{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:Y3OPU3MWUWRMFPCKAGCGR7XNXU","short_pith_number":"pith:Y3OPU3MW","schema_version":"1.0","canonical_sha256":"c6dcfa6d96a5a2c2bc4a018468feedbd0e4ef0db030d0530197c9b4b1b4e0386","source":{"kind":"arxiv","id":"2102.04402","version":2},"attestation_state":"computed","paper":{"title":"Contrasting Centralized and Decentralized Critics in Multi-Agent Reinforcement Learning","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Brett Daley, Christopher Amato, Xueguang Lyu, Yuchen Xiao","submitted_at":"2021-02-08T18:08:11Z","abstract_excerpt":"Centralized Training for Decentralized Execution, where agents are trained offline using centralized information but execute in a decentralized manner online, has gained popularity in the multi-agent reinforcement learning community. In particular, actor-critic methods with a centralized critic and decentralized actors are a common instance of this idea. However, the implications of using a centralized critic in this context are not fully discussed and understood even though it is the standard choice of many algorithms. We therefore formally analyze centralized and decentralized critic approac"},"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":"2102.04402","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2021-02-08T18:08:11Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"61593b2d81da82ea534a49d41d2eb4919c8e32119b17913afb6c0132426bdb17","abstract_canon_sha256":"d50004177199dd6c51456580bd50b7ffc266cab3e2581e0d04d38402eab2baee"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:37:11.025773Z","signature_b64":"qV3+hMGMgLgS8gye1VWdF7I9T8Uszu4GshEwnWJ305/2HfHNNd1X++ywlIYKH5K+5aVl2iXd4+5Dtgo+uJrtAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c6dcfa6d96a5a2c2bc4a018468feedbd0e4ef0db030d0530197c9b4b1b4e0386","last_reissued_at":"2026-07-05T03:37:11.025274Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:37:11.025274Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Contrasting Centralized and Decentralized Critics in Multi-Agent Reinforcement Learning","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Brett Daley, Christopher Amato, Xueguang Lyu, Yuchen Xiao","submitted_at":"2021-02-08T18:08:11Z","abstract_excerpt":"Centralized Training for Decentralized Execution, where agents are trained offline using centralized information but execute in a decentralized manner online, has gained popularity in the multi-agent reinforcement learning community. In particular, actor-critic methods with a centralized critic and decentralized actors are a common instance of this idea. However, the implications of using a centralized critic in this context are not fully discussed and understood even though it is the standard choice of many algorithms. We therefore formally analyze centralized and decentralized critic approac"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.04402","kind":"arxiv","version":2},"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/2102.04402/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":"2102.04402","created_at":"2026-07-05T03:37:11.025335+00:00"},{"alias_kind":"arxiv_version","alias_value":"2102.04402v2","created_at":"2026-07-05T03:37:11.025335+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.04402","created_at":"2026-07-05T03:37:11.025335+00:00"},{"alias_kind":"pith_short_12","alias_value":"Y3OPU3MWUWRM","created_at":"2026-07-05T03:37:11.025335+00:00"},{"alias_kind":"pith_short_16","alias_value":"Y3OPU3MWUWRMFPCK","created_at":"2026-07-05T03:37:11.025335+00:00"},{"alias_kind":"pith_short_8","alias_value":"Y3OPU3MW","created_at":"2026-07-05T03:37:11.025335+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":9,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.12655","citing_title":"Robust Instruction Compliance in Cooperative Multi-Agent Reinforcement Learning","ref_index":113,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00268","citing_title":"Fast Rates in $\\alpha$-Potential Games via Regularized Mirror Descent","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00264","citing_title":"Pessimism-Free Offline Learning in General-Sum Games via KL Regularization","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2508.01049","citing_title":"Centralized Adaptive Sampling for Reliable Co-Training of Independent Multi-Agent Policies","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2601.21972","citing_title":"Learning Decentralized LLM Collaboration with Multi-Agent Actor Critic","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05573","citing_title":"AstroAlertBench: Evaluating the Accuracy, Reasoning, and Honesty of Multimodal LLMs in Astronomical Classification","ref_index":62,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06595","citing_title":"Cross-Modal Navigation with Multi-Agent Reinforcement Learning","ref_index":77,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00268","citing_title":"Fast Rates in $\\alpha$-Potential Games via Regularized Mirror Descent","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00264","citing_title":"Pessimism-Free Offline Learning in General-Sum Games via KL Regularization","ref_index":15,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Y3OPU3MWUWRMFPCKAGCGR7XNXU","json":"https://pith.science/pith/Y3OPU3MWUWRMFPCKAGCGR7XNXU.json","graph_json":"https://pith.science/api/pith-number/Y3OPU3MWUWRMFPCKAGCGR7XNXU/graph.json","events_json":"https://pith.science/api/pith-number/Y3OPU3MWUWRMFPCKAGCGR7XNXU/events.json","paper":"https://pith.science/paper/Y3OPU3MW"},"agent_actions":{"view_html":"https://pith.science/pith/Y3OPU3MWUWRMFPCKAGCGR7XNXU","download_json":"https://pith.science/pith/Y3OPU3MWUWRMFPCKAGCGR7XNXU.json","view_paper":"https://pith.science/paper/Y3OPU3MW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2102.04402&json=true","fetch_graph":"https://pith.science/api/pith-number/Y3OPU3MWUWRMFPCKAGCGR7XNXU/graph.json","fetch_events":"https://pith.science/api/pith-number/Y3OPU3MWUWRMFPCKAGCGR7XNXU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Y3OPU3MWUWRMFPCKAGCGR7XNXU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Y3OPU3MWUWRMFPCKAGCGR7XNXU/action/storage_attestation","attest_author":"https://pith.science/pith/Y3OPU3MWUWRMFPCKAGCGR7XNXU/action/author_attestation","sign_citation":"https://pith.science/pith/Y3OPU3MWUWRMFPCKAGCGR7XNXU/action/citation_signature","submit_replication":"https://pith.science/pith/Y3OPU3MWUWRMFPCKAGCGR7XNXU/action/replication_record"}},"created_at":"2026-07-05T03:37:11.025335+00:00","updated_at":"2026-07-05T03:37:11.025335+00:00"}