{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:CLBEKR57UO3BRZW2G3DQKIGJ5O","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":"94c0ee7de5f3a68fa5755ee82e3de5ab669ef308a6a34cc9f1dac24e85ad0a71","cross_cats_sorted":["cs.MA"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2022-10-31T17:54:51Z","title_canon_sha256":"7711302ff079db3f027fbc9fba92e95838c57151584a8321d3ac7cdf55d6b1a6"},"schema_version":"1.0","source":{"id":"2210.17540","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.17540","created_at":"2026-07-05T05:12:06Z"},{"alias_kind":"arxiv_version","alias_value":"2210.17540v1","created_at":"2026-07-05T05:12:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.17540","created_at":"2026-07-05T05:12:06Z"},{"alias_kind":"pith_short_12","alias_value":"CLBEKR57UO3B","created_at":"2026-07-05T05:12:06Z"},{"alias_kind":"pith_short_16","alias_value":"CLBEKR57UO3BRZW2","created_at":"2026-07-05T05:12:06Z"},{"alias_kind":"pith_short_8","alias_value":"CLBEKR57","created_at":"2026-07-05T05:12:06Z"}],"graph_snapshots":[{"event_id":"sha256:f3a78e9f630eee67508bedb272018efdb0bdb1271bd0503738743abe8bea568d","target":"graph","created_at":"2026-07-05T05:12:06Z","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/2210.17540/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Sparse and delayed rewards pose a challenge to single agent reinforcement learning. This challenge is amplified in multi-agent reinforcement learning (MARL) where credit assignment of these rewards needs to happen not only across time, but also across agents. We propose Agent-Time Attention (ATA), a neural network model with auxiliary losses for redistributing sparse and delayed rewards in collaborative MARL. We provide a simple example that demonstrates how providing agents with their own local redistributed rewards and shared global redistributed rewards motivate different policies. We exten","authors_text":"Jayesh K. Gupta, Jennifer She, Mykel J. Kochenderfer","cross_cats":["cs.MA"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2022-10-31T17:54:51Z","title":"Agent-Time Attention for Sparse Rewards Multi-Agent Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.17540","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":"sha256:13d25187f82c1b433a2f8870f8f3ad10f6167ec6da1bf4c0dbb9fb1d4b04ab20","target":"record","created_at":"2026-07-05T05:12:06Z","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":"94c0ee7de5f3a68fa5755ee82e3de5ab669ef308a6a34cc9f1dac24e85ad0a71","cross_cats_sorted":["cs.MA"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2022-10-31T17:54:51Z","title_canon_sha256":"7711302ff079db3f027fbc9fba92e95838c57151584a8321d3ac7cdf55d6b1a6"},"schema_version":"1.0","source":{"id":"2210.17540","kind":"arxiv","version":1}},"canonical_sha256":"12c24547bfa3b618e6da36c70520c9eb9e95e5758fc955207a0b1386ed0fa0ff","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"12c24547bfa3b618e6da36c70520c9eb9e95e5758fc955207a0b1386ed0fa0ff","first_computed_at":"2026-07-05T05:12:06.223083Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:12:06.223083Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RI4+FkPzRL+u7SPR/eVhcl5Pn4Srdyx0z0bCgtdrq1vYeZ/JKWgMGsgEewJM+hEylSbMGQUe52qwn5M38/SwAA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:12:06.223517Z","signed_message":"canonical_sha256_bytes"},"source_id":"2210.17540","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:13d25187f82c1b433a2f8870f8f3ad10f6167ec6da1bf4c0dbb9fb1d4b04ab20","sha256:f3a78e9f630eee67508bedb272018efdb0bdb1271bd0503738743abe8bea568d"],"state_sha256":"8bfb7f026c7eb9fbf83d829680fc6fe8d76e6f95563f6d0d73a4c23926750e33"}