{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:DJVUNF7OLQTCVEDYUL7Y2MALFP","short_pith_number":"pith:DJVUNF7O","schema_version":"1.0","canonical_sha256":"1a6b4697ee5c262a9078a2ff8d300b2bcd441e3523f0fc7d4486132c70afce6c","source":{"kind":"arxiv","id":"1805.00869","version":1},"attestation_state":"computed","paper":{"title":"Approximate Temporal Difference Learning is a Gradient Descent for Reversible Policies","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Yann Ollivier","submitted_at":"2018-05-02T15:40:24Z","abstract_excerpt":"In reinforcement learning, temporal difference (TD) is the most direct algorithm to learn the value function of a policy. For large or infinite state spaces, exact representations of the value function are usually not available, and it must be approximated by a function in some parametric family.\n  However, with \\emph{nonlinear} parametric approximations (such as neural networks), TD is not guaranteed to converge to a good approximation of the true value function within the family, and is known to diverge even in relatively simple cases. TD lacks an interpretation as a stochastic gradient desc"},"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":"1805.00869","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-02T15:40:24Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"34d309dd2936a519583c04c3fbb4b6060c460c2c3c785d3e4fb415a12649bbbd","abstract_canon_sha256":"a77d88c4da8fb0cb298bad55271aa28ff348443772b34f5afa6987d34a370ede"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:16:57.412919Z","signature_b64":"auK3RBR//U4U6qXufEYZUskv2PeTdv5kvUK4xQYawmnD0cqdGCEn+bSeFjPwvh1/xTLC2VvRXOCnj8xShx7sDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1a6b4697ee5c262a9078a2ff8d300b2bcd441e3523f0fc7d4486132c70afce6c","last_reissued_at":"2026-05-18T00:16:57.412249Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:16:57.412249Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Approximate Temporal Difference Learning is a Gradient Descent for Reversible Policies","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Yann Ollivier","submitted_at":"2018-05-02T15:40:24Z","abstract_excerpt":"In reinforcement learning, temporal difference (TD) is the most direct algorithm to learn the value function of a policy. For large or infinite state spaces, exact representations of the value function are usually not available, and it must be approximated by a function in some parametric family.\n  However, with \\emph{nonlinear} parametric approximations (such as neural networks), TD is not guaranteed to converge to a good approximation of the true value function within the family, and is known to diverge even in relatively simple cases. TD lacks an interpretation as a stochastic gradient desc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.00869","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":""},"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":"1805.00869","created_at":"2026-05-18T00:16:57.412359+00:00"},{"alias_kind":"arxiv_version","alias_value":"1805.00869v1","created_at":"2026-05-18T00:16:57.412359+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.00869","created_at":"2026-05-18T00:16:57.412359+00:00"},{"alias_kind":"pith_short_12","alias_value":"DJVUNF7OLQTC","created_at":"2026-05-18T12:32:19.392346+00:00"},{"alias_kind":"pith_short_16","alias_value":"DJVUNF7OLQTCVEDY","created_at":"2026-05-18T12:32:19.392346+00:00"},{"alias_kind":"pith_short_8","alias_value":"DJVUNF7O","created_at":"2026-05-18T12:32:19.392346+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.02103","citing_title":"Bridging the Gap Between Average and Discounted TD Learning","ref_index":23,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DJVUNF7OLQTCVEDYUL7Y2MALFP","json":"https://pith.science/pith/DJVUNF7OLQTCVEDYUL7Y2MALFP.json","graph_json":"https://pith.science/api/pith-number/DJVUNF7OLQTCVEDYUL7Y2MALFP/graph.json","events_json":"https://pith.science/api/pith-number/DJVUNF7OLQTCVEDYUL7Y2MALFP/events.json","paper":"https://pith.science/paper/DJVUNF7O"},"agent_actions":{"view_html":"https://pith.science/pith/DJVUNF7OLQTCVEDYUL7Y2MALFP","download_json":"https://pith.science/pith/DJVUNF7OLQTCVEDYUL7Y2MALFP.json","view_paper":"https://pith.science/paper/DJVUNF7O","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1805.00869&json=true","fetch_graph":"https://pith.science/api/pith-number/DJVUNF7OLQTCVEDYUL7Y2MALFP/graph.json","fetch_events":"https://pith.science/api/pith-number/DJVUNF7OLQTCVEDYUL7Y2MALFP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DJVUNF7OLQTCVEDYUL7Y2MALFP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DJVUNF7OLQTCVEDYUL7Y2MALFP/action/storage_attestation","attest_author":"https://pith.science/pith/DJVUNF7OLQTCVEDYUL7Y2MALFP/action/author_attestation","sign_citation":"https://pith.science/pith/DJVUNF7OLQTCVEDYUL7Y2MALFP/action/citation_signature","submit_replication":"https://pith.science/pith/DJVUNF7OLQTCVEDYUL7Y2MALFP/action/replication_record"}},"created_at":"2026-05-18T00:16:57.412359+00:00","updated_at":"2026-05-18T00:16:57.412359+00:00"}