{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:LR6EV3YTKSB3HPBPG6B6PEBONM","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":"f12a2a13f5ca2915957f4565757dc89c74ec51ca40d8341229744549fb6edfa8","cross_cats_sorted":["cs.AI","math.OC","stat.ML"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2022-03-24T19:59:43Z","title_canon_sha256":"4969d873fdfd6747b85d7f2db0445f42c0bf385a3ee31f2d368be10986f3adf7"},"schema_version":"1.0","source":{"id":"2203.13319","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.13319","created_at":"2026-07-05T04:54:02Z"},{"alias_kind":"arxiv_version","alias_value":"2203.13319v3","created_at":"2026-07-05T04:54:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.13319","created_at":"2026-07-05T04:54:02Z"},{"alias_kind":"pith_short_12","alias_value":"LR6EV3YTKSB3","created_at":"2026-07-05T04:54:02Z"},{"alias_kind":"pith_short_16","alias_value":"LR6EV3YTKSB3HPBP","created_at":"2026-07-05T04:54:02Z"},{"alias_kind":"pith_short_8","alias_value":"LR6EV3YT","created_at":"2026-07-05T04:54:02Z"}],"graph_snapshots":[{"event_id":"sha256:17b5c2588df90c0fc5d908c1a97e3a0cebba411f8146671c3093497ef0270f94","target":"graph","created_at":"2026-07-05T04:54:02Z","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/2203.13319/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present the extension of the Remember and Forget for Experience Replay (ReF-ER) algorithm to Multi-Agent Reinforcement Learning (MARL). ReF-ER was shown to outperform state of the art algorithms for continuous control in problems ranging from the OpenAI Gym to complex fluid flows. In MARL, the dependencies between the agents are included in the state-value estimator and the environment dynamics are modeled via the importance weights used by ReF-ER. In collaborative environments, we find the best performance when the value is estimated using individual rewards and we ignore the effects of ot","authors_text":"Daniel W\\\"alchli, Mustafa Zeqiri, Pascal Weber, Petros Koumoutsakos","cross_cats":["cs.AI","math.OC","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2022-03-24T19:59:43Z","title":"Remember and Forget Experience Replay for Multi-Agent Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.13319","kind":"arxiv","version":3},"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":"sha256:4271485ff1009bd1c701da5091ee651efcc6260673aa53008333b639d97749f7","target":"record","created_at":"2026-07-05T04:54:02Z","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":"f12a2a13f5ca2915957f4565757dc89c74ec51ca40d8341229744549fb6edfa8","cross_cats_sorted":["cs.AI","math.OC","stat.ML"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2022-03-24T19:59:43Z","title_canon_sha256":"4969d873fdfd6747b85d7f2db0445f42c0bf385a3ee31f2d368be10986f3adf7"},"schema_version":"1.0","source":{"id":"2203.13319","kind":"arxiv","version":3}},"canonical_sha256":"5c7c4aef135483b3bc2f3783e7902e6b0741e34b493ff86db07cefcff0bba6b7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5c7c4aef135483b3bc2f3783e7902e6b0741e34b493ff86db07cefcff0bba6b7","first_computed_at":"2026-07-05T04:54:02.644376Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:54:02.644376Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QGqlVZUBcno+z01vGMK8fjKjxdOQA9YC8y+woPAhnOJnGTVfoKMoBV5GkFyGhHnuJMH8wB2iRpWwKlt7uzgxAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:54:02.644789Z","signed_message":"canonical_sha256_bytes"},"source_id":"2203.13319","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4271485ff1009bd1c701da5091ee651efcc6260673aa53008333b639d97749f7","sha256:17b5c2588df90c0fc5d908c1a97e3a0cebba411f8146671c3093497ef0270f94"],"state_sha256":"ee5e1a2400a64ae6c2930d9305e275363b9256fea877057d5b1b7cde8b39c8d5"}