{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:KJX43K2OWKECP5QUWRPKT33XGH","short_pith_number":"pith:KJX43K2O","canonical_record":{"source":{"id":"2006.01782","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-02T17:02:55Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"852aaf21711bf3033d8323501629a32cb09b43fdafa693fe78869749e518e6e1","abstract_canon_sha256":"b16afcd444b9cb85f91ceba9602bef72978d977ce19496fcf8b861f350c91826"},"schema_version":"1.0"},"canonical_sha256":"526fcdab4eb28827f614b45ea9ef7731e28aa5a1b39abc4001e0e2ed872284ae","source":{"kind":"arxiv","id":"2006.01782","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.01782","created_at":"2026-07-05T01:07:34Z"},{"alias_kind":"arxiv_version","alias_value":"2006.01782v1","created_at":"2026-07-05T01:07:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.01782","created_at":"2026-07-05T01:07:34Z"},{"alias_kind":"pith_short_12","alias_value":"KJX43K2OWKEC","created_at":"2026-07-05T01:07:34Z"},{"alias_kind":"pith_short_16","alias_value":"KJX43K2OWKECP5QU","created_at":"2026-07-05T01:07:34Z"},{"alias_kind":"pith_short_8","alias_value":"KJX43K2O","created_at":"2026-07-05T01:07:34Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:KJX43K2OWKECP5QUWRPKT33XGH","target":"record","payload":{"canonical_record":{"source":{"id":"2006.01782","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-02T17:02:55Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"852aaf21711bf3033d8323501629a32cb09b43fdafa693fe78869749e518e6e1","abstract_canon_sha256":"b16afcd444b9cb85f91ceba9602bef72978d977ce19496fcf8b861f350c91826"},"schema_version":"1.0"},"canonical_sha256":"526fcdab4eb28827f614b45ea9ef7731e28aa5a1b39abc4001e0e2ed872284ae","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:07:34.123660Z","signature_b64":"Irptqm3lf8G+Z/TJG2baSPRFIcc2MQEBGRM4tzQuP2cWXUxisrJEnziaoA73AMHtpKZYkVeLycJxYSR5iCmACw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"526fcdab4eb28827f614b45ea9ef7731e28aa5a1b39abc4001e0e2ed872284ae","last_reissued_at":"2026-07-05T01:07:34.123184Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:07:34.123184Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2006.01782","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":"2026-07-05T01:07:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Z4HHVcqFOjEIKzKiZn67IZUCXgzDihxONikHJe4anqawCr4ls8aP7lIn8nyAue74jvKS4L//nlhT9Z1Ig6wkAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T18:48:16.897887Z"},"content_sha256":"51e8a578b0195e069f75ee45814dae6e3a0be087f9dc2e8cd260a9f62b769f8b","schema_version":"1.0","event_id":"sha256:51e8a578b0195e069f75ee45814dae6e3a0be087f9dc2e8cd260a9f62b769f8b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:KJX43K2OWKECP5QUWRPKT33XGH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Temporally-Extended {\\epsilon}-Greedy Exploration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Andr\\'e Barreto, Georg Ostrovski, Will Dabney","submitted_at":"2020-06-02T17:02:55Z","abstract_excerpt":"Recent work on exploration in reinforcement learning (RL) has led to a series of increasingly complex solutions to the problem. This increase in complexity often comes at the expense of generality. Recent empirical studies suggest that, when applied to a broader set of domains, some sophisticated exploration methods are outperformed by simpler counterparts, such as {\\epsilon}-greedy. In this paper we propose an exploration algorithm that retains the simplicity of {\\epsilon}-greedy while reducing dithering. We build on a simple hypothesis: the main limitation of {\\epsilon}-greedy exploration is"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.01782","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2006.01782/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":"2026-07-05T01:07:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pO6oh6jRd2s+A1+jxvDkT8cloUkfXtvV4JzTCR9vu/uZtxcop794uOABqAi8SWNnqtfC0u7LfHss+rZ/jb6ZAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T18:48:16.898389Z"},"content_sha256":"05bd5127e0b82a4c87bc549df81ca737001d078755ac8e3d9707d26400adbe68","schema_version":"1.0","event_id":"sha256:05bd5127e0b82a4c87bc549df81ca737001d078755ac8e3d9707d26400adbe68"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KJX43K2OWKECP5QUWRPKT33XGH/bundle.json","state_url":"https://pith.science