{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2014:DT67K6S2FX4N5KVKF2ZANLD6IK","short_pith_number":"pith:DT67K6S2","schema_version":"1.0","canonical_sha256":"1cfdf57a5a2df8deaaaa2eb206ac7e4288c6cf73b88c1cfb27e841a1eb524b0a","source":{"kind":"arxiv","id":"1406.3497","version":2},"attestation_state":"computed","paper":{"title":"Multi-objective Reinforcement Learning with Continuous Pareto Frontier Approximation Supplementary Material","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Marcello Restelli, Matteo Pirotta, Simone Parisi","submitted_at":"2014-06-13T10:49:38Z","abstract_excerpt":"This document contains supplementary material for the paper \"Multi-objective Reinforcement Learning with Continuous Pareto Frontier Approximation\", published at the Twenty-Ninth AAAI Conference on Artificial Intelligence (AAAI-15). The paper is about learning a continuous approximation of the Pareto frontier in Multi-Objective Markov Decision Problems (MOMDPs). We propose a policy-based approach that exploits gradient information to generate solutions close to the Pareto ones. Differently from previous policy-gradient multi-objective algorithms, where n optimization routines are use to have n "},"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":"1406.3497","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2014-06-13T10:49:38Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"f48ca193608b453b8a7a7a8322efad41fde96f91d5250be7b2a572a1280965e0","abstract_canon_sha256":"b45d6c16e3ba62052ed4f9fe6cf326bd5eec7eeaac66027f8b19d710689cc705"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:34:44.871128Z","signature_b64":"ePRXdvfgnnIcJeQiEaWQuBrIhKvcBsAROTU8/EW5AJ1N6J9le2Q2mbQRrsN3wK88OLiUNwn9fNACwk+jVPuMBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1cfdf57a5a2df8deaaaa2eb206ac7e4288c6cf73b88c1cfb27e841a1eb524b0a","last_reissued_at":"2026-05-18T02:34:44.870738Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:34:44.870738Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-objective Reinforcement Learning with Continuous Pareto Frontier Approximation Supplementary Material","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Marcello Restelli, Matteo Pirotta, Simone Parisi","submitted_at":"2014-06-13T10:49:38Z","abstract_excerpt":"This document contains supplementary material for the paper \"Multi-objective Reinforcement Learning with Continuous Pareto Frontier Approximation\", published at the Twenty-Ninth AAAI Conference on Artificial Intelligence (AAAI-15). The paper is about learning a continuous approximation of the Pareto frontier in Multi-Objective Markov Decision Problems (MOMDPs). We propose a policy-based approach that exploits gradient information to generate solutions close to the Pareto ones. Differently from previous policy-gradient multi-objective algorithms, where n optimization routines are use to have n "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1406.3497","kind":"arxiv","version":2},"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":"1406.3497","created_at":"2026-05-18T02:34:44.870801+00:00"},{"alias_kind":"arxiv_version","alias_value":"1406.3497v2","created_at":"2026-05-18T02:34:44.870801+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1406.3497","created_at":"2026-05-18T02:34:44.870801+00:00"},{"alias_kind":"pith_short_12","alias_value":"DT67K6S2FX4N","created_at":"2026-05-18T12:28:25.294606+00:00"},{"alias_kind":"pith_short_16","alias_value":"DT67K6S2FX4N5KVK","created_at":"2026-05-18T12:28:25.294606+00:00"},{"alias_kind":"pith_short_8","alias_value":"DT67K6S2","created_at":"2026-05-18T12:28:25.294606+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/DT67K6S2FX4N5KVKF2ZANLD6IK","json":"https://pith.science/pith/DT67K6S2FX4N5KVKF2ZANLD6IK.json","graph_json":"https://pith.science/api/pith-number/DT67K6S2FX4N5KVKF2ZANLD6IK/graph.json","events_json":"https://pith.science/api/pith-number/DT67K6S2FX4N5KVKF2ZANLD6IK/events.json","paper":"https://pith.science/paper/DT67K6S2"},"agent_actions":{"view_html":"https://pith.science/pith/DT67K6S2FX4N5KVKF2ZANLD6IK","download_json":"https://pith.science/pith/DT67K6S2FX4N5KVKF2ZANLD6IK.json","view_paper":"https://pith.science/paper/DT67K6S2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1406.3497&json=true","fetch_graph":"https://pith.science/api/pith-number/DT67K6S2FX4N5KVKF2ZANLD6IK/graph.json","fetch_events":"https://pith.science/api/pith-number/DT67K6S2FX4N5KVKF2ZANLD6IK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DT67K6S2FX4N5KVKF2ZANLD6IK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DT67K6S2FX4N5KVKF2ZANLD6IK/action/storage_attestation","attest_author":"https://pith.science/pith/DT67K6S2FX4N5KVKF2ZANLD6IK/action/author_attestation","sign_citation":"https://pith.science/pith/DT67K6S2FX4N5KVKF2ZANLD6IK/action/citation_signature","submit_replication":"https://pith.science/pith/DT67K6S2FX4N5KVKF2ZANLD6IK/action/replication_record"}},"created_at":"2026-05-18T02:34:44.870801+00:00","updated_at":"2026-05-18T02:34:44.870801+00:00"}