{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:RLC37BYWYDJUKS75Y5M3CWCVMF","short_pith_number":"pith:RLC37BYW","schema_version":"1.0","canonical_sha256":"8ac5bf8716c0d3454bfdc759b15855616ac893dda56e2a9babb1ad8e25493de4","source":{"kind":"arxiv","id":"2102.08159","version":3},"attestation_state":"computed","paper":{"title":"RMIX: Learning Risk-Sensitive Policies for Cooperative Reinforcement Learning Agents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.MA"],"primary_cat":"cs.LG","authors_text":"Bo An, Rundong Wang, Runsheng Yu, Svetlana Obraztsova, Wei Qiu, Xinrun Wang, Xu He, Zinovi Rabinovich","submitted_at":"2021-02-16T13:58:25Z","abstract_excerpt":"Current value-based multi-agent reinforcement learning methods optimize individual Q values to guide individuals' behaviours via centralized training with decentralized execution (CTDE). However, such expected, i.e., risk-neutral, Q value is not sufficient even with CTDE due to the randomness of rewards and the uncertainty in environments, which causes the failure of these methods to train coordinating agents in complex environments. To address these issues, we propose RMIX, a novel cooperative MARL method with the Conditional Value at Risk (CVaR) measure over the learned distributions of indi"},"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":"2102.08159","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-02-16T13:58:25Z","cross_cats_sorted":["cs.MA"],"title_canon_sha256":"891eb04550a0739d76172866baee9a2037151aae5db41bf21d0b7e88d0288bfd","abstract_canon_sha256":"7b80297d1a7d8bd6d3b13546011e0f8462f41a08fa2e7ec000a7a3d12b26739c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:24:53.978895Z","signature_b64":"SfEqtjAZ4vXO0k1m0hIQC7I7vJNdlgCcW1nYTCG7Csm10yiK+jb59m917jmJXlYwOyC5cyNXhCAhW87Jz26ICg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8ac5bf8716c0d3454bfdc759b15855616ac893dda56e2a9babb1ad8e25493de4","last_reissued_at":"2026-07-05T02:24:53.978428Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:24:53.978428Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RMIX: Learning Risk-Sensitive Policies for Cooperative Reinforcement Learning Agents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.MA"],"primary_cat":"cs.LG","authors_text":"Bo An, Rundong Wang, Runsheng Yu, Svetlana Obraztsova, Wei Qiu, Xinrun Wang, Xu He, Zinovi Rabinovich","submitted_at":"2021-02-16T13:58:25Z","abstract_excerpt":"Current value-based multi-agent reinforcement learning methods optimize individual Q values to guide individuals' behaviours via centralized training with decentralized execution (CTDE). However, such expected, i.e., risk-neutral, Q value is not sufficient even with CTDE due to the randomness of rewards and the uncertainty in environments, which causes the failure of these methods to train coordinating agents in complex environments. To address these issues, we propose RMIX, a novel cooperative MARL method with the Conditional Value at Risk (CVaR) measure over the learned distributions of indi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.08159","kind":"arxiv","version":3},"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/2102.08159/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":"2102.08159","created_at":"2026-07-05T02:24:53.978504+00:00"},{"alias_kind":"arxiv_version","alias_value":"2102.08159v3","created_at":"2026-07-05T02:24:53.978504+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.08159","created_at":"2026-07-05T02:24:53.978504+00:00"},{"alias_kind":"pith_short_12","alias_value":"RLC37BYWYDJU","created_at":"2026-07-05T02:24:53.978504+00:00"},{"alias_kind":"pith_short_16","alias_value":"RLC37BYWYDJUKS75","created_at":"2026-07-05T02:24:53.978504+00:00"},{"alias_kind":"pith_short_8","alias_value":"RLC37BYW","created_at":"2026-07-05T02:24:53.978504+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/RLC37BYWYDJUKS75Y5M3CWCVMF","json":"https://pith.science/pith/RLC37BYWYDJUKS75Y5M3CWCVMF.json","graph_json":"https://pith.science/api/pith-number/RLC37BYWYDJUKS75Y5M3CWCVMF/graph.json","events_json":"https://pith.science/api/pith-number/RLC37BYWYDJUKS75Y5M3CWCVMF/events.json","paper":"https://pith.science/paper/RLC37BYW"},"agent_actions":{"view_html":"https://pith.science/pith/RLC37BYWYDJUKS75Y5M3CWCVMF","download_json":"https://pith.science/pith/RLC37BYWYDJUKS75Y5M3CWCVMF.json","view_paper":"https://pith.science/paper/RLC37BYW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2102.08159&json=true","fetch_graph":"https://pith.science/api/pith-number/RLC37BYWYDJUKS75Y5M3CWCVMF/graph.json","fetch_events":"https://pith.science/api/pith-number/RLC37BYWYDJUKS75Y5M3CWCVMF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RLC37BYWYDJUKS75Y5M3CWCVMF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RLC37BYWYDJUKS75Y5M3CWCVMF/action/storage_attestation","attest_author":"https://pith.science/pith/RLC37BYWYDJUKS75Y5M3CWCVMF/action/author_attestation","sign_citation":"https://pith.science/pith/RLC37BYWYDJUKS75Y5M3CWCVMF/action/citation_signature","submit_replication":"https://pith.science/pith/RLC37BYWYDJUKS75Y5M3CWCVMF/action/replication_record"}},"created_at":"2026-07-05T02:24:53.978504+00:00","updated_at":"2026-07-05T02:24:53.978504+00:00"}