{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:4VJDD6XEPVR6QWN2VEYG7DVF5D","short_pith_number":"pith:4VJDD6XE","canonical_record":{"source":{"id":"2109.00157","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-09-01T02:36:14Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"415b397fa48eaffb380ecf767adc1c4dabd985bcc2a67802b919c636cc3ede17","abstract_canon_sha256":"2dbf5ceb5b8f069f1ff4698edddc08861bf2cb2c9c5fdd8e19931ccc9f14bf03"},"schema_version":"1.0"},"canonical_sha256":"e55231fae47d63e859baa9306f8ea5e8db34dc23009350c53b65a6054fcc7d35","source":{"kind":"arxiv","id":"2109.00157","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2109.00157","created_at":"2026-07-05T03:10:55Z"},{"alias_kind":"arxiv_version","alias_value":"2109.00157v2","created_at":"2026-07-05T03:10:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.00157","created_at":"2026-07-05T03:10:55Z"},{"alias_kind":"pith_short_12","alias_value":"4VJDD6XEPVR6","created_at":"2026-07-05T03:10:55Z"},{"alias_kind":"pith_short_16","alias_value":"4VJDD6XEPVR6QWN2","created_at":"2026-07-05T03:10:55Z"},{"alias_kind":"pith_short_8","alias_value":"4VJDD6XE","created_at":"2026-07-05T03:10:55Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:4VJDD6XEPVR6QWN2VEYG7DVF5D","target":"record","payload":{"canonical_record":{"source":{"id":"2109.00157","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-09-01T02:36:14Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"415b397fa48eaffb380ecf767adc1c4dabd985bcc2a67802b919c636cc3ede17","abstract_canon_sha256":"2dbf5ceb5b8f069f1ff4698edddc08861bf2cb2c9c5fdd8e19931ccc9f14bf03"},"schema_version":"1.0"},"canonical_sha256":"e55231fae47d63e859baa9306f8ea5e8db34dc23009350c53b65a6054fcc7d35","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:10:55.645142Z","signature_b64":"jdTY4yTJJKQLhedac8I4Ej8fDLN2sGOwEuyofcktkhOViCpBrYLNiaoAUAN1WL0sBLdAduTJEhKM/S/tJkUjCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e55231fae47d63e859baa9306f8ea5e8db34dc23009350c53b65a6054fcc7d35","last_reissued_at":"2026-07-05T03:10:55.644711Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:10:55.644711Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2109.00157","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":"2026-07-05T03:10:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eTN6cB4ubsoXYw1RVhqTe2ioIrq4uhN9ep9K9Vx9aUkRV7n+lIKe9GFk7NISZqDTPZ3PkwZiDaXaiu4vq/KlCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T12:52:19.379499Z"},"content_sha256":"4665f80a273e4dc4d2692e4cb6d59eaf9a6894475b27b79164e02f2010b502aa","schema_version":"1.0","event_id":"sha256:4665f80a273e4dc4d2692e4cb6d59eaf9a6894475b27b79164e02f2010b502aa"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:4VJDD6XEPVR6QWN2VEYG7DVF5D","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Survey of Exploration Methods in Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Doina Precup, Harsh Satija, Herke van Hoof, Maziar Gomrokchi, Susan Amin","submitted_at":"2021-09-01T02:36:14Z","abstract_excerpt":"Exploration is an essential component of reinforcement learning algorithms, where agents need to learn how to predict and control unknown and often stochastic environments. Reinforcement learning agents depend crucially on exploration to obtain informative data for the learning process as the lack of enough information could hinder effective learning. In this article, we provide a survey of modern exploration methods in (Sequential) reinforcement learning, as well as a taxonomy of exploration methods."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.00157","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2109.00157/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":"2026-07-05T03:10:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2R8+XJK54O21aJGi4N3qhfSjayY3W25n0L+cTwt58kC+aydJGx4Krf7UC9OH9rsNP4RrXUdfpnb/iY4QCUZtAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T12:52:19.379858Z"},"content_sha256":"e00004c3d04b995c0f1a98ec6ae4cc48b6db7883b12d3785b8ab6d291caad0f3","schema_version":"1.0","event_id":"sha256:e00004c3d04b995c0f1a98ec6ae4cc48b6db7883b12d3785b8ab6d291caad0f3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4VJDD6XEPVR6QWN2VEYG7DVF5D/bundle.json","state_url":"https://pith.science