{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:HGEZ57Z5U7DBD7FP3TFKZWZZHQ","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":"300eb841eb200d83f14d8cdfe2d3af23955b5bc2340a49d69d03ec5e27420fae","cross_cats_sorted":["cs.MA","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-05-11T21:21:50Z","title_canon_sha256":"22ca5e7570664173fcd2855510582a83a0fc1bcd19ec915deace9328ec71f264"},"schema_version":"1.0","source":{"id":"2005.05441","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2005.05441","created_at":"2026-07-05T01:31:27Z"},{"alias_kind":"arxiv_version","alias_value":"2005.05441v2","created_at":"2026-07-05T01:31:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.05441","created_at":"2026-07-05T01:31:27Z"},{"alias_kind":"pith_short_12","alias_value":"HGEZ57Z5U7DB","created_at":"2026-07-05T01:31:27Z"},{"alias_kind":"pith_short_16","alias_value":"HGEZ57Z5U7DBD7FP","created_at":"2026-07-05T01:31:27Z"},{"alias_kind":"pith_short_8","alias_value":"HGEZ57Z5","created_at":"2026-07-05T01:31:27Z"}],"graph_snapshots":[{"event_id":"sha256:4a1ba795397d44ed1552cc862756d52f9e0b6caf6b2fa9b8c4dd87c105262f0a","target":"graph","created_at":"2026-07-05T01:31:27Z","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/2005.05441/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Action and observation delays exist prevalently in the real-world cyber-physical systems which may pose challenges in reinforcement learning design. It is particularly an arduous task when handling multi-agent systems where the delay of one agent could spread to other agents. To resolve this problem, this paper proposes a novel framework to deal with delays as well as the non-stationary training issue of multi-agent tasks with model-free deep reinforcement learning. We formally define the Delay-Aware Markov Game that incorporates the delays of all agents in the environment. To solve Delay-Awar","authors_text":"Baiming Chen, Ding Zhao, Liang Li, Mengdi Xu, Zuxin Liu","cross_cats":["cs.MA","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-05-11T21:21:50Z","title":"Delay-Aware Multi-Agent Reinforcement Learning for Cooperative and Competitive Environments"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.05441","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":"sha256:06454ae06b0a268ec7aec8029f51044585e476467052c03d5f5c8485d5372f94","target":"record","created_at":"2026-07-05T01:31:27Z","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":"300eb841eb200d83f14d8cdfe2d3af23955b5bc2340a49d69d03ec5e27420fae","cross_cats_sorted":["cs.MA","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-05-11T21:21:50Z","title_canon_sha256":"22ca5e7570664173fcd2855510582a83a0fc1bcd19ec915deace9328ec71f264"},"schema_version":"1.0","source":{"id":"2005.05441","kind":"arxiv","version":2}},"canonical_sha256":"39899eff3da7c611fcafdccaacdb393c31596ef82fd6e5a7714fa389ce019f85","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"39899eff3da7c611fcafdccaacdb393c31596ef82fd6e5a7714fa389ce019f85","first_computed_at":"2026-07-05T01:31:27.110950Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:31:27.110950Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CThFMAncyxrNTHzys9DE2Ifscn3cZvuMElJlMaG+kDjkQUntOOba9fwzkHq5jQccXueKuCiQqViBwhGCnf6/Dg==","signature_status":"signed_v1","signed_at":"2026-07-05T01:31:27.111391Z","signed_message":"canonical_sha256_bytes"},"source_id":"2005.05441","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:06454ae06b0a268ec7aec8029f51044585e476467052c03d5f5c8485d5372f94","sha256:4a1ba795397d44ed1552cc862756d52f9e0b6caf6b2fa9b8c4dd87c105262f0a"],"state_sha256":"2b91fd4ca0772528174f5c9943f0a9f6cfbc7d6d0520dfba5ef45b32e667cc74"}