{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:LINTXB6B7KVNFJ6C4XFUBSJNLT","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":"3e369469ec0749abb7ada647d3d0e27111f7319a94c3d0419503718be26a5ae9","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-28T22:57:57Z","title_canon_sha256":"e8a8d420b77b37a39dfabc648958d7fe90f37f75e02bacbfabd88a628c60ed3b"},"schema_version":"1.0","source":{"id":"2010.15268","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2010.15268","created_at":"2026-07-05T01:47:35Z"},{"alias_kind":"arxiv_version","alias_value":"2010.15268v1","created_at":"2026-07-05T01:47:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.15268","created_at":"2026-07-05T01:47:35Z"},{"alias_kind":"pith_short_12","alias_value":"LINTXB6B7KVN","created_at":"2026-07-05T01:47:35Z"},{"alias_kind":"pith_short_16","alias_value":"LINTXB6B7KVNFJ6C","created_at":"2026-07-05T01:47:35Z"},{"alias_kind":"pith_short_8","alias_value":"LINTXB6B","created_at":"2026-07-05T01:47:35Z"}],"graph_snapshots":[{"event_id":"sha256:3dd39a99926792ea77ad4d003f2fc65b996e182a6def67e731f911e31e6ca262","target":"graph","created_at":"2026-07-05T01:47:35Z","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/2010.15268/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite empirical success, the theory of reinforcement learning (RL) with value function approximation remains fundamentally incomplete. Prior work has identified a variety of pathological behaviours that arise in RL algorithms that combine approximate on-policy evaluation and greedification. One prominent example is policy oscillation, wherein an algorithm may cycle indefinitely between policies, rather than converging to a fixed point. What is not well understood however is the quality of the policies in the region of oscillation. In this paper we present simple examples illustrating that in","authors_text":"Kenny Young, Richard S. Sutton","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-28T22:57:57Z","title":"Understanding the Pathologies of Approximate Policy Evaluation when Combined with Greedification in Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.15268","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:a066be40be590746ea1160657b22b5ecab8d51eb6070fa7e181372e07d1481fc","target":"record","created_at":"2026-07-05T01:47:35Z","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":"3e369469ec0749abb7ada647d3d0e27111f7319a94c3d0419503718be26a5ae9","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-28T22:57:57Z","title_canon_sha256":"e8a8d420b77b37a39dfabc648958d7fe90f37f75e02bacbfabd88a628c60ed3b"},"schema_version":"1.0","source":{"id":"2010.15268","kind":"arxiv","version":1}},"canonical_sha256":"5a1b3b87c1faaad2a7c2e5cb40c92d5cd3966f1f92db4e29253e52b2f0ddd0c9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5a1b3b87c1faaad2a7c2e5cb40c92d5cd3966f1f92db4e29253e52b2f0ddd0c9","first_computed_at":"2026-07-05T01:47:35.304067Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:47:35.304067Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kZUR2UQ9OAg9B/DOn8lDfUpZ1e0CgmddLp6EWGBVxZDXqWMCBVGtF1rVxJWtAeyyQrq4Ud1Av1f1vGzfAy7hDw==","signature_status":"signed_v1","signed_at":"2026-07-05T01:47:35.304557Z","signed_message":"canonical_sha256_bytes"},"source_id":"2010.15268","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a066be40be590746ea1160657b22b5ecab8d51eb6070fa7e181372e07d1481fc","sha256:3dd39a99926792ea77ad4d003f2fc65b996e182a6def67e731f911e31e6ca262"],"state_sha256":"c6ac0ba4cf5e2ab810eca87434315ade6380b082ba5bad78a8941e12b1ed033d"}