{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:XG2LM6VVLPTI65OLBFVZ4R6HGM","short_pith_number":"pith:XG2LM6VV","schema_version":"1.0","canonical_sha256":"b9b4b67ab55be68f75cb096b9e47c73331777de7b75d7eb4a75e5b095a45e355","source":{"kind":"arxiv","id":"1711.00832","version":2},"attestation_state":"computed","paper":{"title":"A Unified Game-Theoretic Approach to Multiagent Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.GT","cs.LG","cs.MA"],"primary_cat":"cs.AI","authors_text":"Angeliki Lazaridou, Audrunas Gruslys, David Silver, Julien Perolat, Karl Tuyls, Marc Lanctot, Thore Graepel, Vinicius Zambaldi","submitted_at":"2017-11-02T17:34:24Z","abstract_excerpt":"To achieve general intelligence, agents must learn how to interact with others in a shared environment: this is the challenge of multiagent reinforcement learning (MARL). The simplest form is independent reinforcement learning (InRL), where each agent treats its experience as part of its (non-stationary) environment. In this paper, we first observe that policies learned using InRL can overfit to the other agents' policies during training, failing to sufficiently generalize during execution. We introduce a new metric, joint-policy correlation, to quantify this effect. We describe an algorithm f"},"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":"1711.00832","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-11-02T17:34:24Z","cross_cats_sorted":["cs.GT","cs.LG","cs.MA"],"title_canon_sha256":"5c7b5fd148ac7cf758015b946784b6137d965e231888160d2e1174fc3e35f296","abstract_canon_sha256":"0910678a956fa472a96117be2b53ea47f7e22de5ae22ba94e6affbf8bd2a8126"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:31:11.078121Z","signature_b64":"gEf+bqZuIeVLqFmMzJZlcIoLHGj/yZhyn0oh/Be0oug7qa4pXmP1hJ1ZOpV13RjLktH5ZdgIUEcH6fIE7DrTCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b9b4b67ab55be68f75cb096b9e47c73331777de7b75d7eb4a75e5b095a45e355","last_reissued_at":"2026-05-18T00:31:11.077389Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:31:11.077389Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Unified Game-Theoretic Approach to Multiagent Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.GT","cs.LG","cs.MA"],"primary_cat":"cs.AI","authors_text":"Angeliki Lazaridou, Audrunas Gruslys, David Silver, Julien Perolat, Karl Tuyls, Marc Lanctot, Thore Graepel, Vinicius Zambaldi","submitted_at":"2017-11-02T17:34:24Z","abstract_excerpt":"To achieve general intelligence, agents must learn how to interact with others in a shared environment: this is the challenge of multiagent reinforcement learning (MARL). The simplest form is independent reinforcement learning (InRL), where each agent treats its experience as part of its (non-stationary) environment. In this paper, we first observe that policies learned using InRL can overfit to the other agents' policies during training, failing to sufficiently generalize during execution. We introduce a new metric, joint-policy correlation, to quantify this effect. We describe an algorithm f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.00832","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":"1711.00832","created_at":"2026-05-18T00:31:11.077508+00:00"},{"alias_kind":"arxiv_version","alias_value":"1711.00832v2","created_at":"2026-05-18T00:31:11.077508+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.00832","created_at":"2026-05-18T00:31:11.077508+00:00"},{"alias_kind":"pith_short_12","alias_value":"XG2LM6VVLPTI","created_at":"2026-05-18T12:31:53.515858+00:00"},{"alias_kind":"pith_short_16","alias_value":"XG2LM6VVLPTI65OL","created_at":"2026-05-18T12:31:53.515858+00:00"},{"alias_kind":"pith_short_8","alias_value":"XG2LM6VV","created_at":"2026-05-18T12:31:53.515858+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XG2LM6VVLPTI65OLBFVZ4R6HGM","json":"https://pith.science/pith/XG2LM6VVLPTI65OLBFVZ4R6HGM.json","graph_json":"https://pith.science/api/pith-number/XG2LM6VVLPTI65OLBFVZ4R6HGM/graph.json","events_json":"https://pith.science/api/pith-number/XG2LM6VVLPTI65OLBFVZ4R6HGM/events.json","paper":"https://pith.science/paper/XG2LM6VV"},"agent_actions":{"view_html":"https://pith.science/pith/XG2LM6VVLPTI65OLBFVZ4R6HGM","download_json":"https://pith.science/pith/XG2LM6VVLPTI65OLBFVZ4R6HGM.json","view_paper":"https://pith.science/paper/XG2LM6VV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1711.00832&json=true","fetch_graph":"https://pith.science/api/pith-number/XG2LM6VVLPTI65OLBFVZ4R6HGM/graph.json","fetch_events":"https://pith.science/api/pith-number/XG2LM6VVLPTI65OLBFVZ4R6HGM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XG2LM6VVLPTI65OLBFVZ4R6HGM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XG2LM6VVLPTI65OLBFVZ4R6HGM/action/storage_attestation","attest_author":"https://pith.science/pith/XG2LM6VVLPTI65OLBFVZ4R6HGM/action/author_attestation","sign_citation":"https://pith.science/pith/XG2LM6VVLPTI65OLBFVZ4R6HGM/action/citation_signature","submit_replication":"https://pith.science/pith/XG2LM6VVLPTI65OLBFVZ4R6HGM/action/replication_record"}},"created_at":"2026-05-18T00:31:11.077508+00:00","updated_at":"2026-05-18T00:31:11.077508+00:00"}