{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:LINTXB6B7KVNFJ6C4XFUBSJNLT","short_pith_number":"pith:LINTXB6B","schema_version":"1.0","canonical_sha256":"5a1b3b87c1faaad2a7c2e5cb40c92d5cd3966f1f92db4e29253e52b2f0ddd0c9","source":{"kind":"arxiv","id":"2010.15268","version":1},"attestation_state":"computed","paper":{"title":"Understanding the Pathologies of Approximate Policy Evaluation when Combined with Greedification in Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Kenny Young, Richard S. Sutton","submitted_at":"2020-10-28T22:57:57Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2010.15268","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-28T22:57:57Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e8a8d420b77b37a39dfabc648958d7fe90f37f75e02bacbfabd88a628c60ed3b","abstract_canon_sha256":"3e369469ec0749abb7ada647d3d0e27111f7319a94c3d0419503718be26a5ae9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:47:35.304557Z","signature_b64":"kZUR2UQ9OAg9B/DOn8lDfUpZ1e0CgmddLp6EWGBVxZDXqWMCBVGtF1rVxJWtAeyyQrq4Ud1Av1f1vGzfAy7hDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5a1b3b87c1faaad2a7c2e5cb40c92d5cd3966f1f92db4e29253e52b2f0ddd0c9","last_reissued_at":"2026-07-05T01:47:35.304067Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:47:35.304067Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Understanding the Pathologies of Approximate Policy Evaluation when Combined with Greedification in Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Kenny Young, Richard S. Sutton","submitted_at":"2020-10-28T22:57:57Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.15268","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/2010.15268/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2010.15268","created_at":"2026-07-05T01:47:35.304134+00:00"},{"alias_kind":"arxiv_version","alias_value":"2010.15268v1","created_at":"2026-07-05T01:47:35.304134+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.15268","created_at":"2026-07-05T01:47:35.304134+00:00"},{"alias_kind":"pith_short_12","alias_value":"LINTXB6B7KVN","created_at":"2026-07-05T01:47:35.304134+00:00"},{"alias_kind":"pith_short_16","alias_value":"LINTXB6B7KVNFJ6C","created_at":"2026-07-05T01:47:35.304134+00:00"},{"alias_kind":"pith_short_8","alias_value":"LINTXB6B","created_at":"2026-07-05T01:47:35.304134+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LINTXB6B7KVNFJ6C4XFUBSJNLT","json":"https://pith.science/pith/LINTXB6B7KVNFJ6C4XFUBSJNLT.json","graph_json":"https://pith.science/api/pith-number/LINTXB6B7KVNFJ6C4XFUBSJNLT/graph.json","events_json":"https://pith.science/api/pith-number/LINTXB6B7KVNFJ6C4XFUBSJNLT/events.json","paper":"https://pith.science/paper/LINTXB6B"},"agent_actions":{"view_html":"https://pith.science/pith/LINTXB6B7KVNFJ6C4XFUBSJNLT","download_json":"https://pith.science/pith/LINTXB6B7KVNFJ6C4XFUBSJNLT.json","view_paper":"https://pith.science/paper/LINTXB6B","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2010.15268&json=true","fetch_graph":"https://pith.science/api/pith-number/LINTXB6B7KVNFJ6C4XFUBSJNLT/graph.json","fetch_events":"https://pith.science/api/pith-number/LINTXB6B7KVNFJ6C4XFUBSJNLT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LINTXB6B7KVNFJ6C4XFUBSJNLT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LINTXB6B7KVNFJ6C4XFUBSJNLT/action/storage_attestation","attest_author":"https://pith.science/pith/LINTXB6B7KVNFJ6C4XFUBSJNLT/action/author_attestation","sign_citation":"https://pith.science/pith/LINTXB6B7KVNFJ6C4XFUBSJNLT/action/citation_signature","submit_replication":"https://pith.science/pith/LINTXB6B7KVNFJ6C4XFUBSJNLT/action/replication_record"}},"created_at":"2026-07-05T01:47:35.304134+00:00","updated_at":"2026-07-05T01:47:35.304134+00:00"}