{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:RZ36YC4LKAOQMWE7ERT3DSFVKZ","short_pith_number":"pith:RZ36YC4L","schema_version":"1.0","canonical_sha256":"8e77ec0b8b501d06589f2467b1c8b5564923dea21036f50d023e81d11f488cc4","source":{"kind":"arxiv","id":"2210.06041","version":1},"attestation_state":"computed","paper":{"title":"Reinforcement Learning with Automated Auxiliary Loss Search","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Che Wang, Dongsheng Li, Kan Ren, Minghuan Liu, Tairan He, Weinan Zhang, Yuge Zhang, Yuqing Yang","submitted_at":"2022-10-12T09:24:53Z","abstract_excerpt":"A good state representation is crucial to solving complicated reinforcement learning (RL) challenges. Many recent works focus on designing auxiliary losses for learning informative representations. Unfortunately, these handcrafted objectives rely heavily on expert knowledge and may be sub-optimal. In this paper, we propose a principled and universal method for learning better representations with auxiliary loss functions, named Automated Auxiliary Loss Search (A2LS), which automatically searches for top-performing auxiliary loss functions for RL. Specifically, based on the collected trajectory"},"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":"2210.06041","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-10-12T09:24:53Z","cross_cats_sorted":[],"title_canon_sha256":"bf501274997d36bee9363acc9f9d5ac8dd8f6031ce8cc3ab4712811853473109","abstract_canon_sha256":"65bf87a2b893805e5dc4b299b79008360c2631c24df532defcadbd98b5e78840"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:05:55.810199Z","signature_b64":"SmhTEpBDIdE0/N15kcj2/T4Ue/DSk6d8WZbmH9ke+265pJRm9zVANakiln15xU8oij3G6xz6OMRHXaRtbF1PAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8e77ec0b8b501d06589f2467b1c8b5564923dea21036f50d023e81d11f488cc4","last_reissued_at":"2026-07-05T05:05:55.809735Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:05:55.809735Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reinforcement Learning with Automated Auxiliary Loss Search","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Che Wang, Dongsheng Li, Kan Ren, Minghuan Liu, Tairan He, Weinan Zhang, Yuge Zhang, Yuqing Yang","submitted_at":"2022-10-12T09:24:53Z","abstract_excerpt":"A good state representation is crucial to solving complicated reinforcement learning (RL) challenges. Many recent works focus on designing auxiliary losses for learning informative representations. Unfortunately, these handcrafted objectives rely heavily on expert knowledge and may be sub-optimal. In this paper, we propose a principled and universal method for learning better representations with auxiliary loss functions, named Automated Auxiliary Loss Search (A2LS), which automatically searches for top-performing auxiliary loss functions for RL. Specifically, based on the collected trajectory"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.06041","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/2210.06041/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":"2210.06041","created_at":"2026-07-05T05:05:55.809802+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.06041v1","created_at":"2026-07-05T05:05:55.809802+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.06041","created_at":"2026-07-05T05:05:55.809802+00:00"},{"alias_kind":"pith_short_12","alias_value":"RZ36YC4LKAOQ","created_at":"2026-07-05T05:05:55.809802+00:00"},{"alias_kind":"pith_short_16","alias_value":"RZ36YC4LKAOQMWE7","created_at":"2026-07-05T05:05:55.809802+00:00"},{"alias_kind":"pith_short_8","alias_value":"RZ36YC4L","created_at":"2026-07-05T05:05:55.809802+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RZ36YC4LKAOQMWE7ERT3DSFVKZ","json":"https://pith.science/pith/RZ36YC4LKAOQMWE7ERT3DSFVKZ.json","graph_json":"https://pith.science/api/pith-number/RZ36YC4LKAOQMWE7ERT3DSFVKZ/graph.json","events_json":"https://pith.science/api/pith-number/RZ36YC4LKAOQMWE7ERT3DSFVKZ/events.json","paper":"https://pith.science/paper/RZ36YC4L"},"agent_actions":{"view_html":"https://pith.science/pith/RZ36YC4LKAOQMWE7ERT3DSFVKZ","download_json":"https://pith.science/pith/RZ36YC4LKAOQMWE7ERT3DSFVKZ.json","view_paper":"https://pith.science/paper/RZ36YC4L","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.06041&json=true","fetch_graph":"https://pith.science/api/pith-number/RZ36YC4LKAOQMWE7ERT3DSFVKZ/graph.json","fetch_events":"https://pith.science/api/pith-number/RZ36YC4LKAOQMWE7ERT3DSFVKZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RZ36YC4LKAOQMWE7ERT3DSFVKZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RZ36YC4LKAOQMWE7ERT3DSFVKZ/action/storage_attestation","attest_author":"https://pith.science/pith/RZ36YC4LKAOQMWE7ERT3DSFVKZ/action/author_attestation","sign_citation":"https://pith.science/pith/RZ36YC4LKAOQMWE7ERT3DSFVKZ/action/citation_signature","submit_replication":"https://pith.science/pith/RZ36YC4LKAOQMWE7ERT3DSFVKZ/action/replication_record"}},"created_at":"2026-07-05T05:05:55.809802+00:00","updated_at":"2026-07-05T05:05:55.809802+00:00"}