{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:MTEHG53OR4HB6YEH564BZ4JUCY","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":"cb17fe49d5b4829faccc8ae074935e3a2470e51aed3eff77d604da9e6e98635e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-06-25T17:06:57Z","title_canon_sha256":"70ea05de14122cfd37e2a2a323d5df6e4c10ccdee432893cef376f66e649fc8a"},"schema_version":"1.0","source":{"id":"2406.17718","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.17718","created_at":"2026-07-05T08:36:39Z"},{"alias_kind":"arxiv_version","alias_value":"2406.17718v1","created_at":"2026-07-05T08:36:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.17718","created_at":"2026-07-05T08:36:39Z"},{"alias_kind":"pith_short_12","alias_value":"MTEHG53OR4HB","created_at":"2026-07-05T08:36:39Z"},{"alias_kind":"pith_short_16","alias_value":"MTEHG53OR4HB6YEH","created_at":"2026-07-05T08:36:39Z"},{"alias_kind":"pith_short_8","alias_value":"MTEHG53O","created_at":"2026-07-05T08:36:39Z"}],"graph_snapshots":[{"event_id":"sha256:3fc6e6f34eca528fbee33b980fc2ae6b51f53619937fcaebbef4996942414c7e","target":"graph","created_at":"2026-07-05T08:36:39Z","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/2406.17718/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We investigate the impact of auxiliary learning tasks such as observation reconstruction and latent self-prediction on the representation learning problem in reinforcement learning. We also study how they interact with distractions and observation functions in the MDP. We provide a theoretical analysis of the learning dynamics of observation reconstruction, latent self-prediction, and TD learning in the presence of distractions and observation functions under linear model assumptions. With this formalization, we are able to explain why latent-self prediction is a helpful \\emph{auxiliary task},","authors_text":"Amir-massoud Farahmand, Claas Voelcker, Igor Gilitschenski, Tyler Kastner","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-06-25T17:06:57Z","title":"When does Self-Prediction help? Understanding Auxiliary Tasks in Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.17718","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":"sha256:470d894d7c77c8dbb11094941ce7e577f090e1f887d6900be05fb721e470de1f","target":"record","created_at":"2026-07-05T08:36:39Z","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":"cb17fe49d5b4829faccc8ae074935e3a2470e51aed3eff77d604da9e6e98635e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-06-25T17:06:57Z","title_canon_sha256":"70ea05de14122cfd37e2a2a323d5df6e4c10ccdee432893cef376f66e649fc8a"},"schema_version":"1.0","source":{"id":"2406.17718","kind":"arxiv","version":1}},"canonical_sha256":"64c873776e8f0e1f6087efb81cf134161226d4f77efaa0753d85accb1162dc7a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"64c873776e8f0e1f6087efb81cf134161226d4f77efaa0753d85accb1162dc7a","first_computed_at":"2026-07-05T08:36:39.093833Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:36:39.093833Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hg79cm5MIH4ZKSOgkZw8o+DDYzQRe0D5ljUate1TChmgS6bzgDsrxI5cJo3pNlOYsbvQLFurs7CNWpf9NdiqBw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:36:39.094240Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.17718","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:470d894d7c77c8dbb11094941ce7e577f090e1f887d6900be05fb721e470de1f","sha256:3fc6e6f34eca528fbee33b980fc2ae6b51f53619937fcaebbef4996942414c7e"],"state_sha256":"8ec53d0176ad1ba1d96ec2c602f4a689c9775d35917e73abfc7e0a143f5dc0a2"}