{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:PTW2YAAPFYSLFDRKPMBQO333K2","short_pith_number":"pith:PTW2YAAP","canonical_record":{"source":{"id":"1706.04241","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-06-13T20:22:54Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"64980db81832324e43a6be30a4779deaf2c6e702078d7dd698154125736e3d0c","abstract_canon_sha256":"61beb3ad9d179c947576cf595c0c0ac960670f2a1c4c93c7bf2a38c266153da8"},"schema_version":"1.0"},"canonical_sha256":"7cedac000f2e24b28e2a7b03076f7b5688b967a8c219fcbb611bd6157e6632fb","source":{"kind":"arxiv","id":"1706.04241","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1706.04241","created_at":"2026-05-18T00:42:23Z"},{"alias_kind":"arxiv_version","alias_value":"1706.04241v1","created_at":"2026-05-18T00:42:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1706.04241","created_at":"2026-05-18T00:42:23Z"},{"alias_kind":"pith_short_12","alias_value":"PTW2YAAPFYSL","created_at":"2026-05-18T12:31:37Z"},{"alias_kind":"pith_short_16","alias_value":"PTW2YAAPFYSLFDRK","created_at":"2026-05-18T12:31:37Z"},{"alias_kind":"pith_short_8","alias_value":"PTW2YAAP","created_at":"2026-05-18T12:31:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:PTW2YAAPFYSLFDRKPMBQO333K2","target":"record","payload":{"canonical_record":{"source":{"id":"1706.04241","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-06-13T20:22:54Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"64980db81832324e43a6be30a4779deaf2c6e702078d7dd698154125736e3d0c","abstract_canon_sha256":"61beb3ad9d179c947576cf595c0c0ac960670f2a1c4c93c7bf2a38c266153da8"},"schema_version":"1.0"},"canonical_sha256":"7cedac000f2e24b28e2a7b03076f7b5688b967a8c219fcbb611bd6157e6632fb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:42:23.190721Z","signature_b64":"i8ragjr1oQzyvmvJqoezsU0lQQ6Us0rI+1vFqEhwD06VljnBIwUooNK9py54VqkXBSJXU6eDjFvtPmKS6WTXBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7cedac000f2e24b28e2a7b03076f7b5688b967a8c219fcbb611bd6157e6632fb","last_reissued_at":"2026-05-18T00:42:23.190272Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:42:23.190272Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1706.04241","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":"2026-05-18T00:42:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6sjR+wxuyb8mb9Z2xtpKxxbpZAXZ4oEeCAW/w1+U1K1v1YONu2kTS2VXMPOfRNT+wsZS1ocXzJiC+yEliRicBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T14:44:34.022376Z"},"content_sha256":"c58a9ec1c6a388d0793e7529eb4df95f75b01fa6d6678c6a9c4a6f18bb93d08c","schema_version":"1.0","event_id":"sha256:c58a9ec1c6a388d0793e7529eb4df95f75b01fa6d6678c6a9c4a6f18bb93d08c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:PTW2YAAPFYSLFDRKPMBQO333K2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"On Optimistic versus Randomized Exploration in Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Benjamin Van Roy, Ian Osband","submitted_at":"2017-06-13T20:22:54Z","abstract_excerpt":"We discuss the relative merits of optimistic and randomized approaches to exploration in reinforcement learning. Optimistic approaches presented in the literature apply an optimistic boost to the value estimate at each state-action pair and select actions that are greedy with respect to the resulting optimistic value function. Randomized approaches sample from among statistically plausible value functions and select actions that are greedy with respect to the random sample. Prior computational experience suggests that randomized approaches can lead to far more statistically efficient learning."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1706.04241","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":"2026-05-18T00:42:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"D2mt21pn1kGTgQ+lrJCMQiIHbwYlQ5AtptUq30QUCG9XtDqvMYwht06D/khB1P14Kuo5T1Ol1r8u9PEACUljBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T14:44:34.023018Z"},"content_sha256":"ae6ce257b563bf9f67de5d5c59e51002a315548c8645585302696af306630231","schema_version":"1.0","event_id":"sha256:ae6ce257b563bf9f67de5d5c59e51002a315548c8645585302696af306630231"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PTW2YAAPFYSLFDRKPMBQO333K2/bundle.json","state_url":"https://