{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:JCV5HCJQFBZCYLGWSMGYY6CB5D","short_pith_number":"pith:JCV5HCJQ","canonical_record":{"source":{"id":"2406.18924","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-06-27T06:31:51Z","cross_cats_sorted":["cs.LG","cs.RO"],"title_canon_sha256":"2f69b0da5934a3073252730a04abc3b0a113a87fdd26acb027f7e27570aac092","abstract_canon_sha256":"c04bbfe3839906c5231de647690dda922625b687a34551d51e2a9b7bf9046e25"},"schema_version":"1.0"},"canonical_sha256":"48abd3893028722c2cd6930d8c7841e8d0516271b01ab4482660d62d66aee520","source":{"kind":"arxiv","id":"2406.18924","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.18924","created_at":"2026-07-05T08:37:27Z"},{"alias_kind":"arxiv_version","alias_value":"2406.18924v1","created_at":"2026-07-05T08:37:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.18924","created_at":"2026-07-05T08:37:27Z"},{"alias_kind":"pith_short_12","alias_value":"JCV5HCJQFBZC","created_at":"2026-07-05T08:37:27Z"},{"alias_kind":"pith_short_16","alias_value":"JCV5HCJQFBZCYLGW","created_at":"2026-07-05T08:37:27Z"},{"alias_kind":"pith_short_8","alias_value":"JCV5HCJQ","created_at":"2026-07-05T08:37:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:JCV5HCJQFBZCYLGWSMGYY6CB5D","target":"record","payload":{"canonical_record":{"source":{"id":"2406.18924","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-06-27T06:31:51Z","cross_cats_sorted":["cs.LG","cs.RO"],"title_canon_sha256":"2f69b0da5934a3073252730a04abc3b0a113a87fdd26acb027f7e27570aac092","abstract_canon_sha256":"c04bbfe3839906c5231de647690dda922625b687a34551d51e2a9b7bf9046e25"},"schema_version":"1.0"},"canonical_sha256":"48abd3893028722c2cd6930d8c7841e8d0516271b01ab4482660d62d66aee520","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:37:27.578852Z","signature_b64":"PLC7Q3gk2gcFWJJBPldqcg57ftd9vPrd/gM4kf/hwrR6NTG9eTZQSgBLfgp8uXTTLO8Bp+rQ+wkQa44qcq2xAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"48abd3893028722c2cd6930d8c7841e8d0516271b01ab4482660d62d66aee520","last_reissued_at":"2026-07-05T08:37:27.578386Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:37:27.578386Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.18924","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:37:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zUB8/wahflgasTF0C+289/XsjGYVlJLv2lkSz/koG+f1yXmjhlsu1DKhr+hpB0rBzuKTMOXeXZT2kMeDsgK9CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T11:17:54.818389Z"},"content_sha256":"09a5d49ce4bd657d6e788339af1faf4e8a42d23c57f32fd391059ebfdfa818be","schema_version":"1.0","event_id":"sha256:09a5d49ce4bd657d6e788339af1faf4e8a42d23c57f32fd391059ebfdfa818be"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:JCV5HCJQFBZCYLGWSMGYY6CB5D","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning Pareto Set for Multi-Objective Continuous Robot Control","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.RO"],"primary_cat":"cs.AI","authors_text":"Cheng Gong, Hisao Ishibuchi, Ke Shang, Tianye Shu, Yang Nan","submitted_at":"2024-06-27T06:31:51Z","abstract_excerpt":"For a control problem with multiple conflicting objectives, there exists a set of Pareto-optimal policies called the Pareto set instead of a single optimal policy. When a multi-objective control problem is continuous and complex, traditional multi-objective reinforcement learning (MORL) algorithms search for many Pareto-optimal deep policies to approximate the Pareto set, which is quite resource-consuming. In this paper, we propose a simple and resource-efficient MORL algorithm that learns a continuous representation of the Pareto set in a high-dimensional policy parameter space using a single"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.18924","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/2406.18924/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:37:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cGXABFTXgRKAc4Ip5nVbsKoI07HiZ6fmLgz5X1SI1YCMTuFlYnqca1BsoFllH530rSAZrSDqN4MJdDx+uzKtCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T11:17:54.820588Z"},"content_sha256":"83e35c49018d819173552ca4d0698289e82f7990df5f9a26071f1b649ba598d9","schema_version":"1.0","event_id":"sha256:83e35c49018d819173552ca4d0698289e82f7990df5f9a26071f1b649ba598d9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JCV5HCJQFBZCYLGWSMGYY6CB5D/bundle.json","state_url":"https://pith.science/pith/JCV5HCJQFBZCYLGWSMGYY6CB5D/