{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:AESDKJEGSWEKHTLMUSINRQ3J6Z","short_pith_number":"pith:AESDKJEG","schema_version":"1.0","canonical_sha256":"01243524869588a3cd6ca490d8c369f67873b2dccd896aef5e2369b513b4947d","source":{"kind":"arxiv","id":"1704.00621","version":1},"attestation_state":"computed","paper":{"title":"Computing monotone policies for Markov decision processes: a nearly-isotonic penalty approach","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SY","authors_text":"Bo Wahlberg, Cristian R. Rojas, Robert Mattila, Vikram Krishnamurthy","submitted_at":"2017-04-03T14:40:58Z","abstract_excerpt":"This paper discusses algorithms for solving Markov decision processes (MDPs) that have monotone optimal policies. We propose a two-stage alternating convex optimization scheme that can accelerate the search for an optimal policy by exploiting the monotone property. The first stage is a linear program formulated in terms of the joint state-action probabilities. The second stage is a regularized problem formulated in terms of the conditional probabilities of actions given states. The regularization uses techniques from nearly-isotonic regression. While a variety of iterative method can be used i"},"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":"1704.00621","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SY","submitted_at":"2017-04-03T14:40:58Z","cross_cats_sorted":[],"title_canon_sha256":"00aca284355ebd8485289862cc9776d8dbe056e9a1ca00c3db75cbd4b1352319","abstract_canon_sha256":"d8130d276a0ab22b59f324b02f98229bf21ab3e0b5e4f59434208567129a51db"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:47:21.826466Z","signature_b64":"p/vrHAKfplLZnx04Ys1T6jsnvpezbomLiZJipRyVLyavdOKqS3yswyravo75lQO0aUOb0eacqYhV7SDPtbT8AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"01243524869588a3cd6ca490d8c369f67873b2dccd896aef5e2369b513b4947d","last_reissued_at":"2026-05-18T00:47:21.825991Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:47:21.825991Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Computing monotone policies for Markov decision processes: a nearly-isotonic penalty approach","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SY","authors_text":"Bo Wahlberg, Cristian R. Rojas, Robert Mattila, Vikram Krishnamurthy","submitted_at":"2017-04-03T14:40:58Z","abstract_excerpt":"This paper discusses algorithms for solving Markov decision processes (MDPs) that have monotone optimal policies. We propose a two-stage alternating convex optimization scheme that can accelerate the search for an optimal policy by exploiting the monotone property. The first stage is a linear program formulated in terms of the joint state-action probabilities. The second stage is a regularized problem formulated in terms of the conditional probabilities of actions given states. The regularization uses techniques from nearly-isotonic regression. While a variety of iterative method can be used i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1704.00621","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":"1704.00621","created_at":"2026-05-18T00:47:21.826060+00:00"},{"alias_kind":"arxiv_version","alias_value":"1704.00621v1","created_at":"2026-05-18T00:47:21.826060+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1704.00621","created_at":"2026-05-18T00:47:21.826060+00:00"},{"alias_kind":"pith_short_12","alias_value":"AESDKJEGSWEK","created_at":"2026-05-18T12:31:05.417338+00:00"},{"alias_kind":"pith_short_16","alias_value":"AESDKJEGSWEKHTLM","created_at":"2026-05-18T12:31:05.417338+00:00"},{"alias_kind":"pith_short_8","alias_value":"AESDKJEG","created_at":"2026-05-18T12:31:05.417338+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/AESDKJEGSWEKHTLMUSINRQ3J6Z","json":"https://pith.science/pith/AESDKJEGSWEKHTLMUSINRQ3J6Z.json","graph_json":"https://pith.science/api/pith-number/AESDKJEGSWEKHTLMUSINRQ3J6Z/graph.json","events_json":"https://pith.science/api/pith-number/AESDKJEGSWEKHTLMUSINRQ3J6Z/events.json","paper":"https://pith.science/paper/AESDKJEG"},"agent_actions":{"view_html":"https://pith.science/pith/AESDKJEGSWEKHTLMUSINRQ3J6Z","download_json":"https://pith.science/pith/AESDKJEGSWEKHTLMUSINRQ3J6Z.json","view_paper":"https://pith.science/paper/AESDKJEG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1704.00621&json=true","fetch_graph":"https://pith.science/api/pith-number/AESDKJEGSWEKHTLMUSINRQ3J6Z/graph.json","fetch_events":"https://pith.science/api/pith-number/AESDKJEGSWEKHTLMUSINRQ3J6Z/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AESDKJEGSWEKHTLMUSINRQ3J6Z/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AESDKJEGSWEKHTLMUSINRQ3J6Z/action/storage_attestation","attest_author":"https://pith.science/pith/AESDKJEGSWEKHTLMUSINRQ3J6Z/action/author_attestation","sign_citation":"https://pith.science/pith/AESDKJEGSWEKHTLMUSINRQ3J6Z/action/citation_signature","submit_replication":"https://pith.science/pith/AESDKJEGSWEKHTLMUSINRQ3J6Z/action/replication_record"}},"created_at":"2026-05-18T00:47:21.826060+00:00","updated_at":"2026-05-18T00:47:21.826060+00:00"}