{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2014:DT67K6S2FX4N5KVKF2ZANLD6IK","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"b45d6c16e3ba62052ed4f9fe6cf326bd5eec7eeaac66027f8b19d710689cc705","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2014-06-13T10:49:38Z","title_canon_sha256":"f48ca193608b453b8a7a7a8322efad41fde96f91d5250be7b2a572a1280965e0"},"schema_version":"1.0","source":{"id":"1406.3497","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1406.3497","created_at":"2026-05-18T02:34:44Z"},{"alias_kind":"arxiv_version","alias_value":"1406.3497v2","created_at":"2026-05-18T02:34:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1406.3497","created_at":"2026-05-18T02:34:44Z"},{"alias_kind":"pith_short_12","alias_value":"DT67K6S2FX4N","created_at":"2026-05-18T12:28:25Z"},{"alias_kind":"pith_short_16","alias_value":"DT67K6S2FX4N5KVK","created_at":"2026-05-18T12:28:25Z"},{"alias_kind":"pith_short_8","alias_value":"DT67K6S2","created_at":"2026-05-18T12:28:25Z"}],"graph_snapshots":[{"event_id":"sha256:94d5f0df78d567b6752040e939a2294ac022a502ac0882e031d05010e8023f37","target":"graph","created_at":"2026-05-18T02:34:44Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"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 ","authors_text":"Marcello Restelli, Matteo Pirotta, Simone Parisi","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2014-06-13T10:49:38Z","title":"Multi-objective Reinforcement Learning with Continuous Pareto Frontier Approximation Supplementary Material"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1406.3497","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:17c2e3776f1fda11d874387820d78e07ac8ee2ed83747d4d274dd5a134343b74","target":"record","created_at":"2026-05-18T02:34:44Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"b45d6c16e3ba62052ed4f9fe6cf326bd5eec7eeaac66027f8b19d710689cc705","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2014-06-13T10:49:38Z","title_canon_sha256":"f48ca193608b453b8a7a7a8322efad41fde96f91d5250be7b2a572a1280965e0"},"schema_version":"1.0","source":{"id":"1406.3497","kind":"arxiv","version":2}},"canonical_sha256":"1cfdf57a5a2df8deaaaa2eb206ac7e4288c6cf73b88c1cfb27e841a1eb524b0a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1cfdf57a5a2df8deaaaa2eb206ac7e4288c6cf73b88c1cfb27e841a1eb524b0a","first_computed_at":"2026-05-18T02:34:44.870738Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T02:34:44.870738Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ePRXdvfgnnIcJeQiEaWQuBrIhKvcBsAROTU8/EW5AJ1N6J9le2Q2mbQRrsN3wK88OLiUNwn9fNACwk+jVPuMBA==","signature_status":"signed_v1","signed_at":"2026-05-18T02:34:44.871128Z","signed_message":"canonical_sha256_bytes"},"source_id":"1406.3497","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:17c2e3776f1fda11d874387820d78e07ac8ee2ed83747d4d274dd5a134343b74","sha256:94d5f0df78d567b6752040e939a2294ac022a502ac0882e031d05010e8023f37"],"state_sha256":"b078213c01a7e07f350ddde316c4ac86ad3228cdd6e88d2ff3a2827006b5cb74"}