{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:TMF22VZVWDVPSTZD44G7OOSWNL","short_pith_number":"pith:TMF22VZV","schema_version":"1.0","canonical_sha256":"9b0bad5735b0eaf94f23e70df73a566ad2ad0ec4ed53e82363ab8f24bc96cd29","source":{"kind":"arxiv","id":"2305.17372","version":3},"attestation_state":"computed","paper":{"title":"Reinforcement Learning With Reward Machines in Stochastic Games","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.GT","cs.LG"],"primary_cat":"cs.MA","authors_text":"Jean-Raphael Gaglione, Jueming Hu, Ufuk Topcu, Yanze Wang, Yongming Liu, Zhe Xu","submitted_at":"2023-05-27T05:32:30Z","abstract_excerpt":"We investigate multi-agent reinforcement learning for stochastic games with complex tasks, where the reward functions are non-Markovian. We utilize reward machines to incorporate high-level knowledge of complex tasks. We develop an algorithm called Q-learning with reward machines for stochastic games (QRM-SG), to learn the best-response strategy at Nash equilibrium for each agent. In QRM-SG, we define the Q-function at a Nash equilibrium in augmented state space. The augmented state space integrates the state of the stochastic game and the state of reward machines. Each agent learns the Q-func"},"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":"2305.17372","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.MA","submitted_at":"2023-05-27T05:32:30Z","cross_cats_sorted":["cs.AI","cs.GT","cs.LG"],"title_canon_sha256":"7bac365fafaf799802d000adff051f08eb4be935667ae1da88b19e10421fd093","abstract_canon_sha256":"eb7ebb352b9c81a82c33ab10021dbc7070667ecd6a13f436b2c948b70dfe7f11"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:45:36.425557Z","signature_b64":"pghlT994OqYqch+75H+5CdIkxCNycwxMm8I9QB7AWa13vJIwUTPXPFSlQt+HrrwL8xctvLk/Gk4q6jKRh0g3Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9b0bad5735b0eaf94f23e70df73a566ad2ad0ec4ed53e82363ab8f24bc96cd29","last_reissued_at":"2026-07-05T06:45:36.424962Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:45:36.424962Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reinforcement Learning With Reward Machines in Stochastic Games","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.GT","cs.LG"],"primary_cat":"cs.MA","authors_text":"Jean-Raphael Gaglione, Jueming Hu, Ufuk Topcu, Yanze Wang, Yongming Liu, Zhe Xu","submitted_at":"2023-05-27T05:32:30Z","abstract_excerpt":"We investigate multi-agent reinforcement learning for stochastic games with complex tasks, where the reward functions are non-Markovian. We utilize reward machines to incorporate high-level knowledge of complex tasks. We develop an algorithm called Q-learning with reward machines for stochastic games (QRM-SG), to learn the best-response strategy at Nash equilibrium for each agent. In QRM-SG, we define the Q-function at a Nash equilibrium in augmented state space. The augmented state space integrates the state of the stochastic game and the state of reward machines. Each agent learns the Q-func"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.17372","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/2305.17372/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":"2305.17372","created_at":"2026-07-05T06:45:36.425033+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.17372v3","created_at":"2026-07-05T06:45:36.425033+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.17372","created_at":"2026-07-05T06:45:36.425033+00:00"},{"alias_kind":"pith_short_12","alias_value":"TMF22VZVWDVP","created_at":"2026-07-05T06:45:36.425033+00:00"},{"alias_kind":"pith_short_16","alias_value":"TMF22VZVWDVPSTZD","created_at":"2026-07-05T06:45:36.425033+00:00"},{"alias_kind":"pith_short_8","alias_value":"TMF22VZV","created_at":"2026-07-05T06:45:36.425033+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/TMF22VZVWDVPSTZD44G7OOSWNL","json":"https://pith.science/pith/TMF22VZVWDVPSTZD44G7OOSWNL.json","graph_json":"https://pith.science/api/pith-number/TMF22VZVWDVPSTZD44G7OOSWNL/graph.json","events_json":"https://pith.science/api/pith-number/TMF22VZVWDVPSTZD44G7OOSWNL/events.json","paper":"https://pith.science/paper/TMF22VZV"},"agent_actions":{"view_html":"https://pith.science/pith/TMF22VZVWDVPSTZD44G7OOSWNL","download_json":"https://pith.science/pith/TMF22VZVWDVPSTZD44G7OOSWNL.json","view_paper":"https://pith.science/paper/TMF22VZV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.17372&json=true","fetch_graph":"https://pith.science/api/pith-number/TMF22VZVWDVPSTZD44G7OOSWNL/graph.json","fetch_events":"https://pith.science/api/pith-number/TMF22VZVWDVPSTZD44G7OOSWNL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TMF22VZVWDVPSTZD44G7OOSWNL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TMF22VZVWDVPSTZD44G7OOSWNL/action/storage_attestation","attest_author":"https://pith.science/pith/TMF22VZVWDVPSTZD44G7OOSWNL/action/author_attestation","sign_citation":"https://pith.science/pith/TMF22VZVWDVPSTZD44G7OOSWNL/action/citation_signature","submit_replication":"https://pith.science/pith/TMF22VZVWDVPSTZD44G7OOSWNL/action/replication_record"}},"created_at":"2026-07-05T06:45:36.425033+00:00","updated_at":"2026-07-05T06:45:36.425033+00:00"}