{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:6RD3BRGAJC32OPMG4HRT2DWHXO","short_pith_number":"pith:6RD3BRGA","schema_version":"1.0","canonical_sha256":"f447b0c4c048b7a73d86e1e33d0ec7bb95d3b1f01dd5ad9bbf1f462ff3c470a6","source":{"kind":"arxiv","id":"1706.02275","version":4},"attestation_state":"computed","paper":{"title":"Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.NE"],"primary_cat":"cs.LG","authors_text":"Aviv Tamar, Igor Mordatch, Jean Harb, Pieter Abbeel, Ryan Lowe, Yi Wu","submitted_at":"2017-06-07T17:35:00Z","abstract_excerpt":"We explore deep reinforcement learning methods for multi-agent domains. We begin by analyzing the difficulty of traditional algorithms in the multi-agent case: Q-learning is challenged by an inherent non-stationarity of the environment, while policy gradient suffers from a variance that increases as the number of agents grows. We then present an adaptation of actor-critic methods that considers action policies of other agents and is able to successfully learn policies that require complex multi-agent coordination. Additionally, we introduce a training regimen utilizing an ensemble of policies "},"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":"1706.02275","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-06-07T17:35:00Z","cross_cats_sorted":["cs.AI","cs.NE"],"title_canon_sha256":"2d1b31e467eb321e40fda851ae1cdbe502d1479d44063a8b3a828f29056383b0","abstract_canon_sha256":"49df20f1ca08e203c94b018a35f73d224e0dc66d9dc0a6ccc085f2e41947b128"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:47:54.258244Z","signature_b64":"20RP/3pwK4XH0DdLXVJVfIaKiZ7YknxN1lpBz0QFFF9Qiq1G1ybHwpA38BW0kXJqNY4y5dsVKtVaFa9sFg6yCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f447b0c4c048b7a73d86e1e33d0ec7bb95d3b1f01dd5ad9bbf1f462ff3c470a6","last_reissued_at":"2026-07-05T00:47:54.257769Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:47:54.257769Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.NE"],"primary_cat":"cs.LG","authors_text":"Aviv Tamar, Igor Mordatch, Jean Harb, Pieter Abbeel, Ryan Lowe, Yi Wu","submitted_at":"2017-06-07T17:35:00Z","abstract_excerpt":"We explore deep reinforcement learning methods for multi-agent domains. We begin by analyzing the difficulty of traditional algorithms in the multi-agent case: Q-learning is challenged by an inherent non-stationarity of the environment, while policy gradient suffers from a variance that increases as the number of agents grows. We then present an adaptation of actor-critic methods that considers action policies of other agents and is able to successfully learn policies that require complex multi-agent coordination. Additionally, we introduce a training regimen utilizing an ensemble of policies "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1706.02275","kind":"arxiv","version":4},"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/1706.02275/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":"1706.02275","created_at":"2026-07-05T00:47:54.257827+00:00"},{"alias_kind":"arxiv_version","alias_value":"1706.02275v4","created_at":"2026-07-05T00:47:54.257827+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1706.02275","created_at":"2026-07-05T00:47:54.257827+00:00"},{"alias_kind":"pith_short_12","alias_value":"6RD3BRGAJC32","created_at":"2026-07-05T00:47:54.257827+00:00"},{"alias_kind":"pith_short_16","alias_value":"6RD3BRGAJC32OPMG","created_at":"2026-07-05T00:47:54.257827+00:00"},{"alias_kind":"pith_short_8","alias_value":"6RD3BRGA","created_at":"2026-07-05T00:47:54.257827+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":11,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.04750","citing_title":"Fog of Love: Engineering Virtuous Agent Behavior with Affinity-based Reinforcement Learning in a Game Environment","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2605.26286","citing_title":"Decoupled Delay Compensation: Enhancing Pre-trained MARL Policies via Learned Dynamics Filtering","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"1907.03053","citing_title":"A Communication-Efficient Multi-Agent Actor-Critic Algorithm for Distributed Reinforcement Learning","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2502.00558","citing_title":"Asynchronous Cooperative Multi-Agent Reinforcement Learning with Limited Communication","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2506.07548","citing_title":"Overcoming Environmental Meta-Stationarity in MARL via Adaptive Curriculum and Counterfactual Group Advantage","ref_index":56,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14235","citing_title":"Quantum Advantage in Multi Agent Reinforcement Learning","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08404","citing_title":"Built Environment Reasoning from Remote Sensing Imagery Using Large Vision--Language Models","ref_index":83,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05236","citing_title":"Topology-Driven Anti-Entanglement Control for Soft Robots","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18190","citing_title":"Scalable Neighborhood-Based Multi-Agent Actor-Critic","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01362","citing_title":"Coordination Architecture Shapes Continuous Demand Response Outcomes in Building Districts","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2604.25848","citing_title":"A Distributionally Robust Reinforcement Learning Framework for Constrained Urban EV Dispatch","ref_index":31,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6RD3BRGAJC32OPMG4HRT2DWHXO","json":"https://pith.science/pith/6RD3BRGAJC32OPMG4HRT2DWHXO.json","graph_json":"https://pith.science/api/pith-number/6RD3BRGAJC32OPMG4HRT2DWHXO/graph.json","events_json":"https://pith.science/api/pith-number/6RD3BRGAJC32OPMG4HRT2DWHXO/events.json","paper":"https://pith.science/paper/6RD3BRGA"},"agent_actions":{"view_html":"https://pith.science/pith/6RD3BRGAJC32OPMG4HRT2DWHXO","download_json":"https://pith.science/pith/6RD3BRGAJC32OPMG4HRT2DWHXO.json","view_paper":"https://pith.science/paper/6RD3BRGA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1706.02275&json=true","fetch_graph":"https://pith.science/api/pith-number/6RD3BRGAJC32OPMG4HRT2DWHXO/graph.json","fetch_events":"https://pith.science/api/pith-number/6RD3BRGAJC32OPMG4HRT2DWHXO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6RD3BRGAJC32OPMG4HRT2DWHXO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6RD3BRGAJC32OPMG4HRT2DWHXO/action/storage_attestation","attest_author":"https://pith.science/pith/6RD3BRGAJC32OPMG4HRT2DWHXO/action/author_attestation","sign_citation":"https://pith.science/pith/6RD3BRGAJC32OPMG4HRT2DWHXO/action/citation_signature","submit_replication":"https://pith.science/pith/6RD3BRGAJC32OPMG4HRT2DWHXO/action/replication_record"}},"created_at":"2026-07-05T00:47:54.257827+00:00","updated_at":"2026-07-05T00:47:54.257827+00:00"}