{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:CP3WY3HLVG5OI6DRCMQFQUBB2B","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":"55ba61083f6594ada0e4fac32bf90485db43560d37ce02ca1aebc8c426e45879","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-06-05T09:45:26Z","title_canon_sha256":"635c6b33c1f2c3311cfaf8a13a6d26cc1047a7313bd1bc77e2dfd9fdd2579612"},"schema_version":"1.0","source":{"id":"2406.03102","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.03102","created_at":"2026-07-05T08:27:51Z"},{"alias_kind":"arxiv_version","alias_value":"2406.03102v1","created_at":"2026-07-05T08:27:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.03102","created_at":"2026-07-05T08:27:51Z"},{"alias_kind":"pith_short_12","alias_value":"CP3WY3HLVG5O","created_at":"2026-07-05T08:27:51Z"},{"alias_kind":"pith_short_16","alias_value":"CP3WY3HLVG5OI6DR","created_at":"2026-07-05T08:27:51Z"},{"alias_kind":"pith_short_8","alias_value":"CP3WY3HL","created_at":"2026-07-05T08:27:51Z"}],"graph_snapshots":[{"event_id":"sha256:d2e8ed49b35baea0545e7a9c77e576e12090958b1f5e8b9035dcec9b6a4a2517","target":"graph","created_at":"2026-07-05T08:27:51Z","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/2406.03102/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Classic reinforcement learning (RL) frequently confronts challenges in tasks involving delays, which cause a mismatch between received observations and subsequent actions, thereby deviating from the Markov assumption. Existing methods usually tackle this issue with end-to-end solutions using state augmentation. However, these black-box approaches often involve incomprehensible processes and redundant information in the information states, causing instability and potentially undermining the overall performance. To alleviate the delay challenges in RL, we propose $\\textbf{DEER (Delay-resilient E","authors_text":"Bin Liang, Bo Xia, Bo Yuan, Xueqian Wang, Yilun Kong, Yongzhe Chang, Zhiheng Li","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-06-05T09:45:26Z","title":"DEER: A Delay-Resilient Framework for Reinforcement Learning with Variable Delays"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.03102","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":"sha256:8f6c56fb8cd14f09181365c771521221d6dc27cb262e3fc274a9213ee50e459e","target":"record","created_at":"2026-07-05T08:27:51Z","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":"55ba61083f6594ada0e4fac32bf90485db43560d37ce02ca1aebc8c426e45879","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-06-05T09:45:26Z","title_canon_sha256":"635c6b33c1f2c3311cfaf8a13a6d26cc1047a7313bd1bc77e2dfd9fdd2579612"},"schema_version":"1.0","source":{"id":"2406.03102","kind":"arxiv","version":1}},"canonical_sha256":"13f76c6ceba9bae478711320585021d07749c2be579ac64454dcaf9306dbbdd7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"13f76c6ceba9bae478711320585021d07749c2be579ac64454dcaf9306dbbdd7","first_computed_at":"2026-07-05T08:27:51.411289Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:27:51.411289Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"p4faxt4kT1dkdVLB6aJ0EBMmjwt0maQp6XsdUH6vMy/ysy5G3Ql0fsjBI5WDC+ZJ5dd7w8K8CDb57F3gwjZ/AQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:27:51.411802Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.03102","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8f6c56fb8cd14f09181365c771521221d6dc27cb262e3fc274a9213ee50e459e","sha256:d2e8ed49b35baea0545e7a9c77e576e12090958b1f5e8b9035dcec9b6a4a2517"],"state_sha256":"24f954f39e449fa2596f5a0e92f688228679b83deefefa6e715a4821d33e2aaf"}