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JCV5HCJQFBZCYLGWSMGYY6CB5D/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":"2026-08-10T11:17:54Z","links":{"resolver":"https://pith.science/pith/JCV5HCJQFBZCYLGWSMGYY6CB5D","bundle":"https://pith.science/pith/JCV5HCJQFBZCYLGWSMGYY6CB5D/bundle.json","state":"https://pith.science/pith/JCV5HCJQFBZCYLGWSMGYY6CB5D/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JCV5HCJQFBZCYLGWSMGYY6CB5D/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:JCV5HCJQFBZCYLGWSMGYY6CB5D","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":"c04bbfe3839906c5231de647690dda922625b687a34551d51e2a9b7bf9046e25","cross_cats_sorted":["cs.LG","cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-06-27T06:31:51Z","title_canon_sha256":"2f69b0da5934a3073252730a04abc3b0a113a87fdd26acb027f7e27570aac092"},"schema_version":"1.0","source":{"id":"2406.18924","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.18924","created_at":"2026-07-05T08:37:27Z"},{"alias_kind":"arxiv_version","alias_value":"2406.18924v1","created_at":"2026-07-05T08:37:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.18924","created_at":"2026-07-05T08:37:27Z"},{"alias_kind":"pith_short_12","alias_value":"JCV5HCJQFBZC","created_at":"2026-07-05T08:37:27Z"},{"alias_kind":"pith_short_16","alias_value":"JCV5HCJQFBZCYLGW","created_at":"2026-07-05T08:37:27Z"},{"alias_kind":"pith_short_8","alias_value":"JCV5HCJQ","created_at":"2026-07-05T08:37:27Z"}],"graph_snapshots":[{"event_id":"sha256:83e35c49018d819173552ca4d0698289e82f7990df5f9a26071f1b649ba598d9","target":"graph","created_at":"2026-07-05T08:37:27Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2406.18924/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"For a control problem with multiple conflicting objectives, there exists a set of Pareto-optimal policies called the Pareto set instead of a single optimal policy. When a multi-objective control problem is continuous and complex, traditional multi-objective reinforcement learning (MORL) algorithms search for many Pareto-optimal deep policies to approximate the Pareto set, which is quite resource-consuming. In this paper, we propose a simple and resource-efficient MORL algorithm that learns a continuous representation of the Pareto set in a high-dimensional policy parameter space using a single","authors_text":"Cheng Gong, Hisao Ishibuchi, Ke Shang, Tianye Shu, Yang Nan","cross_cats":["cs.LG","cs.RO"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-06-27T06:31:51Z","title":"Learning Pareto Set for Multi-Objective Continuous Robot Control"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.18924","kind":"arxiv","version":1},"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":"sha256:09a5d49ce4bd657d6e788339af1faf4e8a42d23c57f32fd391059ebfdfa818be","target":"record","created_at":"2026-07-05T08:37:27Z","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":"c04bbfe3839906c5231de647690dda922625b687a34551d51e2a9b7bf9046e25","cross_cats_sorted":["cs.LG","cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-06-27T06:31:51Z","title_canon_sha256":"2f69b0da5934a3073252730a04abc3b0a113a87fdd26acb027f7e27570aac092"},"schema_version":"1.0","source":{"id":"2406.18924","kind":"arxiv","version":1}},"canonical_sha256":"48abd3893028722c2cd6930d8c7841e8d0516271b01ab4482660d62d66aee520","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"48abd3893028722c2cd6930d8c7841e8d0516271b01ab4482660d62d66aee520","first_computed_at":"2026-07-05T08:37:27.578386Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:37:27.578386Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PLC7Q3gk2gcFWJJBPldqcg57ftd9vPrd/gM4kf/hwrR6NTG9eTZQSgBLfgp8uXTTLO8Bp+rQ+wkQa44qcq2xAA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:37:27.578852Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.18924","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:09a5d49ce4bd657d6e788339af1faf4e8a42d23c57f32fd391059ebfdfa818be","sha256:83e35c49018d819173552ca4d0698289e82f7990df5f9a26071f1b649ba598d9"],"state_sha256":"a2102b5a570e62c94bd4f6e764b8e3023a256b1e3020a0649a7031f0ada7e582"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"R4Jf/2/YVr1SBgnDfYuVX3/UWBAL8dvDstPc3OHZMkelzrOzNoPCeEkmSAGapR/ItJNzlri7pDVLwuBMUqvQCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T11:17:54.827557Z","bundle_sha256":"85b5af289cf0517a516f73262f1e69185f6d757b724f739e34986e45b42b7a7f"}}