{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:VTN7CONWSEJ5DRJA2JRUM6TF2W","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":"24f583914cfd0e5331b5380aad951b2631d583f97edcf70fa1650772065a261d","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2017-07-14T07:33:20Z","title_canon_sha256":"313685eb8065153d40293c40030b7238e238ea25170c0f887c3bee44f9ea6c7b"},"schema_version":"1.0","source":{"id":"1707.04402","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1707.04402","created_at":"2026-05-18T00:22:28Z"},{"alias_kind":"arxiv_version","alias_value":"1707.04402v2","created_at":"2026-05-18T00:22:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1707.04402","created_at":"2026-05-18T00:22:28Z"},{"alias_kind":"pith_short_12","alias_value":"VTN7CONWSEJ5","created_at":"2026-05-18T12:31:49Z"},{"alias_kind":"pith_short_16","alias_value":"VTN7CONWSEJ5DRJA","created_at":"2026-05-18T12:31:49Z"},{"alias_kind":"pith_short_8","alias_value":"VTN7CONW","created_at":"2026-05-18T12:31:49Z"}],"graph_snapshots":[{"event_id":"sha256:65536bee37741ef07f7acc50d411e4df2d3782061d56abbd5fc8965c52a5b563","target":"graph","created_at":"2026-05-18T00:22:28Z","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":"Much of the success of single agent deep reinforcement learning (DRL) in recent years can be attributed to the use of experience replay memories (ERM), which allow Deep Q-Networks (DQNs) to be trained efficiently through sampling stored state transitions. However, care is required when using ERMs for multi-agent deep reinforcement learning (MA-DRL), as stored transitions can become outdated because agents update their policies in parallel [11]. In this work we apply leniency [23] to MA-DRL. Lenient agents map state-action pairs to decaying temperature values that control the amount of leniency","authors_text":"Daan Bloembergen, Gregory Palmer, Karl Tuyls, Rahul Savani","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2017-07-14T07:33:20Z","title":"Lenient Multi-Agent Deep Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1707.04402","kind":"arxiv","version":2},"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:a1e1456300bcd773ea24a433cf641aea12c7227ab39fda39e83218c06fe5b7f4","target":"record","created_at":"2026-05-18T00:22:28Z","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":"24f583914cfd0e5331b5380aad951b2631d583f97edcf70fa1650772065a261d","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2017-07-14T07:33:20Z","title_canon_sha256":"313685eb8065153d40293c40030b7238e238ea25170c0f887c3bee44f9ea6c7b"},"schema_version":"1.0","source":{"id":"1707.04402","kind":"arxiv","version":2}},"canonical_sha256":"acdbf139b69113d1c520d263467a65d5836b2d04cf49b072cbfc3e3b7dee8559","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"acdbf139b69113d1c520d263467a65d5836b2d04cf49b072cbfc3e3b7dee8559","first_computed_at":"2026-05-18T00:22:28.880369Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:22:28.880369Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MgOhrYks1e3B+Pz96AOrrijEAz0TGo8FCeVWFEd/MKJytpRSuFdgznj4rSGhNo5pygL7JB5VUaDHYXa5zsxTCA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:22:28.881033Z","signed_message":"canonical_sha256_bytes"},"source_id":"1707.04402","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a1e1456300bcd773ea24a433cf641aea12c7227ab39fda39e83218c06fe5b7f4","sha256:65536bee37741ef07f7acc50d411e4df2d3782061d56abbd5fc8965c52a5b563"],"state_sha256":"24a511c1a3a8a7dc0ba443f12708aed9802b7aa83ff859cf6ecbdf39ec6c1e3e"}