{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:HP4ZWL7JKZJITTIZVTSEO2WSCS","short_pith_number":"pith:HP4ZWL7J","schema_version":"1.0","canonical_sha256":"3bf99b2fe9565289cd19ace4476ad2148a7f5a032b348415279ddb94a6cb95dc","source":{"kind":"arxiv","id":"2009.13051","version":3},"attestation_state":"computed","paper":{"title":"Agent Environment Cycle Games","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.GT","cs.MA","stat.ML"],"primary_cat":"cs.LG","authors_text":"Ananth Hari, Benjamin Black, Caroline Horsch, J K Terry, Luis Santos, Nathaniel Grammel","submitted_at":"2020-09-28T04:02:08Z","abstract_excerpt":"Partially Observable Stochastic Games (POSGs) are the most general and common model of games used in Multi-Agent Reinforcement Learning (MARL). We argue that the POSG model is conceptually ill suited to software MARL environments, and offer case studies from the literature where this mismatch has led to severely unexpected behavior. In response to this, we introduce the Agent Environment Cycle Games (AEC Games) model, which is more representative of software implementation. We then prove it's as an equivalent model to POSGs. The AEC games model is also uniquely useful in that it can elegantly "},"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":"2009.13051","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-09-28T04:02:08Z","cross_cats_sorted":["cs.AI","cs.GT","cs.MA","stat.ML"],"title_canon_sha256":"de4790285ebe62fae7593843f781eb66e7c2008ee39beb832324f4f107c349fb","abstract_canon_sha256":"d100861f2b0ff6af48f6f9545d43c0f092c0d16414fc7a93fdda404e7a00a4ee"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:27:41.429654Z","signature_b64":"G4K14Afw54ED9zdf2B3CBHwT8npMgWelQBy3kN22bGHQm15kiMqB4twNFq7obOb9cl2+gmrw2wdJVdIbz1XpDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3bf99b2fe9565289cd19ace4476ad2148a7f5a032b348415279ddb94a6cb95dc","last_reissued_at":"2026-07-05T04:27:41.429272Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:27:41.429272Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Agent Environment Cycle Games","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.GT","cs.MA","stat.ML"],"primary_cat":"cs.LG","authors_text":"Ananth Hari, Benjamin Black, Caroline Horsch, J K Terry, Luis Santos, Nathaniel Grammel","submitted_at":"2020-09-28T04:02:08Z","abstract_excerpt":"Partially Observable Stochastic Games (POSGs) are the most general and common model of games used in Multi-Agent Reinforcement Learning (MARL). We argue that the POSG model is conceptually ill suited to software MARL environments, and offer case studies from the literature where this mismatch has led to severely unexpected behavior. In response to this, we introduce the Agent Environment Cycle Games (AEC Games) model, which is more representative of software implementation. We then prove it's as an equivalent model to POSGs. The AEC games model is also uniquely useful in that it can elegantly "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2009.13051","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2009.13051/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2009.13051","created_at":"2026-07-05T04:27:41.429327+00:00"},{"alias_kind":"arxiv_version","alias_value":"2009.13051v3","created_at":"2026-07-05T04:27:41.429327+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2009.13051","created_at":"2026-07-05T04:27:41.429327+00:00"},{"alias_kind":"pith_short_12","alias_value":"HP4ZWL7JKZJI","created_at":"2026-07-05T04:27:41.429327+00:00"},{"alias_kind":"pith_short_16","alias_value":"HP4ZWL7JKZJITTIZ","created_at":"2026-07-05T04:27:41.429327+00:00"},{"alias_kind":"pith_short_8","alias_value":"HP4ZWL7J","created_at":"2026-07-05T04:27:41.429327+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/HP4ZWL7JKZJITTIZVTSEO2WSCS","json":"https://pith.science/pith/HP4ZWL7JKZJITTIZVTSEO2WSCS.json","graph_json":"https://pith.science/api/pith-number/HP4ZWL7JKZJITTIZVTSEO2WSCS/graph.json","events_json":"https://pith.science/api/pith-number/HP4ZWL7JKZJITTIZVTSEO2WSCS/events.json","paper":"https://pith.science/paper/HP4ZWL7J"},"agent_actions":{"view_html":"https://pith.science/pith/HP4ZWL7JKZJITTIZVTSEO2WSCS","download_json":"https://pith.science/pith/HP4ZWL7JKZJITTIZVTSEO2WSCS.json","view_paper":"https://pith.science/paper/HP4ZWL7J","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2009.13051&json=true","fetch_graph":"https://pith.science/api/pith-number/HP4ZWL7JKZJITTIZVTSEO2WSCS/graph.json","fetch_events":"https://pith.science/api/pith-number/HP4ZWL7JKZJITTIZVTSEO2WSCS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HP4ZWL7JKZJITTIZVTSEO2WSCS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HP4ZWL7JKZJITTIZVTSEO2WSCS/action/storage_attestation","attest_author":"https://pith.science/pith/HP4ZWL7JKZJITTIZVTSEO2WSCS/action/author_attestation","sign_citation":"https://pith.science/pith/HP4ZWL7JKZJITTIZVTSEO2WSCS/action/citation_signature","submit_replication":"https://pith.science/pith/HP4ZWL7JKZJITTIZVTSEO2WSCS/action/replication_record"}},"created_at":"2026-07-05T04:27:41.429327+00:00","updated_at":"2026-07-05T04:27:41.429327+00:00"}