{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:TMFYSKRCVEKG3DQ32FESQCUL72","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":"c5caf9610452588f1d64228de599d15b75235d6601742296a7b801b4dd8ab79d","cross_cats_sorted":["cs.AI","cs.MA"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-01-18T05:52:22Z","title_canon_sha256":"1a18662588578454111258c3e01a2af412eeecbedb48f5aa536a860d73ed7084"},"schema_version":"1.0","source":{"id":"2101.06890","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2101.06890","created_at":"2026-07-05T02:07:38Z"},{"alias_kind":"arxiv_version","alias_value":"2101.06890v1","created_at":"2026-07-05T02:07:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2101.06890","created_at":"2026-07-05T02:07:38Z"},{"alias_kind":"pith_short_12","alias_value":"TMFYSKRCVEKG","created_at":"2026-07-05T02:07:38Z"},{"alias_kind":"pith_short_16","alias_value":"TMFYSKRCVEKG3DQ3","created_at":"2026-07-05T02:07:38Z"},{"alias_kind":"pith_short_8","alias_value":"TMFYSKRC","created_at":"2026-07-05T02:07:38Z"}],"graph_snapshots":[{"event_id":"sha256:cfc25a15d0ea3eff56372b33043f8d27816cc12114c421df324ee397c6690279","target":"graph","created_at":"2026-07-05T02:07:38Z","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/2101.06890/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Training a multi-agent reinforcement learning (MARL) algorithm is more challenging than training a single-agent reinforcement learning algorithm, because the result of a multi-agent task strongly depends on the complex interactions among agents and their interactions with a stochastic and dynamic environment. We propose an algorithm that boosts MARL training using the biased action information of other agents based on a friend-or-foe concept. For a cooperative and competitive environment, there are generally two groups of agents: cooperative-agents and competitive-agents. In the proposed algor","authors_text":"Hayong Shin, Heechang Ryu, Jinkyoo Park","cross_cats":["cs.AI","cs.MA"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-01-18T05:52:22Z","title":"Cooperative and Competitive Biases for Multi-Agent Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2101.06890","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":"sha256:6bb1ee9b9e4abce4a8ba0ae2dda8be2e6a89325e468ce5cc8e6dea3cf91d9905","target":"record","created_at":"2026-07-05T02:07:38Z","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":"c5caf9610452588f1d64228de599d15b75235d6601742296a7b801b4dd8ab79d","cross_cats_sorted":["cs.AI","cs.MA"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-01-18T05:52:22Z","title_canon_sha256":"1a18662588578454111258c3e01a2af412eeecbedb48f5aa536a860d73ed7084"},"schema_version":"1.0","source":{"id":"2101.06890","kind":"arxiv","version":1}},"canonical_sha256":"9b0b892a22a9146d8e1bd149280a8bfe9953f9db99741a5f267942b84cf001e8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9b0b892a22a9146d8e1bd149280a8bfe9953f9db99741a5f267942b84cf001e8","first_computed_at":"2026-07-05T02:07:38.069635Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:07:38.069635Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UktA2GDQ/AuKqbfxl2zCLkAD7qXAQo7+23jeSLdSzOJXB+eLf3QuZT3vl9ZcSQ6vtGLOhY4sGdgR2oKB9d9NAw==","signature_status":"signed_v1","signed_at":"2026-07-05T02:07:38.070140Z","signed_message":"canonical_sha256_bytes"},"source_id":"2101.06890","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6bb1ee9b9e4abce4a8ba0ae2dda8be2e6a89325e468ce5cc8e6dea3cf91d9905","sha256:cfc25a15d0ea3eff56372b33043f8d27816cc12114c421df324ee397c6690279"],"state_sha256":"41d5e89b271acfa6d579f7de1eaec9699deac0a545cf65ed9192c4f908f6d9d3"}