{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:QVBBASFG7Y3SZP4AD3ED3GKRAP","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":"c357c93a202bca881103149276bd945ac6b404fe0a5d94c7f2f30a9b1e81319b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-02-22T19:17:12Z","title_canon_sha256":"2b67a8876cccd4db7b783b88e73d8ec1f64bdb32fd3a26149c62bf937c3440da"},"schema_version":"1.0","source":{"id":"2202.11133","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2202.11133","created_at":"2026-07-05T03:59:28Z"},{"alias_kind":"arxiv_version","alias_value":"2202.11133v1","created_at":"2026-07-05T03:59:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.11133","created_at":"2026-07-05T03:59:28Z"},{"alias_kind":"pith_short_12","alias_value":"QVBBASFG7Y3S","created_at":"2026-07-05T03:59:28Z"},{"alias_kind":"pith_short_16","alias_value":"QVBBASFG7Y3SZP4A","created_at":"2026-07-05T03:59:28Z"},{"alias_kind":"pith_short_8","alias_value":"QVBBASFG","created_at":"2026-07-05T03:59:28Z"}],"graph_snapshots":[{"event_id":"sha256:6ddd17cb8fbb908b3ecbc1446c64d934ab12577bb3dbf1de304b8aa280febb59","target":"graph","created_at":"2026-07-05T03:59:28Z","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/2202.11133/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Learning auxiliary tasks, such as multiple predictions about the world, can provide many benefits to reinforcement learning systems. A variety of off-policy learning algorithms have been developed to learn such predictions, but as yet there is little work on how to adapt the behavior to gather useful data for those off-policy predictions. In this work, we investigate a reinforcement learning system designed to learn a collection of auxiliary tasks, with a behavior policy learning to take actions to improve those auxiliary predictions. We highlight the inherent non-stationarity in this continua","authors_text":"Adam White, Andrew Jacobsen, Chunlok Lo, Martha White, Matthew McLeod, Matthew Schlegel, Raksha Kumaraswamy","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-02-22T19:17:12Z","title":"Continual Auxiliary Task Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.11133","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":"sha256:8077b68815c063f3cca8094fd1c5cbb2f8930ddbd8a2508b46e0205f76d0b36f","target":"record","created_at":"2026-07-05T03:59:28Z","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":"c357c93a202bca881103149276bd945ac6b404fe0a5d94c7f2f30a9b1e81319b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-02-22T19:17:12Z","title_canon_sha256":"2b67a8876cccd4db7b783b88e73d8ec1f64bdb32fd3a26149c62bf937c3440da"},"schema_version":"1.0","source":{"id":"2202.11133","kind":"arxiv","version":1}},"canonical_sha256":"85421048a6fe372cbf801ec83d995103c59b6188b22f3c45cf77f71222aa7d34","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"85421048a6fe372cbf801ec83d995103c59b6188b22f3c45cf77f71222aa7d34","first_computed_at":"2026-07-05T03:59:28.672087Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:59:28.672087Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZN6FHAZ2BmuMl5nXv1/FQXyGjG+hPLxrs+Gmlo4b05QGNbsVUiAmyJGiyqV0K3KS8ddrwR0Op2b302haX5fbCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T03:59:28.672625Z","signed_message":"canonical_sha256_bytes"},"source_id":"2202.11133","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8077b68815c063f3cca8094fd1c5cbb2f8930ddbd8a2508b46e0205f76d0b36f","sha256:6ddd17cb8fbb908b3ecbc1446c64d934ab12577bb3dbf1de304b8aa280febb59"],"state_sha256":"19d98e6a460288c02a4402aa5b9730d3d2cf3d460d526e4a767b18fb3c11d52e"}