{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2014:DT67K6S2FX4N5KVKF2ZANLD6IK","short_pith_number":"pith:DT67K6S2","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"},"canonical_sha256":"1cfdf57a5a2df8deaaaa2eb206ac7e4288c6cf73b88c1cfb27e841a1eb524b0a","source":{"kind":"arxiv","id":"1406.3497","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2014:DT67K6S2FX4N5KVKF2ZANLD6IK","target":"record","payload":{"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"},"canonical_sha256":"1cfdf57a5a2df8deaaaa2eb206ac7e4288c6cf73b88c1cfb27e841a1eb524b0a","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"},"source_kind":"arxiv","source_id":"1406.3497","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T02:34:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"beRIddNzSioOmpPQqvXXy/teNLOv1Ma83YzMP1M/BnQPVmWT3+02Xet3rXO3yY9TXYup7SVpGjt+u66/0SacBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-28T15:37:24.106964Z"},"content_sha256":"17c2e3776f1fda11d874387820d78e07ac8ee2ed83747d4d274dd5a134343b74","schema_version":"1.0","event_id":"sha256:17c2e3776f1fda11d874387820d78e07ac8ee2ed83747d4d274dd5a134343b74"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2014:DT67K6S2FX4N5KVKF2ZANLD6IK","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T02:34:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5uTcLGyhonE9pya3QO9eh4b0eEsFhfA6ge7e7/n2l+xxyx22ByMUY2YL02A8p75g0+CTUqFvAY3Wr+ThuxJQBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-28T15:37:24.107302Z"},"content_sha256":"94d5f0df78d567b6752040e939a2294ac022a502ac0882e031d05010e8023f37","schema_version":"1.0","event_id":"sha256:94d5f0df78d567b6752040e939a2294ac022a502ac0882e031d05010e8023f37"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DT67K6S2FX4N5KVKF2ZANLD6IK/bundle.json","state_url":"https://pith.science/pith/DT67K6S2FX4N5KVKF2ZANLD6IK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DT67K6S2FX4N5KVKF2ZANLD6IK/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-28T15:37:24Z","links":{"resolver":"https://pith.science/pith/DT67K6S2FX4N5KVKF2ZANLD6IK","bundle":"https://pith.science/pith/DT67K6S2FX4N5KVKF2ZANLD6IK/bundle.json","state":"https://pith.science/pith/DT67K6S2FX4N5KVKF2ZANLD6IK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DT67K6S2FX4N5KVKF2ZANLD6IK/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rDIqJbyoB+fKETJaBd0gjaSTZd5GpLUjgXLQndL7MIpC/sQr0r/DrC+1cGW070daMKbyO1y+24mk3HjmmujFCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-28T15:37:24.109275Z","bundle_sha256":"535c6387bef2867b6c6cb1b2e2be4add10fe87a0ce2369d30c2b4f0d07e33dda"}}