/pith/KJX43K2OWKECP5QUWRPKT33XGH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KJX43K2OWKECP5QUWRPKT33XGH/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":"2026-08-12T18:48:16Z","links":{"resolver":"https://pith.science/pith/KJX43K2OWKECP5QUWRPKT33XGH","bundle":"https://pith.science/pith/KJX43K2OWKECP5QUWRPKT33XGH/bundle.json","state":"https://pith.science/pith/KJX43K2OWKECP5QUWRPKT33XGH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KJX43K2OWKECP5QUWRPKT33XGH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:KJX43K2OWKECP5QUWRPKT33XGH","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":"b16afcd444b9cb85f91ceba9602bef72978d977ce19496fcf8b861f350c91826","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-02T17:02:55Z","title_canon_sha256":"852aaf21711bf3033d8323501629a32cb09b43fdafa693fe78869749e518e6e1"},"schema_version":"1.0","source":{"id":"2006.01782","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.01782","created_at":"2026-07-05T01:07:34Z"},{"alias_kind":"arxiv_version","alias_value":"2006.01782v1","created_at":"2026-07-05T01:07:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.01782","created_at":"2026-07-05T01:07:34Z"},{"alias_kind":"pith_short_12","alias_value":"KJX43K2OWKEC","created_at":"2026-07-05T01:07:34Z"},{"alias_kind":"pith_short_16","alias_value":"KJX43K2OWKECP5QU","created_at":"2026-07-05T01:07:34Z"},{"alias_kind":"pith_short_8","alias_value":"KJX43K2O","created_at":"2026-07-05T01:07:34Z"}],"graph_snapshots":[{"event_id":"sha256:05bd5127e0b82a4c87bc549df81ca737001d078755ac8e3d9707d26400adbe68","target":"graph","created_at":"2026-07-05T01:07:34Z","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/2006.01782/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent work on exploration in reinforcement learning (RL) has led to a series of increasingly complex solutions to the problem. This increase in complexity often comes at the expense of generality. Recent empirical studies suggest that, when applied to a broader set of domains, some sophisticated exploration methods are outperformed by simpler counterparts, such as {\\epsilon}-greedy. In this paper we propose an exploration algorithm that retains the simplicity of {\\epsilon}-greedy while reducing dithering. We build on a simple hypothesis: the main limitation of {\\epsilon}-greedy exploration is","authors_text":"Andr\\'e Barreto, Georg Ostrovski, Will Dabney","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-02T17:02:55Z","title":"Temporally-Extended {\\epsilon}-Greedy Exploration"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.01782","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":"sha256:51e8a578b0195e069f75ee45814dae6e3a0be087f9dc2e8cd260a9f62b769f8b","target":"record","created_at":"2026-07-05T01:07:34Z","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":"b16afcd444b9cb85f91ceba9602bef72978d977ce19496fcf8b861f350c91826","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-02T17:02:55Z","title_canon_sha256":"852aaf21711bf3033d8323501629a32cb09b43fdafa693fe78869749e518e6e1"},"schema_version":"1.0","source":{"id":"2006.01782","kind":"arxiv","version":1}},"canonical_sha256":"526fcdab4eb28827f614b45ea9ef7731e28aa5a1b39abc4001e0e2ed872284ae","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"526fcdab4eb28827f614b45ea9ef7731e28aa5a1b39abc4001e0e2ed872284ae","first_computed_at":"2026-07-05T01:07:34.123184Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:07:34.123184Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Irptqm3lf8G+Z/TJG2baSPRFIcc2MQEBGRM4tzQuP2cWXUxisrJEnziaoA73AMHtpKZYkVeLycJxYSR5iCmACw==","signature_status":"signed_v1","signed_at":"2026-07-05T01:07:34.123660Z","signed_message":"canonical_sha256_bytes"},"source_id":"2006.01782","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:51e8a578b0195e069f75ee45814dae6e3a0be087f9dc2e8cd260a9f62b769f8b","sha256:05bd5127e0b82a4c87bc549df81ca737001d078755ac8e3d9707d26400adbe68"],"state_sha256":"3db07f64204a4d34e65a5592fcbbab9e409598506d0d314f4afef05565e4fe62"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1MzmKUw/B2Ok04yMcHgefyICYHBElLRSlNV82X2LydcEiMhXwA0jekFhsGk3BBk/BwjkVPA2BBS8r8hCucmtCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T18:48:16.903055Z","bundle_sha256":"12a4ee5915c4d8bba3f2f5cb7fdeddb345b1599739db322aebca2394c51ae22b"}}