{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:N2EVZ3ZXYEBIRBHOSJFBDOFO3M","short_pith_number":"pith:N2EVZ3ZX","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"},"canonical_sha256":"6e895cef37c1028884ee924a11b8aedb2611dbdc189e55feda4c391b60e088b6","source":{"kind":"arxiv","id":"1906.04737","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.04737","created_at":"2026-05-17T23:43:32Z"},{"alias_kind":"arxiv_version","alias_value":"1906.04737v1","created_at":"2026-05-17T23:43:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.04737","created_at":"2026-05-17T23:43:32Z"},{"alias_kind":"pith_short_12","alias_value":"N2EVZ3ZXYEBI","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_16","alias_value":"N2EVZ3ZXYEBIRBHO","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_8","alias_value":"N2EVZ3ZX","created_at":"2026-05-18T12:33:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:N2EVZ3ZXYEBIRBHOSJFBDOFO3M","target":"record","payload":{"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"},"canonical_sha256":"6e895cef37c1028884ee924a11b8aedb2611dbdc189e55feda4c391b60e088b6","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"},"source_kind":"arxiv","source_id":"1906.04737","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":"2026-05-17T23:43:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EmVFzpGxE4guRdYYAdsb6kYpNxiUFqkzU1mBsqPYnz33OHEDkXcWz8+Ip0hsSPpnrumbrrHj52kH3fGJ6T7NCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T17:17:36.916097Z"},"content_sha256":"0555df4ed353baff6f7f581c2455bca05b85ad04da8dbc303c5da078c675d843","schema_version":"1.0","event_id":"sha256:0555df4ed353baff6f7f581c2455bca05b85ad04da8dbc303c5da078c675d843"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:N2EVZ3ZXYEBIRBHOSJFBDOFO3M","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:43:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HA/hza2WTKqpgqYwWP7Dlrbahd9Wp1s6vgHQWsL6jwkUGaWOqBAsCRlVJmx+muVYvppSTGjQL609L2vEp2ArDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T17:17:36.916747Z"},"content_sha256":"eb404d4a7e7cd644893b03d8d504e956993114cb24af10aae43c76b0c5e833ba","schema_version":"1.0","event_id":"sha256:eb404d4a7e7cd644893b03d8d504e956993114cb24af10aae43c76b0c5e833ba"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/N2EVZ3ZXYEBIRBHOSJFBDOFO3M/bundle.json","state_url":"https://pith.science/pith/N2EVZ3ZXYEBIRBHOSJFBDOFO3M/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/N2EVZ3ZXYEBIRBHOSJFBDOFO3M/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":"2026-05-25T17:17:36Z","links":{"resolver":"https://pith.science/pith/N2EVZ3ZXYEBIRBHOSJFBDOFO3M","bundle":"https://pith.science/pith/N2EVZ3ZXYEBIRBHOSJFBDOFO3M/bundle.json","state":"https://pith.science/pith/N2EVZ3ZXYEBIRBHOSJFBDOFO3M/state.json","well_known_bundle":"https://pith.science/.well-known/pith/N2EVZ3ZXYEBIRBHOSJFBDOFO3M/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:N2EVZ3ZXYEBIRBHOSJFBDOFO3M","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":"1c82d04a14c6ecab04fb2e946049fbd4845cc15ac887db6a3e16ccc440aa188f","cross_cats_sorted":["cs.AI","cs.MA","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-11T09:42:00Z","title_canon_sha256":"74b12702bc62a77f429d48398c263c2ece5a988bd2fe8df05e7c5ae7f3a4d532"},"schema_version":"1.0","source":{"id":"1906.04737","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.04737","created_at":"2026-05-17T23:43:32Z"},{"alias_kind":"arxiv_version","alias_value":"1906.04737v1","created_at":"2026-05-17T23:43:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.04737","created_at":"2026-05-17T23:43:32Z"},{"alias_kind":"pith_short_12","alias_value":"N2EVZ3ZXYEBI","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_16","alias_value":"N2EVZ3ZXYEBIRBHO","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_8","alias_value":"N2EVZ3ZX","created_at":"2026-05-18T12:33:24Z"}],"graph_snapshots":[{"event_id":"sha256:eb404d4a7e7cd644893b03d8d504e956993114cb24af10aae43c76b0c5e833ba","target":"graph","created_at":"2026-05-17T23:43:32Z","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":"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","authors_text":"Arrasy Rahman, Filippos Christianos, Georgios Papoudakis, Stefano V. Albrecht","cross_cats":["cs.AI","cs.MA","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-11T09:42:00Z","title":"Dealing with Non-Stationarity in Multi-Agent Deep Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.04737","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":"sha256:0555df4ed353baff6f7f581c2455bca05b85ad04da8dbc303c5da078c675d843","target":"record","created_at":"2026-05-17T23:43:32Z","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":"1c82d04a14c6ecab04fb2e946049fbd4845cc15ac887db6a3e16ccc440aa188f","cross_cats_sorted":["cs.AI","cs.MA","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-11T09:42:00Z","title_canon_sha256":"74b12702bc62a77f429d48398c263c2ece5a988bd2fe8df05e7c5ae7f3a4d532"},"schema_version":"1.0","source":{"id":"1906.04737","kind":"arxiv","version":1}},"canonical_sha256":"6e895cef37c1028884ee924a11b8aedb2611dbdc189e55feda4c391b60e088b6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6e895cef37c1028884ee924a11b8aedb2611dbdc189e55feda4c391b60e088b6","first_computed_at":"2026-05-17T23:43:32.372998Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:43:32.372998Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OJeSNua5bS63msmG7tDNZ01AkSdaMSjOYliPFPaWgIx2vxQfkICoRxZvcqGGnn472fe7ZWX2dK9nKnbbY93vBQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:43:32.373590Z","signed_message":"canonical_sha256_bytes"},"source_id":"1906.04737","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0555df4ed353baff6f7f581c2455bca05b85ad04da8dbc303c5da078c675d843","sha256:eb404d4a7e7cd644893b03d8d504e956993114cb24af10aae43c76b0c5e833ba"],"state_sha256":"b7db4524e093609f88edf6a30a01a9d71a9d5433a4257dcf0002852456dea550"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UL7t4EfPehT2G9T9mmzJiBrcUYN7cFUcVfx4XkvSGe7oxWz6m2invwdjUrhCJQXZicBqRJmJrwtuB6m8vkskAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T17:17:36.920463Z","bundle_sha256":"802820ab91bcc7666d87a806b499877f2fcd1bb1a857f979f61aba7cacceb988"}}