{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:VH637U7TSHODGTZCFMS3M4ZSL6","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":"52c736dce7e4e761ba80f141cb16266cd2353ae5217591d8d4b876bffaa1eba9","cross_cats_sorted":["cs.AI","cs.SY","eess.SY"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-05T16:11:03Z","title_canon_sha256":"7909ffc9f893abc546cd6c7a014f15bbd51bde7f801c4b7f5aaa2d7f93bb82cd"},"schema_version":"1.0","source":{"id":"2402.03141","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.03141","created_at":"2026-07-05T08:28:05Z"},{"alias_kind":"arxiv_version","alias_value":"2402.03141v2","created_at":"2026-07-05T08:28:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.03141","created_at":"2026-07-05T08:28:05Z"},{"alias_kind":"pith_short_12","alias_value":"VH637U7TSHOD","created_at":"2026-07-05T08:28:05Z"},{"alias_kind":"pith_short_16","alias_value":"VH637U7TSHODGTZC","created_at":"2026-07-05T08:28:05Z"},{"alias_kind":"pith_short_8","alias_value":"VH637U7T","created_at":"2026-07-05T08:28:05Z"}],"graph_snapshots":[{"event_id":"sha256:b278b8e694cf49e8505f61d2d49257d89979ae7d7841464d9a575e3297b2b456","target":"graph","created_at":"2026-07-05T08:28:05Z","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/2402.03141/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning (RL) is challenging in the common case of delays between events and their sensory perceptions. State-of-the-art (SOTA) state augmentation techniques either suffer from state space explosion or performance degeneration in stochastic environments. To address these challenges, we present a novel Auxiliary-Delayed Reinforcement Learning (AD-RL) method that leverages auxiliary tasks involving short delays to accelerate RL with long delays, without compromising performance in stochastic environments. Specifically, AD-RL learns a value function for short delays and uses bootstr","authors_text":"Chao Huang, Chen Lv, Chung-Wei Lin, J\\\"urgen Schmidhuber, Qingyuan Wu, Qi Zhu, Simon Sinong Zhan, Yixuan Wang, Yuhui Wang","cross_cats":["cs.AI","cs.SY","eess.SY"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-05T16:11:03Z","title":"Boosting Reinforcement Learning with Strongly Delayed Feedback Through Auxiliary Short Delays"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.03141","kind":"arxiv","version":2},"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":"sha256:06de2a13ce8b2327736aafee3fc77a0f0ba3075437085f26068e6f679869ebd7","target":"record","created_at":"2026-07-05T08:28:05Z","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":"52c736dce7e4e761ba80f141cb16266cd2353ae5217591d8d4b876bffaa1eba9","cross_cats_sorted":["cs.AI","cs.SY","eess.SY"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-05T16:11:03Z","title_canon_sha256":"7909ffc9f893abc546cd6c7a014f15bbd51bde7f801c4b7f5aaa2d7f93bb82cd"},"schema_version":"1.0","source":{"id":"2402.03141","kind":"arxiv","version":2}},"canonical_sha256":"a9fdbfd3f391dc334f222b25b673325f98f2accce5d78b2e1d73664a6de5383b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a9fdbfd3f391dc334f222b25b673325f98f2accce5d78b2e1d73664a6de5383b","first_computed_at":"2026-07-05T08:28:05.527759Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:28:05.527759Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"agNYH4gBXIeQdruRwk09woZRNKIzWlBKRSQYd8Utr5jbhrPu3UzVywjoUPexk+yOp1IddywsKDv+KS8PVh6lCw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:28:05.528183Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.03141","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:06de2a13ce8b2327736aafee3fc77a0f0ba3075437085f26068e6f679869ebd7","sha256:b278b8e694cf49e8505f61d2d49257d89979ae7d7841464d9a575e3297b2b456"],"state_sha256":"3cd67547641c9efb0136130d5129d879c50b2b763c96af09caf56cd0bfe55df1"}