{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:RQJPYBGIWXN6M5HXMVRFWEZO23","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":"f4552b774d8cd09a71bf19bc2962b320074a18f5824685af8227422c5331b20b","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-06-01T19:44:18Z","title_canon_sha256":"24eefdd0f3b406c6b883534c984883467adcd05788f690fe572f89d48ea729eb"},"schema_version":"1.0","source":{"id":"2206.00730","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.00730","created_at":"2026-07-05T05:08:52Z"},{"alias_kind":"arxiv_version","alias_value":"2206.00730v3","created_at":"2026-07-05T05:08:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.00730","created_at":"2026-07-05T05:08:52Z"},{"alias_kind":"pith_short_12","alias_value":"RQJPYBGIWXN6","created_at":"2026-07-05T05:08:52Z"},{"alias_kind":"pith_short_16","alias_value":"RQJPYBGIWXN6M5HX","created_at":"2026-07-05T05:08:52Z"},{"alias_kind":"pith_short_8","alias_value":"RQJPYBGI","created_at":"2026-07-05T05:08:52Z"}],"graph_snapshots":[{"event_id":"sha256:86bf90098cc5b0c9d0e46d9f6bd07c130ca680896ec629d265d003f5d54957a3","target":"graph","created_at":"2026-07-05T05:08:52Z","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/2206.00730/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We identify and study the phenomenon of policy churn, that is, the rapid change of the greedy policy in value-based reinforcement learning. Policy churn operates at a surprisingly rapid pace, changing the greedy action in a large fraction of states within a handful of learning updates (in a typical deep RL set-up such as DQN on Atari). We characterise the phenomenon empirically, verifying that it is not limited to specific algorithm or environment properties. A number of ablations help whittle down the plausible explanations on why churn occurs to just a handful, all related to deep learning. ","authors_text":"Andr\\'e Barreto, Georg Ostrovski, John Quan, Tom Schaul","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-06-01T19:44:18Z","title":"The Phenomenon of Policy Churn"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.00730","kind":"arxiv","version":3},"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":"sha256:5df3b224cdf6c0648ca037a2fc9a091b35020e4ce0321e29ad878b6df03c9b3d","target":"record","created_at":"2026-07-05T05:08:52Z","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":"f4552b774d8cd09a71bf19bc2962b320074a18f5824685af8227422c5331b20b","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-06-01T19:44:18Z","title_canon_sha256":"24eefdd0f3b406c6b883534c984883467adcd05788f690fe572f89d48ea729eb"},"schema_version":"1.0","source":{"id":"2206.00730","kind":"arxiv","version":3}},"canonical_sha256":"8c12fc04c8b5dbe674f765625b132ed6e4d967e7d5de9f5ee0584257b88f397e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8c12fc04c8b5dbe674f765625b132ed6e4d967e7d5de9f5ee0584257b88f397e","first_computed_at":"2026-07-05T05:08:52.300876Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:08:52.300876Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3TACg1s8f6MkiJiiEl+3ZTc8Wgec8DTUT4P3SFkgz+r0i2E9XuxswPDC3IORMFom9ogo8iPlo0xy5oSFiAufBA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:08:52.301368Z","signed_message":"canonical_sha256_bytes"},"source_id":"2206.00730","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5df3b224cdf6c0648ca037a2fc9a091b35020e4ce0321e29ad878b6df03c9b3d","sha256:86bf90098cc5b0c9d0e46d9f6bd07c130ca680896ec629d265d003f5d54957a3"],"state_sha256":"4d4203530cb2ef5fc6d1d9328d11fe36e129dc89d2273e40601e95e1ada4ac9c"}