{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:Y5C4OFTEQN3FGYJEOHY42G6KKJ","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":"06b514c58b40e56bb5c53a0a1cd8e145e548b43f074e29b588302e2dfe497e5c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-25T05:57:46Z","title_canon_sha256":"914df82fb24e02ccd392b0a1ddbf47cc244a0a5e9744440eb1731789591a4a38"},"schema_version":"1.0","source":{"id":"2405.16077","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.16077","created_at":"2026-07-05T09:52:38Z"},{"alias_kind":"arxiv_version","alias_value":"2405.16077v3","created_at":"2026-07-05T09:52:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.16077","created_at":"2026-07-05T09:52:38Z"},{"alias_kind":"pith_short_12","alias_value":"Y5C4OFTEQN3F","created_at":"2026-07-05T09:52:38Z"},{"alias_kind":"pith_short_16","alias_value":"Y5C4OFTEQN3FGYJE","created_at":"2026-07-05T09:52:38Z"},{"alias_kind":"pith_short_8","alias_value":"Y5C4OFTE","created_at":"2026-07-05T09:52:38Z"}],"graph_snapshots":[{"event_id":"sha256:6d3aa1a48ff2b752d9d80177066f5cedb2fe9f544fcf5445899a413186251878","target":"graph","created_at":"2026-07-05T09:52:38Z","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/2405.16077/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multi-task reinforcement learning (MTRL) has shown great promise in many real-world applications. Existing MTRL algorithms often aim to learn a policy that optimizes individual objective functions simultaneously with a given prior preference (or weights) on different tasks. However, these methods often suffer from the issue of \\textit{gradient conflict} such that the tasks with larger gradients dominate the update direction, resulting in a performance degeneration on other tasks. In this paper, we develop a novel dynamic weighting multi-task actor-critic algorithm (MTAC) under two options of s","authors_text":"Hao Ban, Kaiyi Ji, Peiyao Xiao, Shaofeng Zou, Yudan Wang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-25T05:57:46Z","title":"Theoretical Study of Conflict-Avoidant Multi-Objective Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.16077","kind":"arxiv","version":3},"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:f010a5e8246563b1090d4bcbc52cc4f6d10ed46a923d660ef50b60dcd8a0e61f","target":"record","created_at":"2026-07-05T09:52:38Z","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":"06b514c58b40e56bb5c53a0a1cd8e145e548b43f074e29b588302e2dfe497e5c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-25T05:57:46Z","title_canon_sha256":"914df82fb24e02ccd392b0a1ddbf47cc244a0a5e9744440eb1731789591a4a38"},"schema_version":"1.0","source":{"id":"2405.16077","kind":"arxiv","version":3}},"canonical_sha256":"c745c71664837653612471f1cd1bca525fe137939e2b36d79a6a6d91cfa519fe","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c745c71664837653612471f1cd1bca525fe137939e2b36d79a6a6d91cfa519fe","first_computed_at":"2026-07-05T09:52:38.307486Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:52:38.307486Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TStSkF9xKIVzyWi3NdVNQ8DZi3YG7XwmoewymSMo6Ej+2ggxga/OPq6aVJmMbAzEy4TX5VWQ7U9fqVBUnAxCAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:52:38.307987Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.16077","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f010a5e8246563b1090d4bcbc52cc4f6d10ed46a923d660ef50b60dcd8a0e61f","sha256:6d3aa1a48ff2b752d9d80177066f5cedb2fe9f544fcf5445899a413186251878"],"state_sha256":"9ac50c1cb46211e7b26ce6394c58a3d3c894aa2878fde443ff7447c58ea57196"}