{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:AKZER62NHSI4CVKDVXQABBZ5HP","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":"262b43479ac50e3acf4a7255c7f10ebf9f22a482e6ed4da7418e6ccb73b23458","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-26T17:15:53Z","title_canon_sha256":"1a87eb0e1d19b845daf8e6896636e5efa90c5558f0a7b2f6f9c8d2827c69ce9b"},"schema_version":"1.0","source":{"id":"2002.12174","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2002.12174","created_at":"2026-07-05T00:44:21Z"},{"alias_kind":"arxiv_version","alias_value":"2002.12174v1","created_at":"2026-07-05T00:44:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.12174","created_at":"2026-07-05T00:44:21Z"},{"alias_kind":"pith_short_12","alias_value":"AKZER62NHSI4","created_at":"2026-07-05T00:44:21Z"},{"alias_kind":"pith_short_16","alias_value":"AKZER62NHSI4CVKD","created_at":"2026-07-05T00:44:21Z"},{"alias_kind":"pith_short_8","alias_value":"AKZER62N","created_at":"2026-07-05T00:44:21Z"}],"graph_snapshots":[{"event_id":"sha256:4b3fea45cc0595a0e997ccd9a5231cb3cea0c416648410a602c44d933903bd86","target":"graph","created_at":"2026-07-05T00:44:21Z","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/2002.12174/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Optimistic initialisation is an effective strategy for efficient exploration in reinforcement learning (RL). In the tabular case, all provably efficient model-free algorithms rely on it. However, model-free deep RL algorithms do not use optimistic initialisation despite taking inspiration from these provably efficient tabular algorithms. In particular, in scenarios with only positive rewards, Q-values are initialised at their lowest possible values due to commonly used network initialisation schemes, a pessimistic initialisation. Merely initialising the network to output optimistic Q-values is","authors_text":"Bei Peng, Shimon Whiteson, Tabish Rashid, Wendelin B\\\"ohmer","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-26T17:15:53Z","title":"Optimistic Exploration even with a Pessimistic Initialisation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.12174","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":"sha256:2e59dea348d49bf473b0fb2fef1573f83a8e76b87f34e40ae7faa766b510fd2d","target":"record","created_at":"2026-07-05T00:44:21Z","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":"262b43479ac50e3acf4a7255c7f10ebf9f22a482e6ed4da7418e6ccb73b23458","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-26T17:15:53Z","title_canon_sha256":"1a87eb0e1d19b845daf8e6896636e5efa90c5558f0a7b2f6f9c8d2827c69ce9b"},"schema_version":"1.0","source":{"id":"2002.12174","kind":"arxiv","version":1}},"canonical_sha256":"02b248fb4d3c91c15543ade000873d3bc31ce529180ca0c71ab13777f17319ab","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"02b248fb4d3c91c15543ade000873d3bc31ce529180ca0c71ab13777f17319ab","first_computed_at":"2026-07-05T00:44:21.176531Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:44:21.176531Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wPZECVq3D7CYW8JfF1LS1rYVU4aubbBDCSPRpc4Jl7fxw2vhN4BD5GIKskWj8PFt4iWukuGvdqqGYcFytntYCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T00:44:21.176930Z","signed_message":"canonical_sha256_bytes"},"source_id":"2002.12174","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2e59dea348d49bf473b0fb2fef1573f83a8e76b87f34e40ae7faa766b510fd2d","sha256:4b3fea45cc0595a0e997ccd9a5231cb3cea0c416648410a602c44d933903bd86"],"state_sha256":"9de726ac76e88e0f63183f537d78724fc4a7de2bc39df43e672ea83ce6375cd7"}