{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:QEK6NAKD3JCPXIGY4SCBO5E7GA","short_pith_number":"pith:QEK6NAKD","schema_version":"1.0","canonical_sha256":"8115e68143da44fba0d8e48417749f3025c0d356b8b2768c9b37668bbebed1fa","source":{"kind":"arxiv","id":"1702.08887","version":3},"attestation_state":"computed","paper":{"title":"Stabilising Experience Replay for Deep Multi-Agent Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.MA"],"primary_cat":"cs.AI","authors_text":"Gregory Farquhar, Jakob Foerster, Nantas Nardelli, Philip H. S. Torr, Pushmeet Kohli, Shimon Whiteson, Triantafyllos Afouras","submitted_at":"2017-02-28T17:56:41Z","abstract_excerpt":"Many real-world problems, such as network packet routing and urban traffic control, are naturally modeled as multi-agent reinforcement learning (RL) problems. However, existing multi-agent RL methods typically scale poorly in the problem size. Therefore, a key challenge is to translate the success of deep learning on single-agent RL to the multi-agent setting. A major stumbling block is that independent Q-learning, the most popular multi-agent RL method, introduces nonstationarity that makes it incompatible with the experience replay memory on which deep Q-learning relies. This paper proposes "},"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":"1702.08887","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-02-28T17:56:41Z","cross_cats_sorted":["cs.LG","cs.MA"],"title_canon_sha256":"47777c60637b1823e6aec0bde0c94420d4911c5fe0061113b2a8c36af4199861","abstract_canon_sha256":"43aa1e5a054011e3e969d73a65ba9fc0767b6d6efb181db3f49a9b0d778617f6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:15:37.844714Z","signature_b64":"1CycDfOdjO8HUiOpP6gBFp34CsP64WRbnNZqrt5p/9a4y0sqifpDhTqxWvIRR8UC+gW8KS1kOcoukaWWUsHCBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8115e68143da44fba0d8e48417749f3025c0d356b8b2768c9b37668bbebed1fa","last_reissued_at":"2026-05-18T00:15:37.844055Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:15:37.844055Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Stabilising Experience Replay for Deep Multi-Agent Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.MA"],"primary_cat":"cs.AI","authors_text":"Gregory Farquhar, Jakob Foerster, Nantas Nardelli, Philip H. S. Torr, Pushmeet Kohli, Shimon Whiteson, Triantafyllos Afouras","submitted_at":"2017-02-28T17:56:41Z","abstract_excerpt":"Many real-world problems, such as network packet routing and urban traffic control, are naturally modeled as multi-agent reinforcement learning (RL) problems. However, existing multi-agent RL methods typically scale poorly in the problem size. Therefore, a key challenge is to translate the success of deep learning on single-agent RL to the multi-agent setting. A major stumbling block is that independent Q-learning, the most popular multi-agent RL method, introduces nonstationarity that makes it incompatible with the experience replay memory on which deep Q-learning relies. This paper proposes "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1702.08887","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":""},"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":"1702.08887","created_at":"2026-05-18T00:15:37.844135+00:00"},{"alias_kind":"arxiv_version","alias_value":"1702.08887v3","created_at":"2026-05-18T00:15:37.844135+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1702.08887","created_at":"2026-05-18T00:15:37.844135+00:00"},{"alias_kind":"pith_short_12","alias_value":"QEK6NAKD3JCP","created_at":"2026-05-18T12:31:37.085036+00:00"},{"alias_kind":"pith_short_16","alias_value":"QEK6NAKD3JCPXIGY","created_at":"2026-05-18T12:31:37.085036+00:00"},{"alias_kind":"pith_short_8","alias_value":"QEK6NAKD","created_at":"2026-05-18T12:31:37.085036+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"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":14,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QEK6NAKD3JCPXIGY4SCBO5E7GA","json":"https://pith.science/pith/QEK6NAKD3JCPXIGY4SCBO5E7GA.json","graph_json":"https://pith.science/api/pith-number/QEK6NAKD3JCPXIGY4SCBO5E7GA/graph.json","events_json":"https://pith.science/api/pith-number/QEK6NAKD3JCPXIGY4SCBO5E7GA/events.json","paper":"https://pith.science/paper/QEK6NAKD"},"agent_actions":{"view_html":"https://pith.science/pith/QEK6NAKD3JCPXIGY4SCBO5E7GA","download_json":"https://pith.science/pith/QEK6NAKD3JCPXIGY4SCBO5E7GA.json","view_paper":"https://pith.science/paper/QEK6NAKD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1702.08887&json=true","fetch_graph":"https://pith.science/api/pith-number/QEK6NAKD3JCPXIGY4SCBO5E7GA/graph.json","fetch_events":"https://pith.science/api/pith-number/QEK6NAKD3JCPXIGY4SCBO5E7GA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QEK6NAKD3JCPXIGY4SCBO5E7GA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QEK6NAKD3JCPXIGY4SCBO5E7GA/action/storage_attestation","attest_author":"https://pith.science/pith/QEK6NAKD3JCPXIGY4SCBO5E7GA/action/author_attestation","sign_citation":"https://pith.science/pith/QEK6NAKD3JCPXIGY4SCBO5E7GA/action/citation_signature","submit_replication":"https://pith.science/pith/QEK6NAKD3JCPXIGY4SCBO5E7GA/action/replication_record"}},"created_at":"2026-05-18T00:15:37.844135+00:00","updated_at":"2026-05-18T00:15:37.844135+00:00"}