{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:XVWZDOG6V6PMQVMFA7MR7W4DQU","short_pith_number":"pith:XVWZDOG6","schema_version":"1.0","canonical_sha256":"bd6d91b8deaf9ec8558507d91fdb83850360a9e54b3633677273063a07fe9f83","source":{"kind":"arxiv","id":"2412.14002","version":1},"attestation_state":"computed","paper":{"title":"Operator Splitting for Convex Constrained Markov Decision Processes","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SY","eess.SY"],"primary_cat":"math.OC","authors_text":"Anastasios Tsiamis, John Lygeros, Panagiotis D. Grontas","submitted_at":"2024-12-18T16:17:25Z","abstract_excerpt":"We consider finite Markov decision processes (MDPs) with convex constraints and known dynamics. In principle, this problem is amenable to off-the-shelf convex optimization solvers, but typically this approach suffers from poor scalability. In this work, we develop a first-order algorithm, based on the Douglas-Rachford splitting, that allows us to decompose the dynamics and constraints. Thanks to this decoupling, we can incorporate a wide variety of convex constraints. Our scheme consists of simple and easy-to-implement updates that alternate between solving a regularized MDP and a projection. "},"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":"2412.14002","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2024-12-18T16:17:25Z","cross_cats_sorted":["cs.SY","eess.SY"],"title_canon_sha256":"fa4fdf25124ac7365e9a4785ea3b9821d540ec6ef75f0c4f9ac38c83adf01479","abstract_canon_sha256":"9035a6bb8ae1606e67c1e5a5bf50fdd9471d5803f236c3785f2cb067ff3774a2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:51:12.056879Z","signature_b64":"/ygRx0o2Wkr6LhN4123In2wEMId+VUneVPCgURqbhZpEOaS3guDGg1SKgro8QBqWP7/ZZsmAEwaYojxP80jqAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bd6d91b8deaf9ec8558507d91fdb83850360a9e54b3633677273063a07fe9f83","last_reissued_at":"2026-07-05T09:51:12.056331Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:51:12.056331Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Operator Splitting for Convex Constrained Markov Decision Processes","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SY","eess.SY"],"primary_cat":"math.OC","authors_text":"Anastasios Tsiamis, John Lygeros, Panagiotis D. Grontas","submitted_at":"2024-12-18T16:17:25Z","abstract_excerpt":"We consider finite Markov decision processes (MDPs) with convex constraints and known dynamics. In principle, this problem is amenable to off-the-shelf convex optimization solvers, but typically this approach suffers from poor scalability. In this work, we develop a first-order algorithm, based on the Douglas-Rachford splitting, that allows us to decompose the dynamics and constraints. Thanks to this decoupling, we can incorporate a wide variety of convex constraints. Our scheme consists of simple and easy-to-implement updates that alternate between solving a regularized MDP and a projection. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.14002","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2412.14002/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2412.14002","created_at":"2026-07-05T09:51:12.056406+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.14002v1","created_at":"2026-07-05T09:51:12.056406+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.14002","created_at":"2026-07-05T09:51:12.056406+00:00"},{"alias_kind":"pith_short_12","alias_value":"XVWZDOG6V6PM","created_at":"2026-07-05T09:51:12.056406+00:00"},{"alias_kind":"pith_short_16","alias_value":"XVWZDOG6V6PMQVMF","created_at":"2026-07-05T09:51:12.056406+00:00"},{"alias_kind":"pith_short_8","alias_value":"XVWZDOG6","created_at":"2026-07-05T09:51:12.056406+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.30829","citing_title":"Joint Chance Constrained Safe-Optimal Control","ref_index":18,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XVWZDOG6V6PMQVMFA7MR7W4DQU","json":"https://pith.science/pith/XVWZDOG6V6PMQVMFA7MR7W4DQU.json","graph_json":"https://pith.science/api/pith-number/XVWZDOG6V6PMQVMFA7MR7W4DQU/graph.json","events_json":"https://pith.science/api/pith-number/XVWZDOG6V6PMQVMFA7MR7W4DQU/events.json","paper":"https://pith.science/paper/XVWZDOG6"},"agent_actions":{"view_html":"https://pith.science/pith/XVWZDOG6V6PMQVMFA7MR7W4DQU","download_json":"https://pith.science/pith/XVWZDOG6V6PMQVMFA7MR7W4DQU.json","view_paper":"https://pith.science/paper/XVWZDOG6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.14002&json=true","fetch_graph":"https://pith.science/api/pith-number/XVWZDOG6V6PMQVMFA7MR7W4DQU/graph.json","fetch_events":"https://pith.science/api/pith-number/XVWZDOG6V6PMQVMFA7MR7W4DQU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XVWZDOG6V6PMQVMFA7MR7W4DQU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XVWZDOG6V6PMQVMFA7MR7W4DQU/action/storage_attestation","attest_author":"https://pith.science/pith/XVWZDOG6V6PMQVMFA7MR7W4DQU/action/author_attestation","sign_citation":"https://pith.science/pith/XVWZDOG6V6PMQVMFA7MR7W4DQU/action/citation_signature","submit_replication":"https://pith.science/pith/XVWZDOG6V6PMQVMFA7MR7W4DQU/action/replication_record"}},"created_at":"2026-07-05T09:51:12.056406+00:00","updated_at":"2026-07-05T09:51:12.056406+00:00"}