/pith/4VJDD6XEPVR6QWN2VEYG7DVF5D/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4VJDD6XEPVR6QWN2VEYG7DVF5D/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":"2026-08-05T12:52:19Z","links":{"resolver":"https://pith.science/pith/4VJDD6XEPVR6QWN2VEYG7DVF5D","bundle":"https://pith.science/pith/4VJDD6XEPVR6QWN2VEYG7DVF5D/bundle.json","state":"https://pith.science/pith/4VJDD6XEPVR6QWN2VEYG7DVF5D/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4VJDD6XEPVR6QWN2VEYG7DVF5D/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:4VJDD6XEPVR6QWN2VEYG7DVF5D","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":"2dbf5ceb5b8f069f1ff4698edddc08861bf2cb2c9c5fdd8e19931ccc9f14bf03","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-09-01T02:36:14Z","title_canon_sha256":"415b397fa48eaffb380ecf767adc1c4dabd985bcc2a67802b919c636cc3ede17"},"schema_version":"1.0","source":{"id":"2109.00157","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2109.00157","created_at":"2026-07-05T03:10:55Z"},{"alias_kind":"arxiv_version","alias_value":"2109.00157v2","created_at":"2026-07-05T03:10:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.00157","created_at":"2026-07-05T03:10:55Z"},{"alias_kind":"pith_short_12","alias_value":"4VJDD6XEPVR6","created_at":"2026-07-05T03:10:55Z"},{"alias_kind":"pith_short_16","alias_value":"4VJDD6XEPVR6QWN2","created_at":"2026-07-05T03:10:55Z"},{"alias_kind":"pith_short_8","alias_value":"4VJDD6XE","created_at":"2026-07-05T03:10:55Z"}],"graph_snapshots":[{"event_id":"sha256:e00004c3d04b995c0f1a98ec6ae4cc48b6db7883b12d3785b8ab6d291caad0f3","target":"graph","created_at":"2026-07-05T03:10:55Z","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/2109.00157/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Exploration is an essential component of reinforcement learning algorithms, where agents need to learn how to predict and control unknown and often stochastic environments. Reinforcement learning agents depend crucially on exploration to obtain informative data for the learning process as the lack of enough information could hinder effective learning. In this article, we provide a survey of modern exploration methods in (Sequential) reinforcement learning, as well as a taxonomy of exploration methods.","authors_text":"Doina Precup, Harsh Satija, Herke van Hoof, Maziar Gomrokchi, Susan Amin","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-09-01T02:36:14Z","title":"A Survey of Exploration Methods in Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.00157","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":"sha256:4665f80a273e4dc4d2692e4cb6d59eaf9a6894475b27b79164e02f2010b502aa","target":"record","created_at":"2026-07-05T03:10:55Z","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":"2dbf5ceb5b8f069f1ff4698edddc08861bf2cb2c9c5fdd8e19931ccc9f14bf03","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-09-01T02:36:14Z","title_canon_sha256":"415b397fa48eaffb380ecf767adc1c4dabd985bcc2a67802b919c636cc3ede17"},"schema_version":"1.0","source":{"id":"2109.00157","kind":"arxiv","version":2}},"canonical_sha256":"e55231fae47d63e859baa9306f8ea5e8db34dc23009350c53b65a6054fcc7d35","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e55231fae47d63e859baa9306f8ea5e8db34dc23009350c53b65a6054fcc7d35","first_computed_at":"2026-07-05T03:10:55.644711Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:10:55.644711Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jdTY4yTJJKQLhedac8I4Ej8fDLN2sGOwEuyofcktkhOViCpBrYLNiaoAUAN1WL0sBLdAduTJEhKM/S/tJkUjCw==","signature_status":"signed_v1","signed_at":"2026-07-05T03:10:55.645142Z","signed_message":"canonical_sha256_bytes"},"source_id":"2109.00157","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4665f80a273e4dc4d2692e4cb6d59eaf9a6894475b27b79164e02f2010b502aa","sha256:e00004c3d04b995c0f1a98ec6ae4cc48b6db7883b12d3785b8ab6d291caad0f3"],"state_sha256":"0e1ce033b64d796e691e742c66af71b5adf749de470e2d064219a9dac0ba02a3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"B76j8u5cucBJiSRoM1wXK3SRnaw5UiG1F2kRGiYt+LJ1wNF1qbScZxZKw0IghwNrjqb2y9s7kP/3CPWo9tmRDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T12:52:19.383381Z","bundle_sha256":"944d640f9bb03056fd7d2d7cc8a50e8f1e06854037b1afe0d4ac836ef1a0fd13"}}