{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2011:G3JQSEQJFLNV63UWUARHUBZVOE","short_pith_number":"pith:G3JQSEQJ","schema_version":"1.0","canonical_sha256":"36d30912092adb5f6e96a0227a0735713e8f33c94ed9c352929e362bcdb5ac8c","source":{"kind":"arxiv","id":"1107.4606","version":2},"attestation_state":"computed","paper":{"title":"The Divergence of Reinforcement Learning Algorithms with Value-Iteration and Function Approximation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Eduardo Alonso, Michael Fairbank","submitted_at":"2011-07-22T13:05:48Z","abstract_excerpt":"This paper gives specific divergence examples of value-iteration for several major Reinforcement Learning and Adaptive Dynamic Programming algorithms, when using a function approximator for the value function. These divergence examples differ from previous divergence examples in the literature, in that they are applicable for a greedy policy, i.e. in a \"value iteration\" scenario. Perhaps surprisingly, with a greedy policy, it is also possible to get divergence for the algorithms TD(1) and Sarsa(1). In addition to these divergences, we also achieve divergence for the Adaptive Dynamic Programmin"},"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":"1107.4606","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2011-07-22T13:05:48Z","cross_cats_sorted":[],"title_canon_sha256":"c5a31ee81356e9fb9f9ceeef226443d51e2f834269ffd694cfded947595f62e8","abstract_canon_sha256":"091ae1b2a48e6256484b7ee0bcb2d71dd7ae2527a7a6c971e39f143c9e7ed26a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:49:58.474240Z","signature_b64":"NjEosLHWySwBOJB/vZDsSeJlMcTIgvHHZFAKeTh9lezz4RpF5nxpSXWZT2ovfiJEmFZp2aVtULA5IRTwkjb5CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"36d30912092adb5f6e96a0227a0735713e8f33c94ed9c352929e362bcdb5ac8c","last_reissued_at":"2026-05-18T03:49:58.473707Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:49:58.473707Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Divergence of Reinforcement Learning Algorithms with Value-Iteration and Function Approximation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Eduardo Alonso, Michael Fairbank","submitted_at":"2011-07-22T13:05:48Z","abstract_excerpt":"This paper gives specific divergence examples of value-iteration for several major Reinforcement Learning and Adaptive Dynamic Programming algorithms, when using a function approximator for the value function. These divergence examples differ from previous divergence examples in the literature, in that they are applicable for a greedy policy, i.e. in a \"value iteration\" scenario. Perhaps surprisingly, with a greedy policy, it is also possible to get divergence for the algorithms TD(1) and Sarsa(1). In addition to these divergences, we also achieve divergence for the Adaptive Dynamic Programmin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1107.4606","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1107.4606","created_at":"2026-05-18T03:49:58.473796+00:00"},{"alias_kind":"arxiv_version","alias_value":"1107.4606v2","created_at":"2026-05-18T03:49:58.473796+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1107.4606","created_at":"2026-05-18T03:49:58.473796+00:00"},{"alias_kind":"pith_short_12","alias_value":"G3JQSEQJFLNV","created_at":"2026-05-18T12:26:28.662955+00:00"},{"alias_kind":"pith_short_16","alias_value":"G3JQSEQJFLNV63UW","created_at":"2026-05-18T12:26:28.662955+00:00"},{"alias_kind":"pith_short_8","alias_value":"G3JQSEQJ","created_at":"2026-05-18T12:26:28.662955+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/G3JQSEQJFLNV63UWUARHUBZVOE","json":"https://pith.science/pith/G3JQSEQJFLNV63UWUARHUBZVOE.json","graph_json":"https://pith.science/api/pith-number/G3JQSEQJFLNV63UWUARHUBZVOE/graph.json","events_json":"https://pith.science/api/pith-number/G3JQSEQJFLNV63UWUARHUBZVOE/events.json","paper":"https://pith.science/paper/G3JQSEQJ"},"agent_actions":{"view_html":"https://pith.science/pith/G3JQSEQJFLNV63UWUARHUBZVOE","download_json":"https://pith.science/pith/G3JQSEQJFLNV63UWUARHUBZVOE.json","view_paper":"https://pith.science/paper/G3JQSEQJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1107.4606&json=true","fetch_graph":"https://pith.science/api/pith-number/G3JQSEQJFLNV63UWUARHUBZVOE/graph.json","fetch_events":"https://pith.science/api/pith-number/G3JQSEQJFLNV63UWUARHUBZVOE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/G3JQSEQJFLNV63UWUARHUBZVOE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/G3JQSEQJFLNV63UWUARHUBZVOE/action/storage_attestation","attest_author":"https://pith.science/pith/G3JQSEQJFLNV63UWUARHUBZVOE/action/author_attestation","sign_citation":"https://pith.science/pith/G3JQSEQJFLNV63UWUARHUBZVOE/action/citation_signature","submit_replication":"https://pith.science/pith/G3JQSEQJFLNV63UWUARHUBZVOE/action/replication_record"}},"created_at":"2026-05-18T03:49:58.473796+00:00","updated_at":"2026-05-18T03:49:58.473796+00:00"}