{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:QEK6NAKD3JCPXIGY4SCBO5E7GA","short_pith_number":"pith:QEK6NAKD","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"},"canonical_sha256":"8115e68143da44fba0d8e48417749f3025c0d356b8b2768c9b37668bbebed1fa","source":{"kind":"arxiv","id":"1702.08887","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1702.08887","created_at":"2026-05-18T00:15:37Z"},{"alias_kind":"arxiv_version","alias_value":"1702.08887v3","created_at":"2026-05-18T00:15:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1702.08887","created_at":"2026-05-18T00:15:37Z"},{"alias_kind":"pith_short_12","alias_value":"QEK6NAKD3JCP","created_at":"2026-05-18T12:31:37Z"},{"alias_kind":"pith_short_16","alias_value":"QEK6NAKD3JCPXIGY","created_at":"2026-05-18T12:31:37Z"},{"alias_kind":"pith_short_8","alias_value":"QEK6NAKD","created_at":"2026-05-18T12:31:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:QEK6NAKD3JCPXIGY4SCBO5E7GA","target":"record","payload":{"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"},"canonical_sha256":"8115e68143da44fba0d8e48417749f3025c0d356b8b2768c9b37668bbebed1fa","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"},"source_kind":"arxiv","source_id":"1702.08887","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:15:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bIWs612MUzpV5XJHNjSx4pXV4T6aO4FsQwDJggwxheheomGGusaWht9QCKfeqhjMCZ8KivPpeMSaTnf+4DD1Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T08:52:40.208433Z"},"content_sha256":"af39279f3ed4d85f0bfefc38b3f23288a6fcd8c8b07a603a804ffd94a1e3d33c","schema_version":"1.0","event_id":"sha256:af39279f3ed4d85f0bfefc38b3f23288a6fcd8c8b07a603a804ffd94a1e3d33c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:QEK6NAKD3JCPXIGY4SCBO5E7GA","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:15:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"H7p/CkE6HHpMurfGholIRQPwPci++Aat/q419f67QEZNWmetOrlvYDsU8MHM062ZHljavonuI3Wm0EB54Xr7BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T08:52:40.209191Z"},"content_sha256":"17c7e73d105a69bdc4a45527b85b5600e702972f06f36e31113bc50dbd861b07","schema_version":"1.0","event_id":"sha256:17c7e73d105a69bdc4a45527b85b5600e702972f06f36e31113bc50dbd861b07"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QEK6NAKD3JCPXIGY4SCBO5E7GA/bundle.json","state_url":"https://pith.science/pith/QEK6NAKD3JCPXIGY4SCBO5E7GA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QEK6NAKD3JCPXIGY4SCBO5E7GA/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":"2026-05-25T08:52:40Z","links":{"resolver":"https://pith.science/pith/QEK6NAKD3JCPXIGY4SCBO5E7GA","bundle":"https://pith.science/pith/QEK6NAKD3JCPXIGY4SCBO5E7GA/bundle.json","state":"https://pith.science/pith/QEK6NAKD3JCPXIGY4SCBO5E7GA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QEK6NAKD3JCPXIGY4SCBO5E7GA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:QEK6NAKD3JCPXIGY4SCBO5E7GA","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":"43aa1e5a054011e3e969d73a65ba9fc0767b6d6efb181db3f49a9b0d778617f6","cross_cats_sorted":["cs.LG","cs.MA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-02-28T17:56:41Z","title_canon_sha256":"47777c60637b1823e6aec0bde0c94420d4911c5fe0061113b2a8c36af4199861"},"schema_version":"1.0","source":{"id":"1702.08887","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1702.08887","created_at":"2026-05-18T00:15:37Z"},{"alias_kind":"arxiv_version","alias_value":"1702.08887v3","created_at":"2026-05-18T00:15:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1702.08887","created_at":"2026-05-18T00:15:37Z"},{"alias_kind":"pith_short_12","alias_value":"QEK6NAKD3JCP","created_at":"2026-05-18T12:31:37Z"},{"alias_kind":"pith_short_16","alias_value":"QEK6NAKD3JCPXIGY","created_at":"2026-05-18T12:31:37Z"},{"alias_kind":"pith_short_8","alias_value":"QEK6NAKD","created_at":"2026-05-18T12:31:37Z"}],"graph_snapshots":[{"event_id":"sha256:17c7e73d105a69bdc4a45527b85b5600e702972f06f36e31113bc50dbd861b07","target":"graph","created_at":"2026-05-18T00:15:37Z","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":"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 ","authors_text":"Gregory Farquhar, Jakob Foerster, Nantas Nardelli, Philip H. S. Torr, Pushmeet Kohli, Shimon Whiteson, Triantafyllos Afouras","cross_cats":["cs.LG","cs.MA"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-02-28T17:56:41Z","title":"Stabilising Experience Replay for Deep Multi-Agent Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1702.08887","kind":"arxiv","version":3},"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:af39279f3ed4d85f0bfefc38b3f23288a6fcd8c8b07a603a804ffd94a1e3d33c","target":"record","created_at":"2026-05-18T00:15:37Z","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":"43aa1e5a054011e3e969d73a65ba9fc0767b6d6efb181db3f49a9b0d778617f6","cross_cats_sorted":["cs.LG","cs.MA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-02-28T17:56:41Z","title_canon_sha256":"47777c60637b1823e6aec0bde0c94420d4911c5fe0061113b2a8c36af4199861"},"schema_version":"1.0","source":{"id":"1702.08887","kind":"arxiv","version":3}},"canonical_sha256":"8115e68143da44fba0d8e48417749f3025c0d356b8b2768c9b37668bbebed1fa","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8115e68143da44fba0d8e48417749f3025c0d356b8b2768c9b37668bbebed1fa","first_computed_at":"2026-05-18T00:15:37.844055Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:15:37.844055Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1CycDfOdjO8HUiOpP6gBFp34CsP64WRbnNZqrt5p/9a4y0sqifpDhTqxWvIRR8UC+gW8KS1kOcoukaWWUsHCBw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:15:37.844714Z","signed_message":"canonical_sha256_bytes"},"source_id":"1702.08887","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:af39279f3ed4d85f0bfefc38b3f23288a6fcd8c8b07a603a804ffd94a1e3d33c","sha256:17c7e73d105a69bdc4a45527b85b5600e702972f06f36e31113bc50dbd861b07"],"state_sha256":"b9952306a88f6c6f2b948a1f247ecc53186927686ff869f416a5b702ffe630cc"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dAcUHdbbaf+KMjLCJxguKhvlAukPvGj84j5Ysj0B9NGcEuGTZGQH+Ru4I8DSTnhrpf6KYI4poowZFkj2lc1qCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T08:52:40.212532Z","bundle_sha256":"82a1fa4c089d15ee90eec462b9028078d6c3c94325a1201cdb5c2cb5cc1a16b6"}}