{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:HJP7NQZ6F3LT4YSJMNGFZVCO74","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":"2133a1fe4e81e2453e03a15a784f48327856ae7a02e60e31bc6afd2a43cd8eb1","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-10-21T01:00:10Z","title_canon_sha256":"090f97878b3594e8cbee0d18f557959975d497878e2ef6427f5b2fe10fce8770"},"schema_version":"1.0","source":{"id":"2210.11653","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.11653","created_at":"2026-07-05T05:08:56Z"},{"alias_kind":"arxiv_version","alias_value":"2210.11653v1","created_at":"2026-07-05T05:08:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.11653","created_at":"2026-07-05T05:08:56Z"},{"alias_kind":"pith_short_12","alias_value":"HJP7NQZ6F3LT","created_at":"2026-07-05T05:08:56Z"},{"alias_kind":"pith_short_16","alias_value":"HJP7NQZ6F3LT4YSJ","created_at":"2026-07-05T05:08:56Z"},{"alias_kind":"pith_short_8","alias_value":"HJP7NQZ6","created_at":"2026-07-05T05:08:56Z"}],"graph_snapshots":[{"event_id":"sha256:274a4b73cc2400390df0a6b631a4ca5cea58d5dcaed7e88eea86d9595afaadad","target":"graph","created_at":"2026-07-05T05:08:56Z","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/2210.11653/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The purpose of multi-task reinforcement learning (MTRL) is to train a single policy that can be applied to a set of different tasks. Sharing parameters allows us to take advantage of the similarities among tasks. However, the gaps between contents and difficulties of different tasks bring us challenges on both which tasks should share the parameters and what parameters should be shared, as well as the optimization challenges due to parameter sharing. In this work, we introduce a parameter-compositional approach (PaCo) as an attempt to address these challenges. In this framework, a policy subsp","authors_text":"Haichao Zhang, Lingfeng Sun, Masayoshi Tomizuka, Wei Xu","cross_cats":["cs.AI","cs.RO"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-10-21T01:00:10Z","title":"PaCo: Parameter-Compositional Multi-Task Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.11653","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":"sha256:528f424e32e032bde250a47af5a850a33631a65e7063e3ba8e8c65714651ad13","target":"record","created_at":"2026-07-05T05:08:56Z","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":"2133a1fe4e81e2453e03a15a784f48327856ae7a02e60e31bc6afd2a43cd8eb1","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-10-21T01:00:10Z","title_canon_sha256":"090f97878b3594e8cbee0d18f557959975d497878e2ef6427f5b2fe10fce8770"},"schema_version":"1.0","source":{"id":"2210.11653","kind":"arxiv","version":1}},"canonical_sha256":"3a5ff6c33e2ed73e6249634c5cd44eff33601207bc9d6cc20992dd3e473ca20d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3a5ff6c33e2ed73e6249634c5cd44eff33601207bc9d6cc20992dd3e473ca20d","first_computed_at":"2026-07-05T05:08:56.011819Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:08:56.011819Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1K1NZhYTtinxW97yApyM2U27BqylE/RppGBKtz1aSocslV2JlnwUrPvypUJholIrcsuTrQ3j59tgqorpIMSWCA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:08:56.012289Z","signed_message":"canonical_sha256_bytes"},"source_id":"2210.11653","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:528f424e32e032bde250a47af5a850a33631a65e7063e3ba8e8c65714651ad13","sha256:274a4b73cc2400390df0a6b631a4ca5cea58d5dcaed7e88eea86d9595afaadad"],"state_sha256":"c4be1c43794dabff092df02dea94e0da2714d3058adf2d05f484677ea71603d5"}