{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2014:2BYMIE6MHEDY6GKSSOGJIWG4XU","short_pith_number":"pith:2BYMIE6M","schema_version":"1.0","canonical_sha256":"d070c413cc39078f1952938c9458dcbd2dca8c16c74a4ac05f26217c9d6498b7","source":{"kind":"arxiv","id":"1405.6757","version":1},"attestation_state":"computed","paper":{"title":"Proximal Reinforcement Learning: A New Theory of Sequential Decision Making in Primal-Dual Spaces","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bo Liu, Ian Gemp, Ji Liu, Nicholas Jacek, Philip Thomas, Sridhar Mahadevan, Steve Giguere, Will Dabney","submitted_at":"2014-05-26T23:11:40Z","abstract_excerpt":"In this paper, we set forth a new vision of reinforcement learning developed by us over the past few years, one that yields mathematically rigorous solutions to longstanding important questions that have remained unresolved: (i) how to design reliable, convergent, and robust reinforcement learning algorithms (ii) how to guarantee that reinforcement learning satisfies pre-specified \"safety\" guarantees, and remains in a stable region of the parameter space (iii) how to design \"off-policy\" temporal difference learning algorithms in a reliable and stable manner, and finally (iv) how to integrate t"},"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":"1405.6757","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2014-05-26T23:11:40Z","cross_cats_sorted":[],"title_canon_sha256":"ce9944de280a2346d6f7dde493aa106800a9d884825631732fb39c8abdbf73a5","abstract_canon_sha256":"560dc58191616637ccfb02773df3ec6d110a7363240a447df32793003141c985"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:51:00.401359Z","signature_b64":"2rA5lVA6Wb39CV0Wv19caFyCoCT2kePkAGfiHZDAYH03atpPsY0mbXQxpKkKLQdjQzEvsazc0f/cBQ3lEy2FDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d070c413cc39078f1952938c9458dcbd2dca8c16c74a4ac05f26217c9d6498b7","last_reissued_at":"2026-05-18T02:51:00.400703Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:51:00.400703Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Proximal Reinforcement Learning: A New Theory of Sequential Decision Making in Primal-Dual Spaces","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bo Liu, Ian Gemp, Ji Liu, Nicholas Jacek, Philip Thomas, Sridhar Mahadevan, Steve Giguere, Will Dabney","submitted_at":"2014-05-26T23:11:40Z","abstract_excerpt":"In this paper, we set forth a new vision of reinforcement learning developed by us over the past few years, one that yields mathematically rigorous solutions to longstanding important questions that have remained unresolved: (i) how to design reliable, convergent, and robust reinforcement learning algorithms (ii) how to guarantee that reinforcement learning satisfies pre-specified \"safety\" guarantees, and remains in a stable region of the parameter space (iii) how to design \"off-policy\" temporal difference learning algorithms in a reliable and stable manner, and finally (iv) how to integrate t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1405.6757","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":"1405.6757","created_at":"2026-05-18T02:51:00.400811+00:00"},{"alias_kind":"arxiv_version","alias_value":"1405.6757v1","created_at":"2026-05-18T02:51:00.400811+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1405.6757","created_at":"2026-05-18T02:51:00.400811+00:00"},{"alias_kind":"pith_short_12","alias_value":"2BYMIE6MHEDY","created_at":"2026-05-18T12:28:09.283467+00:00"},{"alias_kind":"pith_short_16","alias_value":"2BYMIE6MHEDY6GKS","created_at":"2026-05-18T12:28:09.283467+00:00"},{"alias_kind":"pith_short_8","alias_value":"2BYMIE6M","created_at":"2026-05-18T12:28:09.283467+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1907.04214","citing_title":"Entropic Regularization of Markov Decision Processes","ref_index":48,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2BYMIE6MHEDY6GKSSOGJIWG4XU","json":"https://pith.science/pith/2BYMIE6MHEDY6GKSSOGJIWG4XU.json","graph_json":"https://pith.science/api/pith-number/2BYMIE6MHEDY6GKSSOGJIWG4XU/graph.json","events_json":"https://pith.science/api/pith-number/2BYMIE6MHEDY6GKSSOGJIWG4XU/events.json","paper":"https://pith.science/paper/2BYMIE6M"},"agent_actions":{"view_html":"https://pith.science/pith/2BYMIE6MHEDY6GKSSOGJIWG4XU","download_json":"https://pith.science/pith/2BYMIE6MHEDY6GKSSOGJIWG4XU.json","view_paper":"https://pith.science/paper/2BYMIE6M","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1405.6757&json=true","fetch_graph":"https://pith.science/api/pith-number/2BYMIE6MHEDY6GKSSOGJIWG4XU/graph.json","fetch_events":"https://pith.science/api/pith-number/2BYMIE6MHEDY6GKSSOGJIWG4XU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2BYMIE6MHEDY6GKSSOGJIWG4XU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2BYMIE6MHEDY6GKSSOGJIWG4XU/action/storage_attestation","attest_author":"https://pith.science/pith/2BYMIE6MHEDY6GKSSOGJIWG4XU/action/author_attestation","sign_citation":"https://pith.science/pith/2BYMIE6MHEDY6GKSSOGJIWG4XU/action/citation_signature","submit_replication":"https://pith.science/pith/2BYMIE6MHEDY6GKSSOGJIWG4XU/action/replication_record"}},"created_at":"2026-05-18T02:51:00.400811+00:00","updated_at":"2026-05-18T02:51:00.400811+00:00"}