{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:VPX3E7ZPFWNKGEZVHLTMVGFG3R","short_pith_number":"pith:VPX3E7ZP","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"},"canonical_sha256":"abefb27f2f2d9aa313353ae6ca98a6dc75f01024ec28c00783d2a1dc4b340f6c","source":{"kind":"arxiv","id":"1811.12557","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1811.12557","created_at":"2026-05-17T23:59:29Z"},{"alias_kind":"arxiv_version","alias_value":"1811.12557v1","created_at":"2026-05-17T23:59:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.12557","created_at":"2026-05-17T23:59:29Z"},{"alias_kind":"pith_short_12","alias_value":"VPX3E7ZPFWNK","created_at":"2026-05-18T12:32:59Z"},{"alias_kind":"pith_short_16","alias_value":"VPX3E7ZPFWNKGEZV","created_at":"2026-05-18T12:32:59Z"},{"alias_kind":"pith_short_8","alias_value":"VPX3E7ZP","created_at":"2026-05-18T12:32:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:VPX3E7ZPFWNKGEZVHLTMVGFG3R","target":"record","payload":{"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"},"canonical_sha256":"abefb27f2f2d9aa313353ae6ca98a6dc75f01024ec28c00783d2a1dc4b340f6c","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"},"source_kind":"arxiv","source_id":"1811.12557","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:59:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WfgP7dyFSXDYYP/F+ahy43zmH0xXeYoCDNSpi58ueU2VfhnYqHIiIa3AYFNz9QDQlkLvZA7AdI/XjaCjUHBlAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-11T22:54:08.169787Z"},"content_sha256":"5b406bf4fac8012cfda5dd0b5ad8825c8fe91ec1dfba508cb34b621d258bb173","schema_version":"1.0","event_id":"sha256:5b406bf4fac8012cfda5dd0b5ad8825c8fe91ec1dfba508cb34b621d258bb173"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:VPX3E7ZPFWNKGEZVHLTMVGFG3R","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:59:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hNoxxhLPB+thwI4wX8iruM43mU1zaA6/yqNFfr4C5yZUG1v07XEWRaO1lTNXlGFYteEfqcxfPqumJWmaQjm+AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-11T22:54:08.170557Z"},"content_sha256":"d5648bb33a004d52fd741e6a1f2732492df590b7c6985ff97456c89187a9df5c","schema_version":"1.0","event_id":"sha256:d5648bb33a004d52fd741e6a1f2732492df590b7c6985ff97456c89187a9df5c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VPX3E7ZPFWNKGEZVHLTMVGFG3R/bundle.json","state_url":"https://pith.science/pith/VPX3E7ZPFWNKGEZVHLTMVGFG3R/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VPX3E7ZPFWNKGEZVHLTMVGFG3R/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-11T22:54:08Z","links":{"resolver":"https://pith.science/pith/VPX3E7ZPFWNKGEZVHLTMVGFG3R","bundle":"https://pith.science/pith/VPX3E7ZPFWNKGEZVHLTMVGFG3R/bundle.json","state":"https://pith.science/pith/VPX3E7ZPFWNKGEZVHLTMVGFG3R/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VPX3E7ZPFWNKGEZVHLTMVGFG3R/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:VPX3E7ZPFWNKGEZVHLTMVGFG3R","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"3788ec648bd4e8f7566cbff6de92d7efbc1ec7e4f54c0c1e93541f20c7f984ee","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2018-11-30T00:38:18Z","title_canon_sha256":"53c96029f13f92bd02c9aafa1c828cfbd42331a21bed2cd698fd66f65843ad9c"},"schema_version":"1.0","source":{"id":"1811.12557","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1811.12557","created_at":"2026-05-17T23:59:29Z"},{"alias_kind":"arxiv_version","alias_value":"1811.12557v1","created_at":"2026-05-17T23:59:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.12557","created_at":"2026-05-17T23:59:29Z"},{"alias_kind":"pith_short_12","alias_value":"VPX3E7ZPFWNK","created_at":"2026-05-18T12:32:59Z"},{"alias_kind":"pith_short_16","alias_value":"VPX3E7ZPFWNKGEZV","created_at":"2026-05-18T12:32:59Z"},{"alias_kind":"pith_short_8","alias_value":"VPX3E7ZP","created_at":"2026-05-18T12:32:59Z"}],"graph_snapshots":[{"event_id":"sha256:d5648bb33a004d52fd741e6a1f2732492df590b7c6985ff97456c89187a9df5c","target":"graph","created_at":"2026-05-17T23:59:29Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"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","authors_text":"Aleksandra Malysheva, Aleksei Shpilman, Chae-Bong Sohn, Daniel Kudenko, Tegg Taekyong Sung","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2018-11-30T00:38:18Z","title":"Deep Multi-Agent Reinforcement Learning with Relevance Graphs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.12557","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:5b406bf4fac8012cfda5dd0b5ad8825c8fe91ec1dfba508cb34b621d258bb173","target":"record","created_at":"2026-05-17T23:59:29Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"3788ec648bd4e8f7566cbff6de92d7efbc1ec7e4f54c0c1e93541f20c7f984ee","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2018-11-30T00:38:18Z","title_canon_sha256":"53c96029f13f92bd02c9aafa1c828cfbd42331a21bed2cd698fd66f65843ad9c"},"schema_version":"1.0","source":{"id":"1811.12557","kind":"arxiv","version":1}},"canonical_sha256":"abefb27f2f2d9aa313353ae6ca98a6dc75f01024ec28c00783d2a1dc4b340f6c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"abefb27f2f2d9aa313353ae6ca98a6dc75f01024ec28c00783d2a1dc4b340f6c","first_computed_at":"2026-05-17T23:59:29.285417Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:59:29.285417Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jg+YOBQ5YJU5SxB0eIJ6IoVVWULykdNgi/inZ656tgs3F55nUBdnMHQ7lp41zun74OHiiDreFSwfTpG61gvwCw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:59:29.285895Z","signed_message":"canonical_sha256_bytes"},"source_id":"1811.12557","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5b406bf4fac8012cfda5dd0b5ad8825c8fe91ec1dfba508cb34b621d258bb173","sha256:d5648bb33a004d52fd741e6a1f2732492df590b7c6985ff97456c89187a9df5c"],"state_sha256":"e353119db5de76eabdbd34b85eb82a3da90a56e9815dca5aeef103634a218896"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WHb92n7Ht4gocZKEC7lzvuBhKLK7VynAjmNGuavsCs77ihJeEVFHAMrx2reAqFln/Eezv3GX6OYLF5yXALwoCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-11T22:54:08.174947Z","bundle_sha256":"5177674d065828966f048425e24b0eded0f0f98f3e83d4cc07b9e08415267b37"}}