{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:N2EVZ3ZXYEBIRBHOSJFBDOFO3M","short_pith_number":"pith:N2EVZ3ZX","schema_version":"1.0","canonical_sha256":"6e895cef37c1028884ee924a11b8aedb2611dbdc189e55feda4c391b60e088b6","source":{"kind":"arxiv","id":"1906.04737","version":1},"attestation_state":"computed","paper":{"title":"Dealing with Non-Stationarity in Multi-Agent Deep Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MA","stat.ML"],"primary_cat":"cs.LG","authors_text":"Arrasy Rahman, Filippos Christianos, Georgios Papoudakis, Stefano V. Albrecht","submitted_at":"2019-06-11T09:42:00Z","abstract_excerpt":"Recent developments in deep reinforcement learning are concerned with creating decision-making agents which can perform well in various complex domains. A particular approach which has received increasing attention is multi-agent reinforcement learning, in which multiple agents learn concurrently to coordinate their actions. In such multi-agent environments, additional learning problems arise due to the continually changing decision-making policies of agents. This paper surveys recent works that address the non-stationarity problem in multi-agent deep reinforcement learning. The surveyed metho"},"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":"1906.04737","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-11T09:42:00Z","cross_cats_sorted":["cs.AI","cs.MA","stat.ML"],"title_canon_sha256":"74b12702bc62a77f429d48398c263c2ece5a988bd2fe8df05e7c5ae7f3a4d532","abstract_canon_sha256":"1c82d04a14c6ecab04fb2e946049fbd4845cc15ac887db6a3e16ccc440aa188f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:43:32.373590Z","signature_b64":"OJeSNua5bS63msmG7tDNZ01AkSdaMSjOYliPFPaWgIx2vxQfkICoRxZvcqGGnn472fe7ZWX2dK9nKnbbY93vBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6e895cef37c1028884ee924a11b8aedb2611dbdc189e55feda4c391b60e088b6","last_reissued_at":"2026-05-17T23:43:32.372998Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:43:32.372998Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dealing with Non-Stationarity in Multi-Agent Deep Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MA","stat.ML"],"primary_cat":"cs.LG","authors_text":"Arrasy Rahman, Filippos Christianos, Georgios Papoudakis, Stefano V. Albrecht","submitted_at":"2019-06-11T09:42:00Z","abstract_excerpt":"Recent developments in deep reinforcement learning are concerned with creating decision-making agents which can perform well in various complex domains. A particular approach which has received increasing attention is multi-agent reinforcement learning, in which multiple agents learn concurrently to coordinate their actions. In such multi-agent environments, additional learning problems arise due to the continually changing decision-making policies of agents. This paper surveys recent works that address the non-stationarity problem in multi-agent deep reinforcement learning. The surveyed metho"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.04737","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1906.04737","created_at":"2026-05-17T23:43:32.373089+00:00"},{"alias_kind":"arxiv_version","alias_value":"1906.04737v1","created_at":"2026-05-17T23:43:32.373089+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.04737","created_at":"2026-05-17T23:43:32.373089+00:00"},{"alias_kind":"pith_short_12","alias_value":"N2EVZ3ZXYEBI","created_at":"2026-05-18T12:33:24.271573+00:00"},{"alias_kind":"pith_short_16","alias_value":"N2EVZ3ZXYEBIRBHO","created_at":"2026-05-18T12:33:24.271573+00:00"},{"alias_kind":"pith_short_8","alias_value":"N2EVZ3ZX","created_at":"2026-05-18T12:33:24.271573+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":5,"sample":[{"citing_arxiv_id":"2605.23027","citing_title":"PIMbot: A Self-Adaptive Attack Framework for Adversarial Manipulation of Multi-Robot Reinforcement Learning","ref_index":51,"is_internal_anchor":true},{"citing_arxiv_id":"2603.18396","citing_title":"RE-SAC: Disentangling aleatoric and epistemic risks in bus fleet control: A stable and robust ensemble DRL approach","ref_index":24,"is_internal_anchor":true},{"citing_arxiv_id":"2605.18281","citing_title":"Temporal Task Diversity: Inductive Biases Under Non-Stationarity in Synthetic Sequence Modelling","ref_index":31,"is_internal_anchor":true},{"citing_arxiv_id":"2506.07548","citing_title":"Overcoming Environmental Meta-Stationarity in MARL via Adaptive Curriculum and Counterfactual Group Advantage","ref_index":21,"is_internal_anchor":true},{"citing_arxiv_id":"2605.13131","citing_title":"ERPPO: Entropy Regularization-based Proximal Policy Optimization","ref_index":64,"is_internal_anchor":true},{"citing_arxiv_id":"2604.09028","citing_title":"Plasticity-Enhanced Multi-Agent Mixture of Experts for Dynamic Objective Adaptation in UAVs-Assisted Emergency Communication Networks","ref_index":30,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/N2EVZ3ZXYEBIRBHOSJFBDOFO3M","json":"https://pith.science/pith/N2EVZ3ZXYEBIRBHOSJFBDOFO3M.json","graph_json":"https://pith.science/api/pith-number/N2EVZ3ZXYEBIRBHOSJFBDOFO3M/graph.json","events_json":"https://pith.science/api/pith-number/N2EVZ3ZXYEBIRBHOSJFBDOFO3M/events.json","paper":"https://pith.science/paper/N2EVZ3ZX"},"agent_actions":{"view_html":"https://pith.science/pith/N2EVZ3ZXYEBIRBHOSJFBDOFO3M","download_json":"https://pith.science/pith/N2EVZ3ZXYEBIRBHOSJFBDOFO3M.json","view_paper":"https://pith.science/paper/N2EVZ3ZX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1906.04737&json=true","fetch_graph":"https://pith.science/api/pith-number/N2EVZ3ZXYEBIRBHOSJFBDOFO3M/graph.json","fetch_events":"https://pith.science/api/pith-number/N2EVZ3ZXYEBIRBHOSJFBDOFO3M/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/N2EVZ3ZXYEBIRBHOSJFBDOFO3M/action/timestamp_anchor","attest_storage":"https://pith.science/pith/N2EVZ3ZXYEBIRBHOSJFBDOFO3M/action/storage_attestation","attest_author":"https://pith.science/pith/N2EVZ3ZXYEBIRBHOSJFBDOFO3M/action/author_attestation","sign_citation":"https://pith.science/pith/N2EVZ3ZXYEBIRBHOSJFBDOFO3M/action/citation_signature","submit_replication":"https://pith.science/pith/N2EVZ3ZXYEBIRBHOSJFBDOFO3M/action/replication_record"}},"created_at":"2026-05-17T23:43:32.373089+00:00","updated_at":"2026-05-17T23:43:32.373089+00:00"}