{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:VPX3E7ZPFWNKGEZVHLTMVGFG3R","short_pith_number":"pith:VPX3E7ZP","schema_version":"1.0","canonical_sha256":"abefb27f2f2d9aa313353ae6ca98a6dc75f01024ec28c00783d2a1dc4b340f6c","source":{"kind":"arxiv","id":"1811.12557","version":1},"attestation_state":"computed","paper":{"title":"Deep Multi-Agent Reinforcement Learning with Relevance Graphs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.MA","authors_text":"Aleksandra Malysheva, Aleksei Shpilman, Chae-Bong Sohn, Daniel Kudenko, Tegg Taekyong Sung","submitted_at":"2018-11-30T00:38:18Z","abstract_excerpt":"Over recent years, deep reinforcement learning has shown strong successes in complex single-agent tasks, and more recently this approach has also been applied to multi-agent domains. In this paper, we propose a novel approach, called MAGnet, to multi-agent reinforcement learning (MARL) that utilizes a relevance graph representation of the environment obtained by a self-attention mechanism, and a message-generation technique inspired by the NerveNet architecture. We applied our MAGnet approach to the Pommerman game and the results show that it significantly outperforms state-of-the-art MARL sol"},"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":"1811.12557","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2018-11-30T00:38:18Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"53c96029f13f92bd02c9aafa1c828cfbd42331a21bed2cd698fd66f65843ad9c","abstract_canon_sha256":"3788ec648bd4e8f7566cbff6de92d7efbc1ec7e4f54c0c1e93541f20c7f984ee"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:59:29.285895Z","signature_b64":"jg+YOBQ5YJU5SxB0eIJ6IoVVWULykdNgi/inZ656tgs3F55nUBdnMHQ7lp41zun74OHiiDreFSwfTpG61gvwCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"abefb27f2f2d9aa313353ae6ca98a6dc75f01024ec28c00783d2a1dc4b340f6c","last_reissued_at":"2026-05-17T23:59:29.285417Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:59:29.285417Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep Multi-Agent Reinforcement Learning with Relevance Graphs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.MA","authors_text":"Aleksandra Malysheva, Aleksei Shpilman, Chae-Bong Sohn, Daniel Kudenko, Tegg Taekyong Sung","submitted_at":"2018-11-30T00:38:18Z","abstract_excerpt":"Over recent years, deep reinforcement learning has shown strong successes in complex single-agent tasks, and more recently this approach has also been applied to multi-agent domains. In this paper, we propose a novel approach, called MAGnet, to multi-agent reinforcement learning (MARL) that utilizes a relevance graph representation of the environment obtained by a self-attention mechanism, and a message-generation technique inspired by the NerveNet architecture. We applied our MAGnet approach to the Pommerman game and the results show that it significantly outperforms state-of-the-art MARL sol"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.12557","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":"1811.12557","created_at":"2026-05-17T23:59:29.285488+00:00"},{"alias_kind":"arxiv_version","alias_value":"1811.12557v1","created_at":"2026-05-17T23:59:29.285488+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.12557","created_at":"2026-05-17T23:59:29.285488+00:00"},{"alias_kind":"pith_short_12","alias_value":"VPX3E7ZPFWNK","created_at":"2026-05-18T12:32:59.047623+00:00"},{"alias_kind":"pith_short_16","alias_value":"VPX3E7ZPFWNKGEZV","created_at":"2026-05-18T12:32:59.047623+00:00"},{"alias_kind":"pith_short_8","alias_value":"VPX3E7ZP","created_at":"2026-05-18T12:32:59.047623+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.08391","citing_title":"SACHI: Structured Agent Coordination via Holistic Information Integration in Multi-Agent Reinforcement Learning","ref_index":39,"is_internal_anchor":true},{"citing_arxiv_id":"2605.08391","citing_title":"SACHI: Structured Agent Coordination via Holistic Information Integration in Multi-Agent Reinforcement Learning","ref_index":39,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VPX3E7ZPFWNKGEZVHLTMVGFG3R","json":"https://pith.science/pith/VPX3E7ZPFWNKGEZVHLTMVGFG3R.json","graph_json":"https://pith.science/api/pith-number/VPX3E7ZPFWNKGEZVHLTMVGFG3R/graph.json","events_json":"https://pith.science/api/pith-number/VPX3E7ZPFWNKGEZVHLTMVGFG3R/events.json","paper":"https://pith.science/paper/VPX3E7ZP"},"agent_actions":{"view_html":"https://pith.science/pith/VPX3E7ZPFWNKGEZVHLTMVGFG3R","download_json":"https://pith.science/pith/VPX3E7ZPFWNKGEZVHLTMVGFG3R.json","view_paper":"https://pith.science/paper/VPX3E7ZP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1811.12557&json=true","fetch_graph":"https://pith.science/api/pith-number/VPX3E7ZPFWNKGEZVHLTMVGFG3R/graph.json","fetch_events":"https://pith.science/api/pith-number/VPX3E7ZPFWNKGEZVHLTMVGFG3R/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VPX3E7ZPFWNKGEZVHLTMVGFG3R/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VPX3E7ZPFWNKGEZVHLTMVGFG3R/action/storage_attestation","attest_author":"https://pith.science/pith/VPX3E7ZPFWNKGEZVHLTMVGFG3R/action/author_attestation","sign_citation":"https://pith.science/pith/VPX3E7ZPFWNKGEZVHLTMVGFG3R/action/citation_signature","submit_replication":"https://pith.science/pith/VPX3E7ZPFWNKGEZVHLTMVGFG3R/action/replication_record"}},"created_at":"2026-05-17T23:59:29.285488+00:00","updated_at":"2026-05-17T23:59:29.285488+00:00"}