{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:TMF22VZVWDVPSTZD44G7OOSWNL","short_pith_number":"pith:TMF22VZV","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"},"canonical_sha256":"9b0bad5735b0eaf94f23e70df73a566ad2ad0ec4ed53e82363ab8f24bc96cd29","source":{"kind":"arxiv","id":"2305.17372","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.17372","created_at":"2026-07-05T06:45:36Z"},{"alias_kind":"arxiv_version","alias_value":"2305.17372v3","created_at":"2026-07-05T06:45:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.17372","created_at":"2026-07-05T06:45:36Z"},{"alias_kind":"pith_short_12","alias_value":"TMF22VZVWDVP","created_at":"2026-07-05T06:45:36Z"},{"alias_kind":"pith_short_16","alias_value":"TMF22VZVWDVPSTZD","created_at":"2026-07-05T06:45:36Z"},{"alias_kind":"pith_short_8","alias_value":"TMF22VZV","created_at":"2026-07-05T06:45:36Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:TMF22VZVWDVPSTZD44G7OOSWNL","target":"record","payload":{"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"},"canonical_sha256":"9b0bad5735b0eaf94f23e70df73a566ad2ad0ec4ed53e82363ab8f24bc96cd29","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"},"source_kind":"arxiv","source_id":"2305.17372","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:45:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0njGy0X6i0ssnDXdQRk6RB2OkW9oV5ZHZkItdaDF2tNnL2IxktgU1afsq4sZdWZJEz9NiV3YcXAamDw96Q8TDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T20:54:38.137432Z"},"content_sha256":"9f0c0338932c8019d592c50cddcca155075196c79bdd6b9c9460adc889e19999","schema_version":"1.0","event_id":"sha256:9f0c0338932c8019d592c50cddcca155075196c79bdd6b9c9460adc889e19999"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:TMF22VZVWDVPSTZD44G7OOSWNL","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:45:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"w4Q7Wep3xBE3L2s2cG0jisGRB6pbe60QMV3nng+pCTkacF7CXDfGTUgoSPuemMuOdMRZRPP1xsHCr4GIqtgHDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T20:54:38.137983Z"},"content_sha256":"806d479b874cc0b989e1ff9e8eb1790edee66c5f5ebea31986d7f73106491ef6","schema_version":"1.0","event_id":"sha256:806d479b874cc0b989e1ff9e8eb1790edee66c5f5ebea31986d7f73106491ef6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TMF22VZVWDVPSTZD44G7OOSWNL/bundle.json","state_url":"https://pith.science/pith/TMF22VZVWDVPSTZD44G7OOSWNL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TMF22VZVWDVPSTZD44G7OOSWNL/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":"2026-08-20T20:54:38Z","links":{"resolver":"https://pith.science/pith/TMF22VZVWDVPSTZD44G7OOSWNL","bundle":"https://pith.science/pith/TMF22VZVWDVPSTZD44G7OOSWNL/bundle.json","state":"https://pith.science/pith/TMF22VZVWDVPSTZD44G7OOSWNL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TMF22VZVWDVPSTZD44G7OOSWNL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:TMF22VZVWDVPSTZD44G7OOSWNL","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":"eb7ebb352b9c81a82c33ab10021dbc7070667ecd6a13f436b2c948b70dfe7f11","cross_cats_sorted":["cs.AI","cs.GT","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.MA","submitted_at":"2023-05-27T05:32:30Z","title_canon_sha256":"7bac365fafaf799802d000adff051f08eb4be935667ae1da88b19e10421fd093"},"schema_version":"1.0","source":{"id":"2305.17372","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.17372","created_at":"2026-07-05T06:45:36Z"},{"alias_kind":"arxiv_version","alias_value":"2305.17372v3","created_at":"2026-07-05T06:45:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.17372","created_at":"2026-07-05T06:45:36Z"},{"alias_kind":"pith_short_12","alias_value":"TMF22VZVWDVP","created_at":"2026-07-05T06:45:36Z"},{"alias_kind":"pith_short_16","alias_value":"TMF22VZVWDVPSTZD","created_at":"2026-07-05T06:45:36Z"},{"alias_kind":"pith_short_8","alias_value":"TMF22VZV","created_at":"2026-07-05T06:45:36Z"}],"graph_snapshots":[{"event_id":"sha256:806d479b874cc0b989e1ff9e8eb1790edee66c5f5ebea31986d7f73106491ef6","target":"graph","created_at":"2026-07-05T06:45:36Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2305.17372/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Jean-Raphael Gaglione, Jueming Hu, Ufuk Topcu, Yanze Wang, Yongming Liu, Zhe Xu","cross_cats":["cs.AI","cs.GT","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.MA","submitted_at":"2023-05-27T05:32:30Z","title":"Reinforcement Learning With Reward Machines in Stochastic Games"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.17372","kind":"arxiv","version":3},"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":"sha256:9f0c0338932c8019d592c50cddcca155075196c79bdd6b9c9460adc889e19999","target":"record","created_at":"2026-07-05T06:45:36Z","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":"eb7ebb352b9c81a82c33ab10021dbc7070667ecd6a13f436b2c948b70dfe7f11","cross_cats_sorted":["cs.AI","cs.GT","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.MA","submitted_at":"2023-05-27T05:32:30Z","title_canon_sha256":"7bac365fafaf799802d000adff051f08eb4be935667ae1da88b19e10421fd093"},"schema_version":"1.0","source":{"id":"2305.17372","kind":"arxiv","version":3}},"canonical_sha256":"9b0bad5735b0eaf94f23e70df73a566ad2ad0ec4ed53e82363ab8f24bc96cd29","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9b0bad5735b0eaf94f23e70df73a566ad2ad0ec4ed53e82363ab8f24bc96cd29","first_computed_at":"2026-07-05T06:45:36.424962Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:45:36.424962Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pghlT994OqYqch+75H+5CdIkxCNycwxMm8I9QB7AWa13vJIwUTPXPFSlQt+HrrwL8xctvLk/Gk4q6jKRh0g3Aw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:45:36.425557Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.17372","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9f0c0338932c8019d592c50cddcca155075196c79bdd6b9c9460adc889e19999","sha256:806d479b874cc0b989e1ff9e8eb1790edee66c5f5ebea31986d7f73106491ef6"],"state_sha256":"0a3c4eace144ba9186790aa8da4ab4b4a6102ad4874bc47be4b28f6b3e5d53a8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"y2ywtvUopIhPa9P75HM+BZCzoGiKQN0iK+NBbF0PDpTieNHyVC0Os619SOjfkQkpOV4d9Fxc5T+9dXCBWZbTAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-20T20:54:38.142730Z","bundle_sha256":"9dc654f4f605428dfd195d289202e46bddf5cc3e8ada047004c422fbbd8e9495"}}