsbIDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-02T00:22:19.153480Z","bundle_sha256":"98db381ba6651dc74e3178e039f9a1090b3f9539f31b1042eec8758c6ec3d64c"}}