{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:XG2LM6VVLPTI65OLBFVZ4R6HGM","short_pith_number":"pith:XG2LM6VV","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"},"canonical_sha256":"b9b4b67ab55be68f75cb096b9e47c73331777de7b75d7eb4a75e5b095a45e355","source":{"kind":"arxiv","id":"1711.00832","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1711.00832","created_at":"2026-05-18T00:31:11Z"},{"alias_kind":"arxiv_version","alias_value":"1711.00832v2","created_at":"2026-05-18T00:31:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.00832","created_at":"2026-05-18T00:31:11Z"},{"alias_kind":"pith_short_12","alias_value":"XG2LM6VVLPTI","created_at":"2026-05-18T12:31:53Z"},{"alias_kind":"pith_short_16","alias_value":"XG2LM6VVLPTI65OL","created_at":"2026-05-18T12:31:53Z"},{"alias_kind":"pith_short_8","alias_value":"XG2LM6VV","created_at":"2026-05-18T12:31:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:XG2LM6VVLPTI65OLBFVZ4R6HGM","target":"record","payload":{"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"},"canonical_sha256":"b9b4b67ab55be68f75cb096b9e47c73331777de7b75d7eb4a75e5b095a45e355","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"},"source_kind":"arxiv","source_id":"1711.00832","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:31:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6k4NwskslQDNoLQBJnzvuX4aHCYfOmA3G1rM1qrKAkVZEDL3r44CW674Va37C9MHZusEuk3KfjMd8+wLEquNAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T21:14:42.694449Z"},"content_sha256":"eae794cadf29c444e7b71226620be6a967ac5a47e72724cdacd9384988b2fc98","schema_version":"1.0","event_id":"sha256:eae794cadf29c444e7b71226620be6a967ac5a47e72724cdacd9384988b2fc98"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:XG2LM6VVLPTI65OLBFVZ4R6HGM","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:31:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"REjkraSFk7IAfzBG6N/Yw7bcuKZJ1Lav6hyXQGrkBWKzEQdn+noXpikyK03WTLAkjrhcfTl94aKK9Ad/46crDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T21:14:42.694794Z"},"content_sha256":"132ae57bdb8f7217d16a11cda1f6ce3206554f7a99f154d866de0eefb7dc1e45","schema_version":"1.0","event_id":"sha256:132ae57bdb8f7217d16a11cda1f6ce3206554f7a99f154d866de0eefb7dc1e45"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XG2LM6VVLPTI65OLBFVZ4R6HGM/bundle.json","state_url":"https://pith.science/pith/XG2LM6VVLPTI65OLBFVZ4R6HGM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XG2LM6VVLPTI65OLBFVZ4R6HGM/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":"2026-06-01T21:14:42Z","links":{"resolver":"https://pith.science/pith/XG2LM6VVLPTI65OLBFVZ4R6HGM","bundle":"https://pith.science/pith/XG2LM6VVLPTI65OLBFVZ4R6HGM/bundle.json","state":"https://pith.science/pith/XG2LM6VVLPTI65OLBFVZ4R6HGM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XG2LM6VVLPTI65OLBFVZ4R6HGM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:XG2LM6VVLPTI65OLBFVZ4R6HGM","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":"0910678a956fa472a96117be2b53ea47f7e22de5ae22ba94e6affbf8bd2a8126","cross_cats_sorted":["cs.GT","cs.LG","cs.MA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-11-02T17:34:24Z","title_canon_sha256":"5c7b5fd148ac7cf758015b946784b6137d965e231888160d2e1174fc3e35f296"},"schema_version":"1.0","source":{"id":"1711.00832","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1711.00832","created_at":"2026-05-18T00:31:11Z"},{"alias_kind":"arxiv_version","alias_value":"1711.00832v2","created_at":"2026-05-18T00:31:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.00832","created_at":"2026-05-18T00:31:11Z"},{"alias_kind":"pith_short_12","alias_value":"XG2LM6VVLPTI","created_at":"2026-05-18T12:31:53Z"},{"alias_kind":"pith_short_16","alias_value":"XG2LM6VVLPTI65OL","created_at":"2026-05-18T12:31:53Z"},{"alias_kind":"pith_short_8","alias_value":"XG2LM6VV","created_at":"2026-05-18T12:31:53Z"}],"graph_snapshots":[{"event_id":"sha256:132ae57bdb8f7217d16a11cda1f6ce3206554f7a99f154d866de0eefb7dc1e45","target":"graph","created_at":"2026-05-18T00:31:11Z","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":"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","authors_text":"Angeliki Lazaridou, Audrunas Gruslys, David Silver, Julien Perolat, Karl Tuyls, Marc Lanctot, Thore Graepel, Vinicius Zambaldi","cross_cats":["cs.GT","cs.LG","cs.MA"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-11-02T17:34:24Z","title":"A Unified Game-Theoretic Approach to Multiagent Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.00832","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:eae794cadf29c444e7b71226620be6a967ac5a47e72724cdacd9384988b2fc98","target":"record","created_at":"2026-05-18T00:31:11Z","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":"0910678a956fa472a96117be2b53ea47f7e22de5ae22ba94e6affbf8bd2a8126","cross_cats_sorted":["cs.GT","cs.LG","cs.MA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-11-02T17:34:24Z","title_canon_sha256":"5c7b5fd148ac7cf758015b946784b6137d965e231888160d2e1174fc3e35f296"},"schema_version":"1.0","source":{"id":"1711.00832","kind":"arxiv","version":2}},"canonical_sha256":"b9b4b67ab55be68f75cb096b9e47c73331777de7b75d7eb4a75e5b095a45e355","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b9b4b67ab55be68f75cb096b9e47c73331777de7b75d7eb4a75e5b095a45e355","first_computed_at":"2026-05-18T00:31:11.077389Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:31:11.077389Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gEf+bqZuIeVLqFmMzJZlcIoLHGj/yZhyn0oh/Be0oug7qa4pXmP1hJ1ZOpV13RjLktH5ZdgIUEcH6fIE7DrTCQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:31:11.078121Z","signed_message":"canonical_sha256_bytes"},"source_id":"1711.00832","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:eae794cadf29c444e7b71226620be6a967ac5a47e72724cdacd9384988b2fc98","sha256:132ae57bdb8f7217d16a11cda1f6ce3206554f7a99f154d866de0eefb7dc1e45"],"state_sha256":"c50fdf7fc09fce59d5ab660940e983691074901c89ba4a06d767c546e2f31aad"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VY6j0HziyG4+oIfvPgy03wLHfLjKM/uQOqSw5Y6aJQ4FXHZtE1AKOAxm1iQ4EJTALPry0DgUNrz6f+kjLsyfAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T21:14:42.696827Z","bundle_sha256":"30ac1cd8743e2bd85e675e8f1662941d0636f7851fc7a6e35baf678fe3fecd7b"}}