{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:FHADIYOB4LPIBYWZHQIGLYDD5Z","short_pith_number":"pith:FHADIYOB","schema_version":"1.0","canonical_sha256":"29c03461c1e2de80e2d93c1065e063ee582732702f37cd6c9b45bc19d649aa88","source":{"kind":"arxiv","id":"2311.11385","version":2},"attestation_state":"computed","paper":{"title":"Multi-Task Reinforcement Learning with Mixture of Orthogonal Experts","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ahmed Hendawy, Carlo D'Eramo, Jan Peters","submitted_at":"2023-11-19T18:09:25Z","abstract_excerpt":"Multi-Task Reinforcement Learning (MTRL) tackles the long-standing problem of endowing agents with skills that generalize across a variety of problems. To this end, sharing representations plays a fundamental role in capturing both unique and common characteristics of the tasks. Tasks may exhibit similarities in terms of skills, objects, or physical properties while leveraging their representations eases the achievement of a universal policy. Nevertheless, the pursuit of learning a shared set of diverse representations is still an open challenge. In this paper, we introduce a novel approach fo"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2311.11385","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-11-19T18:09:25Z","cross_cats_sorted":[],"title_canon_sha256":"b9e90df2cf42fe7965768a60ef48d1c1bad55fb59873b42723401f9c8f0bbdc8","abstract_canon_sha256":"eac0f61dbd5192382e0bee098f0c628bada0b628b1e1af30fda69c786eb2fb1e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:15:42.020144Z","signature_b64":"ZlvqVrq3KV6Y34EB/xCaK/1loX6HJE0SP+6gR6EVE9MWxzf5trhuv5mrij4+/NrRD77vnXuUp8CakcjaxwxECw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"29c03461c1e2de80e2d93c1065e063ee582732702f37cd6c9b45bc19d649aa88","last_reissued_at":"2026-07-05T08:15:42.019611Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:15:42.019611Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-Task Reinforcement Learning with Mixture of Orthogonal Experts","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ahmed Hendawy, Carlo D'Eramo, Jan Peters","submitted_at":"2023-11-19T18:09:25Z","abstract_excerpt":"Multi-Task Reinforcement Learning (MTRL) tackles the long-standing problem of endowing agents with skills that generalize across a variety of problems. To this end, sharing representations plays a fundamental role in capturing both unique and common characteristics of the tasks. Tasks may exhibit similarities in terms of skills, objects, or physical properties while leveraging their representations eases the achievement of a universal policy. Nevertheless, the pursuit of learning a shared set of diverse representations is still an open challenge. In this paper, we introduce a novel approach fo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.11385","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2311.11385/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2311.11385","created_at":"2026-07-05T08:15:42.019679+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.11385v2","created_at":"2026-07-05T08:15:42.019679+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.11385","created_at":"2026-07-05T08:15:42.019679+00:00"},{"alias_kind":"pith_short_12","alias_value":"FHADIYOB4LPI","created_at":"2026-07-05T08:15:42.019679+00:00"},{"alias_kind":"pith_short_16","alias_value":"FHADIYOB4LPIBYWZ","created_at":"2026-07-05T08:15:42.019679+00:00"},{"alias_kind":"pith_short_8","alias_value":"FHADIYOB","created_at":"2026-07-05T08:15:42.019679+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2512.08411","citing_title":"Prismatic World Model: Learning Compositional Dynamics for Planning in Hybrid Systems","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2604.03404","citing_title":"Diffusion Policy with Bayesian Expert Selection for Active Multi-Target Tracking","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11473","citing_title":"TOPPO: Rethinking PPO for Multi-Task Reinforcement Learning with Critic Balancing","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09355","citing_title":"FLAME: Adaptive Mixture-of-Experts for Continual Multimodal Multi-Task Learning","ref_index":21,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FHADIYOB4LPIBYWZHQIGLYDD5Z","json":"https://pith.science/pith/FHADIYOB4LPIBYWZHQIGLYDD5Z.json","graph_json":"https://pith.science/api/pith-number/FHADIYOB4LPIBYWZHQIGLYDD5Z/graph.json","events_json":"https://pith.science/api/pith-number/FHADIYOB4LPIBYWZHQIGLYDD5Z/events.json","paper":"https://pith.science/paper/FHADIYOB"},"agent_actions":{"view_html":"https://pith.science/pith/FHADIYOB4LPIBYWZHQIGLYDD5Z","download_json":"https://pith.science/pith/FHADIYOB4LPIBYWZHQIGLYDD5Z.json","view_paper":"https://pith.science/paper/FHADIYOB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.11385&json=true","fetch_graph":"https://pith.science/api/pith-number/FHADIYOB4LPIBYWZHQIGLYDD5Z/graph.json","fetch_events":"https://pith.science/api/pith-number/FHADIYOB4LPIBYWZHQIGLYDD5Z/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FHADIYOB4LPIBYWZHQIGLYDD5Z/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FHADIYOB4LPIBYWZHQIGLYDD5Z/action/storage_attestation","attest_author":"https://pith.science/pith/FHADIYOB4LPIBYWZHQIGLYDD5Z/action/author_attestation","sign_citation":"https://pith.science/pith/FHADIYOB4LPIBYWZHQIGLYDD5Z/action/citation_signature","submit_replication":"https://pith.science/pith/FHADIYOB4LPIBYWZHQIGLYDD5Z/action/replication_record"}},"created_at":"2026-07-05T08:15:42.019679+00:00","updated_at":"2026-07-05T08:15:42.019679+00:00"}