{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:KCBFEFQPGD754NSMUBWIQUR3IP","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":"c0328577a80bd2eac333f1bf94d4cce89a8ab9d48c29bb2d335acf1f338079a9","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-22T05:08:36Z","title_canon_sha256":"841e1447789e35cb52c57d1f3bcd2ee23894d9fa0bcd38838e0189676815f143"},"schema_version":"1.0","source":{"id":"2006.12010","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.12010","created_at":"2026-07-05T01:40:32Z"},{"alias_kind":"arxiv_version","alias_value":"2006.12010v2","created_at":"2026-07-05T01:40:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.12010","created_at":"2026-07-05T01:40:32Z"},{"alias_kind":"pith_short_12","alias_value":"KCBFEFQPGD75","created_at":"2026-07-05T01:40:32Z"},{"alias_kind":"pith_short_16","alias_value":"KCBFEFQPGD754NSM","created_at":"2026-07-05T01:40:32Z"},{"alias_kind":"pith_short_8","alias_value":"KCBFEFQP","created_at":"2026-07-05T01:40:32Z"}],"graph_snapshots":[{"event_id":"sha256:b80729b1b458507c57f9c4cefaa575848e30321e2a330f811dc8a9d0eb6fa517","target":"graph","created_at":"2026-07-05T01:40:32Z","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/2006.12010/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"QTRAN is a multi-agent reinforcement learning (MARL) algorithm capable of learning the largest class of joint-action value functions up to date. However, despite its strong theoretical guarantee, it has shown poor empirical performance in complex environments, such as Starcraft Multi-Agent Challenge (SMAC). In this paper, we identify the performance bottleneck of QTRAN and propose a substantially improved version, coined QTRAN++. Our gains come from (i) stabilizing the training objective of QTRAN, (ii) removing the strict role separation between the action-value estimators of QTRAN, and (iii) ","authors_text":"Jinwoo Shin, Kyunghwan Son, Roben Delos Reyes, Sungsoo Ahn, Yung Yi","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-22T05:08:36Z","title":"QTRAN++: Improved Value Transformation for Cooperative Multi-Agent Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.12010","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:a5c99b122207056610b84a1469fcd7f03cfdb6c84e659bd3c99334ebe81272dc","target":"record","created_at":"2026-07-05T01:40:32Z","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":"c0328577a80bd2eac333f1bf94d4cce89a8ab9d48c29bb2d335acf1f338079a9","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-22T05:08:36Z","title_canon_sha256":"841e1447789e35cb52c57d1f3bcd2ee23894d9fa0bcd38838e0189676815f143"},"schema_version":"1.0","source":{"id":"2006.12010","kind":"arxiv","version":2}},"canonical_sha256":"508252160f30ffde364ca06c88523b43f7cc28988e8709965194854346fe271d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"508252160f30ffde364ca06c88523b43f7cc28988e8709965194854346fe271d","first_computed_at":"2026-07-05T01:40:32.457998Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:40:32.457998Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ltcUiNY7U3zVISb9F9jj8kU3KfSQYcJvY9jwVB35/3DiQ8Twq0/l3Cw/858RbsWXFP7rXxSjTWeb8VM5Z8LyCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T01:40:32.458642Z","signed_message":"canonical_sha256_bytes"},"source_id":"2006.12010","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a5c99b122207056610b84a1469fcd7f03cfdb6c84e659bd3c99334ebe81272dc","sha256:b80729b1b458507c57f9c4cefaa575848e30321e2a330f811dc8a9d0eb6fa517"],"state_sha256":"7ddb31874cb414115fe30845e3aecd594d78660f44e3e09be59bdc384c8bc2c9"}