{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:CP3WY3HLVG5OI6DRCMQFQUBB2B","short_pith_number":"pith:CP3WY3HL","schema_version":"1.0","canonical_sha256":"13f76c6ceba9bae478711320585021d07749c2be579ac64454dcaf9306dbbdd7","source":{"kind":"arxiv","id":"2406.03102","version":1},"attestation_state":"computed","paper":{"title":"DEER: A Delay-Resilient Framework for Reinforcement Learning with Variable Delays","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Bin Liang, Bo Xia, Bo Yuan, Xueqian Wang, Yilun Kong, Yongzhe Chang, Zhiheng Li","submitted_at":"2024-06-05T09:45:26Z","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"},"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":"2406.03102","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-06-05T09:45:26Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"635c6b33c1f2c3311cfaf8a13a6d26cc1047a7313bd1bc77e2dfd9fdd2579612","abstract_canon_sha256":"55ba61083f6594ada0e4fac32bf90485db43560d37ce02ca1aebc8c426e45879"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:27:51.411802Z","signature_b64":"p4faxt4kT1dkdVLB6aJ0EBMmjwt0maQp6XsdUH6vMy/ysy5G3Ql0fsjBI5WDC+ZJ5dd7w8K8CDb57F3gwjZ/AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"13f76c6ceba9bae478711320585021d07749c2be579ac64454dcaf9306dbbdd7","last_reissued_at":"2026-07-05T08:27:51.411289Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:27:51.411289Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DEER: A Delay-Resilient Framework for Reinforcement Learning with Variable Delays","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Bin Liang, Bo Xia, Bo Yuan, Xueqian Wang, Yilun Kong, Yongzhe Chang, Zhiheng Li","submitted_at":"2024-06-05T09:45:26Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.03102","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/2406.03102/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":"2406.03102","created_at":"2026-07-05T08:27:51.411360+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.03102v1","created_at":"2026-07-05T08:27:51.411360+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.03102","created_at":"2026-07-05T08:27:51.411360+00:00"},{"alias_kind":"pith_short_12","alias_value":"CP3WY3HLVG5O","created_at":"2026-07-05T08:27:51.411360+00:00"},{"alias_kind":"pith_short_16","alias_value":"CP3WY3HLVG5OI6DR","created_at":"2026-07-05T08:27:51.411360+00:00"},{"alias_kind":"pith_short_8","alias_value":"CP3WY3HL","created_at":"2026-07-05T08:27:51.411360+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/CP3WY3HLVG5OI6DRCMQFQUBB2B","json":"https://pith.science/pith/CP3WY3HLVG5OI6DRCMQFQUBB2B.json","graph_json":"https://pith.science/api/pith-number/CP3WY3HLVG5OI6DRCMQFQUBB2B/graph.json","events_json":"https://pith.science/api/pith-number/CP3WY3HLVG5OI6DRCMQFQUBB2B/events.json","paper":"https://pith.science/paper/CP3WY3HL"},"agent_actions":{"view_html":"https://pith.science/pith/CP3WY3HLVG5OI6DRCMQFQUBB2B","download_json":"https://pith.science/pith/CP3WY3HLVG5OI6DRCMQFQUBB2B.json","view_paper":"https://pith.science/paper/CP3WY3HL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.03102&json=true","fetch_graph":"https://pith.science/api/pith-number/CP3WY3HLVG5OI6DRCMQFQUBB2B/graph.json","fetch_events":"https://pith.science/api/pith-number/CP3WY3HLVG5OI6DRCMQFQUBB2B/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CP3WY3HLVG5OI6DRCMQFQUBB2B/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CP3WY3HLVG5OI6DRCMQFQUBB2B/action/storage_attestation","attest_author":"https://pith.science/pith/CP3WY3HLVG5OI6DRCMQFQUBB2B/action/author_attestation","sign_citation":"https://pith.science/pith/CP3WY3HLVG5OI6DRCMQFQUBB2B/action/citation_signature","submit_replication":"https://pith.science/pith/CP3WY3HLVG5OI6DRCMQFQUBB2B/action/replication_record"}},"created_at":"2026-07-05T08:27:51.411360+00:00","updated_at":"2026-07-05T08:27:51.411360+00:00"}