{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:VTN7CONWSEJ5DRJA2JRUM6TF2W","short_pith_number":"pith:VTN7CONW","schema_version":"1.0","canonical_sha256":"acdbf139b69113d1c520d263467a65d5836b2d04cf49b072cbfc3e3b7dee8559","source":{"kind":"arxiv","id":"1707.04402","version":2},"attestation_state":"computed","paper":{"title":"Lenient Multi-Agent Deep Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.MA","authors_text":"Daan Bloembergen, Gregory Palmer, Karl Tuyls, Rahul Savani","submitted_at":"2017-07-14T07:33:20Z","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care is required when using ERMs for multi-agent deep reinforcement learning (MA-DRL), as stored transitions can become outdated because agents update their policies in parallel [11].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"},"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":"1707.04402","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2017-07-14T07:33:20Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"313685eb8065153d40293c40030b7238e238ea25170c0f887c3bee44f9ea6c7b","abstract_canon_sha256":"24f583914cfd0e5331b5380aad951b2631d583f97edcf70fa1650772065a261d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:22:28.881033Z","signature_b64":"MgOhrYks1e3B+Pz96AOrrijEAz0TGo8FCeVWFEd/MKJytpRSuFdgznj4rSGhNo5pygL7JB5VUaDHYXa5zsxTCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"acdbf139b69113d1c520d263467a65d5836b2d04cf49b072cbfc3e3b7dee8559","last_reissued_at":"2026-05-18T00:22:28.880369Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:22:28.880369Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Lenient Multi-Agent Deep Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.MA","authors_text":"Daan Bloembergen, Gregory Palmer, Karl Tuyls, Rahul Savani","submitted_at":"2017-07-14T07:33:20Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1707.04402","kind":"arxiv","version":2},"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":"1707.04402","created_at":"2026-05-18T00:22:28.880477+00:00"},{"alias_kind":"arxiv_version","alias_value":"1707.04402v2","created_at":"2026-05-18T00:22:28.880477+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1707.04402","created_at":"2026-05-18T00:22:28.880477+00:00"},{"alias_kind":"pith_short_12","alias_value":"VTN7CONWSEJ5","created_at":"2026-05-18T12:31:49.984773+00:00"},{"alias_kind":"pith_short_16","alias_value":"VTN7CONWSEJ5DRJA","created_at":"2026-05-18T12:31:49.984773+00:00"},{"alias_kind":"pith_short_8","alias_value":"VTN7CONW","created_at":"2026-05-18T12:31:49.984773+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.01049","citing_title":"Centralized Adaptive Sampling for Reliable Co-Training of Independent Multi-Agent Policies","ref_index":28,"is_internal_anchor":true},{"citing_arxiv_id":"2604.15695","citing_title":"The Price of Paranoia: Robust Risk-Sensitive Cooperation in Non-Stationary Multi-Agent Reinforcement Learning","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VTN7CONWSEJ5DRJA2JRUM6TF2W","json":"https://pith.science/pith/VTN7CONWSEJ5DRJA2JRUM6TF2W.json","graph_json":"https://pith.science/api/pith-number/VTN7CONWSEJ5DRJA2JRUM6TF2W/graph.json","events_json":"https://pith.science/api/pith-number/VTN7CONWSEJ5DRJA2JRUM6TF2W/events.json","paper":"https://pith.science/paper/VTN7CONW"},"agent_actions":{"view_html":"https://pith.science/pith/VTN7CONWSEJ5DRJA2JRUM6TF2W","download_json":"https://pith.science/pith/VTN7CONWSEJ5DRJA2JRUM6TF2W.json","view_paper":"https://pith.science/paper/VTN7CONW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1707.04402&json=true","fetch_graph":"https://pith.science/api/pith-number/VTN7CONWSEJ5DRJA2JRUM6TF2W/graph.json","fetch_events":"https://pith.science/api/pith-number/VTN7CONWSEJ5DRJA2JRUM6TF2W/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VTN7CONWSEJ5DRJA2JRUM6TF2W/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VTN7CONWSEJ5DRJA2JRUM6TF2W/action/storage_attestation","attest_author":"https://pith.science/pith/VTN7CONWSEJ5DRJA2JRUM6TF2W/action/author_attestation","sign_citation":"https://pith.science/pith/VTN7CONWSEJ5DRJA2JRUM6TF2W/action/citation_signature","submit_replication":"https://pith.science/pith/VTN7CONWSEJ5DRJA2JRUM6TF2W/action/replication_record"}},"created_at":"2026-05-18T00:22:28.880477+00:00","updated_at":"2026-05-18T00:22:28.880477+00:00"}