{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:QOA5QNG3U2R3MSNHHC6ARRQAF2","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":"fdf93c4cbea5e0303e892876d91ee27fa323c7aaf22fd5dc3e7904d7fecf7fae","cross_cats_sorted":["cs.IT","math.IT"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-12-28T23:59:12Z","title_canon_sha256":"c4435343ce97d059fa561682a4773276d3c57c3bfbae22dc02d77c5a4a32f5f3"},"schema_version":"1.0","source":{"id":"1512.08562","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1512.08562","created_at":"2026-05-18T00:24:45Z"},{"alias_kind":"arxiv_version","alias_value":"1512.08562v4","created_at":"2026-05-18T00:24:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1512.08562","created_at":"2026-05-18T00:24:45Z"},{"alias_kind":"pith_short_12","alias_value":"QOA5QNG3U2R3","created_at":"2026-05-18T12:29:37Z"},{"alias_kind":"pith_short_16","alias_value":"QOA5QNG3U2R3MSNH","created_at":"2026-05-18T12:29:37Z"},{"alias_kind":"pith_short_8","alias_value":"QOA5QNG3","created_at":"2026-05-18T12:29:37Z"}],"graph_snapshots":[{"event_id":"sha256:989100affb42b083e459d7593f802a852fd3eb2763c9703ca88aed8bd1cc4815","target":"graph","created_at":"2026-05-18T00:24:45Z","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":"Model-free reinforcement learning algorithms, such as Q-learning, perform poorly in the early stages of learning in noisy environments, because much effort is spent unlearning biased estimates of the state-action value function. The bias results from selecting, among several noisy estimates, the apparent optimum, which may actually be suboptimal. We propose G-learning, a new off-policy learning algorithm that regularizes the value estimates by penalizing deterministic policies in the beginning of the learning process. We show that this method reduces the bias of the value-function estimation, ","authors_text":"Ari Pakman, Naftali Tishby, Roy Fox","cross_cats":["cs.IT","math.IT"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-12-28T23:59:12Z","title":"Taming the Noise in Reinforcement Learning via Soft Updates"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1512.08562","kind":"arxiv","version":4},"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":"sha256:11dde0654f220b1339485dd11bf1cf1a0ba26b6644d228d00facdefbe15839e5","target":"record","created_at":"2026-05-18T00:24:45Z","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":"fdf93c4cbea5e0303e892876d91ee27fa323c7aaf22fd5dc3e7904d7fecf7fae","cross_cats_sorted":["cs.IT","math.IT"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-12-28T23:59:12Z","title_canon_sha256":"c4435343ce97d059fa561682a4773276d3c57c3bfbae22dc02d77c5a4a32f5f3"},"schema_version":"1.0","source":{"id":"1512.08562","kind":"arxiv","version":4}},"canonical_sha256":"8381d834dba6a3b649a738bc08c6002ebb5fc2ddccdde70eb4bbdd2e5c82eb95","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8381d834dba6a3b649a738bc08c6002ebb5fc2ddccdde70eb4bbdd2e5c82eb95","first_computed_at":"2026-05-18T00:24:45.418249Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:24:45.418249Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"eYm6azdp8FCIs9ulC3TUhnAZ2mPc9nMRolyCYyBZe1cSocEEhaskwD67Bg8bJcveJl9VfWXHRIcfEhMPYGx9AQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:24:45.418918Z","signed_message":"canonical_sha256_bytes"},"source_id":"1512.08562","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:11dde0654f220b1339485dd11bf1cf1a0ba26b6644d228d00facdefbe15839e5","sha256:989100affb42b083e459d7593f802a852fd3eb2763c9703ca88aed8bd1cc4815"],"state_sha256":"3796fbb52f32bf335db12b460bb84f93f23d253642f2d0f25a1a706a56660b6e"}