{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:RVHDCYU5JF5WT42DSQK4MHMAJT","short_pith_number":"pith:RVHDCYU5","schema_version":"1.0","canonical_sha256":"8d4e31629d497b69f3439415c61d804cf34ec5c3e832aec8ed645f71b790524d","source":{"kind":"arxiv","id":"1804.07323","version":1},"attestation_state":"computed","paper":{"title":"Nonparametric Stochastic Compositional Gradient Descent for Q-Learning in Continuous Markov Decision Problems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SY","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alec Koppel, Alejandro Ribeiro, Ekaterina Tolstaya, Ethan Stump","submitted_at":"2018-04-19T18:24:18Z","abstract_excerpt":"We consider Markov Decision Problems defined over continuous state and action spaces, where an autonomous agent seeks to learn a map from its states to actions so as to maximize its long-term discounted accumulation of rewards. We address this problem by considering Bellman's optimality equation defined over action-value functions, which we reformulate into a nested non-convex stochastic optimization problem defined over a Reproducing Kernel Hilbert Space (RKHS). We develop a functional generalization of stochastic quasi-gradient method to solve it, which, owing to the structure of the RKHS, a"},"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":"1804.07323","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-04-19T18:24:18Z","cross_cats_sorted":["cs.SY","stat.ML"],"title_canon_sha256":"a587e227ddefad2d0e9fbbf07b4f83e42edc86cebffa0bedc53a9578d8e7847e","abstract_canon_sha256":"22da1d4e5816927b2c40c870ee754a969924b9436fc2d1d9d5792f7da37764a6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:17:59.159685Z","signature_b64":"cyjDx/M6kO+kIaTPvfgv3sS6AKlb/Hbe2EG3SPGwhymFhvzA0VudTO4PgZCus06jeCbOKpcbNAuU0W1In/dJBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8d4e31629d497b69f3439415c61d804cf34ec5c3e832aec8ed645f71b790524d","last_reissued_at":"2026-05-18T00:17:59.158995Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:17:59.158995Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Nonparametric Stochastic Compositional Gradient Descent for Q-Learning in Continuous Markov Decision Problems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SY","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alec Koppel, Alejandro Ribeiro, Ekaterina Tolstaya, Ethan Stump","submitted_at":"2018-04-19T18:24:18Z","abstract_excerpt":"We consider Markov Decision Problems defined over continuous state and action spaces, where an autonomous agent seeks to learn a map from its states to actions so as to maximize its long-term discounted accumulation of rewards. We address this problem by considering Bellman's optimality equation defined over action-value functions, which we reformulate into a nested non-convex stochastic optimization problem defined over a Reproducing Kernel Hilbert Space (RKHS). We develop a functional generalization of stochastic quasi-gradient method to solve it, which, owing to the structure of the RKHS, a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.07323","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":"1804.07323","created_at":"2026-05-18T00:17:59.159113+00:00"},{"alias_kind":"arxiv_version","alias_value":"1804.07323v1","created_at":"2026-05-18T00:17:59.159113+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.07323","created_at":"2026-05-18T00:17:59.159113+00:00"},{"alias_kind":"pith_short_12","alias_value":"RVHDCYU5JF5W","created_at":"2026-05-18T12:32:50.500415+00:00"},{"alias_kind":"pith_short_16","alias_value":"RVHDCYU5JF5WT42D","created_at":"2026-05-18T12:32:50.500415+00:00"},{"alias_kind":"pith_short_8","alias_value":"RVHDCYU5","created_at":"2026-05-18T12:32:50.500415+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/RVHDCYU5JF5WT42DSQK4MHMAJT","json":"https://pith.science/pith/RVHDCYU5JF5WT42DSQK4MHMAJT.json","graph_json":"https://pith.science/api/pith-number/RVHDCYU5JF5WT42DSQK4MHMAJT/graph.json","events_json":"https://pith.science/api/pith-number/RVHDCYU5JF5WT42DSQK4MHMAJT/events.json","paper":"https://pith.science/paper/RVHDCYU5"},"agent_actions":{"view_html":"https://pith.science/pith/RVHDCYU5JF5WT42DSQK4MHMAJT","download_json":"https://pith.science/pith/RVHDCYU5JF5WT42DSQK4MHMAJT.json","view_paper":"https://pith.science/paper/RVHDCYU5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1804.07323&json=true","fetch_graph":"https://pith.science/api/pith-number/RVHDCYU5JF5WT42DSQK4MHMAJT/graph.json","fetch_events":"https://pith.science/api/pith-number/RVHDCYU5JF5WT42DSQK4MHMAJT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RVHDCYU5JF5WT42DSQK4MHMAJT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RVHDCYU5JF5WT42DSQK4MHMAJT/action/storage_attestation","attest_author":"https://pith.science/pith/RVHDCYU5JF5WT42DSQK4MHMAJT/action/author_attestation","sign_citation":"https://pith.science/pith/RVHDCYU5JF5WT42DSQK4MHMAJT/action/citation_signature","submit_replication":"https://pith.science/pith/RVHDCYU5JF5WT42DSQK4MHMAJT/action/replication_record"}},"created_at":"2026-05-18T00:17:59.159113+00:00","updated_at":"2026-05-18T00:17:59.159113+00:00"}