pith.science/pith/PTW2YAAPFYSLFDRKPMBQO333K2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PTW2YAAPFYSLFDRKPMBQO333K2/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":"2026-08-11T14:44:34Z","links":{"resolver":"https://pith.science/pith/PTW2YAAPFYSLFDRKPMBQO333K2","bundle":"https://pith.science/pith/PTW2YAAPFYSLFDRKPMBQO333K2/bundle.json","state":"https://pith.science/pith/PTW2YAAPFYSLFDRKPMBQO333K2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PTW2YAAPFYSLFDRKPMBQO333K2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:PTW2YAAPFYSLFDRKPMBQO333K2","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":"61beb3ad9d179c947576cf595c0c0ac960670f2a1c4c93c7bf2a38c266153da8","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-06-13T20:22:54Z","title_canon_sha256":"64980db81832324e43a6be30a4779deaf2c6e702078d7dd698154125736e3d0c"},"schema_version":"1.0","source":{"id":"1706.04241","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1706.04241","created_at":"2026-05-18T00:42:23Z"},{"alias_kind":"arxiv_version","alias_value":"1706.04241v1","created_at":"2026-05-18T00:42:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1706.04241","created_at":"2026-05-18T00:42:23Z"},{"alias_kind":"pith_short_12","alias_value":"PTW2YAAPFYSL","created_at":"2026-05-18T12:31:37Z"},{"alias_kind":"pith_short_16","alias_value":"PTW2YAAPFYSLFDRK","created_at":"2026-05-18T12:31:37Z"},{"alias_kind":"pith_short_8","alias_value":"PTW2YAAP","created_at":"2026-05-18T12:31:37Z"}],"graph_snapshots":[{"event_id":"sha256:ae6ce257b563bf9f67de5d5c59e51002a315548c8645585302696af306630231","target":"graph","created_at":"2026-05-18T00:42:23Z","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 discuss the relative merits of optimistic and randomized approaches to exploration in reinforcement learning. Optimistic approaches presented in the literature apply an optimistic boost to the value estimate at each state-action pair and select actions that are greedy with respect to the resulting optimistic value function. Randomized approaches sample from among statistically plausible value functions and select actions that are greedy with respect to the random sample. Prior computational experience suggests that randomized approaches can lead to far more statistically efficient learning.","authors_text":"Benjamin Van Roy, Ian Osband","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-06-13T20:22:54Z","title":"On Optimistic versus Randomized Exploration in Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1706.04241","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:c58a9ec1c6a388d0793e7529eb4df95f75b01fa6d6678c6a9c4a6f18bb93d08c","target":"record","created_at":"2026-05-18T00:42:23Z","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":"61beb3ad9d179c947576cf595c0c0ac960670f2a1c4c93c7bf2a38c266153da8","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-06-13T20:22:54Z","title_canon_sha256":"64980db81832324e43a6be30a4779deaf2c6e702078d7dd698154125736e3d0c"},"schema_version":"1.0","source":{"id":"1706.04241","kind":"arxiv","version":1}},"canonical_sha256":"7cedac000f2e24b28e2a7b03076f7b5688b967a8c219fcbb611bd6157e6632fb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7cedac000f2e24b28e2a7b03076f7b5688b967a8c219fcbb611bd6157e6632fb","first_computed_at":"2026-05-18T00:42:23.190272Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:42:23.190272Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"i8ragjr1oQzyvmvJqoezsU0lQQ6Us0rI+1vFqEhwD06VljnBIwUooNK9py54VqkXBSJXU6eDjFvtPmKS6WTXBQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:42:23.190721Z","signed_message":"canonical_sha256_bytes"},"source_id":"1706.04241","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c58a9ec1c6a388d0793e7529eb4df95f75b01fa6d6678c6a9c4a6f18bb93d08c","sha256:ae6ce257b563bf9f67de5d5c59e51002a315548c8645585302696af306630231"],"state_sha256":"f99980df004ee8527ffe22cbeaed146e59d6698bd0e078818107f7f360bdfb98"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MjY/HeDG9QDJqOGe8xIj3wklR/tnlAEu+UOo1bNlAMfD8ppvcnhHe0kJmriqAylCroA71OIqXyjDfHXB2HgKAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T14:44:34.030231Z","bundle_sha256":"9f2c1ecd450d59a9af65cb7c6673cb4c0e4223a8e15a185fb4582165301db8e3"}}