{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:75KAXS2PRX7W6H5LSZXQUN2LG7","short_pith_number":"pith:75KAXS2P","canonical_record":{"source":{"id":"2303.13539","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-03-16T14:25:16Z","cross_cats_sorted":["cs.GT"],"title_canon_sha256":"12afae21d870c4b8756763515b360426d8d6d626df360d521dbc0c488dcccfb2","abstract_canon_sha256":"7d8ef0ff6efbbd62c8df109caddbfd4c78ee7f14fa6bb7068040a26482150308"},"schema_version":"1.0"},"canonical_sha256":"ff540bcb4f8dff6f1fab966f0a374b37e18e3267879b71e803a1837513fa513c","source":{"kind":"arxiv","id":"2303.13539","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.13539","created_at":"2026-07-05T08:00:59Z"},{"alias_kind":"arxiv_version","alias_value":"2303.13539v1","created_at":"2026-07-05T08:00:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.13539","created_at":"2026-07-05T08:00:59Z"},{"alias_kind":"pith_short_12","alias_value":"75KAXS2PRX7W","created_at":"2026-07-05T08:00:59Z"},{"alias_kind":"pith_short_16","alias_value":"75KAXS2PRX7W6H5L","created_at":"2026-07-05T08:00:59Z"},{"alias_kind":"pith_short_8","alias_value":"75KAXS2P","created_at":"2026-07-05T08:00:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:75KAXS2PRX7W6H5LSZXQUN2LG7","target":"record","payload":{"canonical_record":{"source":{"id":"2303.13539","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-03-16T14:25:16Z","cross_cats_sorted":["cs.GT"],"title_canon_sha256":"12afae21d870c4b8756763515b360426d8d6d626df360d521dbc0c488dcccfb2","abstract_canon_sha256":"7d8ef0ff6efbbd62c8df109caddbfd4c78ee7f14fa6bb7068040a26482150308"},"schema_version":"1.0"},"canonical_sha256":"ff540bcb4f8dff6f1fab966f0a374b37e18e3267879b71e803a1837513fa513c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:00:59.160799Z","signature_b64":"bjcCZQ0INii2ipBo0cnhxbYmloU2o6nHDMlHqp46gxIYlvaFkaz6KhFDBuo6PxGzp3dMRssnEzp5CkvCDoQoCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ff540bcb4f8dff6f1fab966f0a374b37e18e3267879b71e803a1837513fa513c","last_reissued_at":"2026-07-05T08:00:59.160332Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:00:59.160332Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2303.13539","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:00:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"12sXhvva9q3MAAO2v3pgEALcOlW5FA5fJ4mWwWeItHpPTXWxDxo58wjiT1OlfyQJBnTl4LXfqThn8WRoj2CmAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T02:12:02.334398Z"},"content_sha256":"5cccbc8ac44046a496ef34865b2f07a6b86b7450328682b9d1d20a37464900c5","schema_version":"1.0","event_id":"sha256:5cccbc8ac44046a496ef34865b2f07a6b86b7450328682b9d1d20a37464900c5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:75KAXS2PRX7W6H5LSZXQUN2LG7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Decentralized Multi-Agent Reinforcement Learning for Continuous-Space Stochastic Games","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.GT"],"primary_cat":"cs.LG","authors_text":"Awni Altabaa, Bora Yongacoglu, Serdar Y\\\"uksel","submitted_at":"2023-03-16T14:25:16Z","abstract_excerpt":"Stochastic games are a popular framework for studying multi-agent reinforcement learning (MARL). Recent advances in MARL have focused primarily on games with finitely many states. In this work, we study multi-agent learning in stochastic games with general state spaces and an information structure in which agents do not observe each other's actions. In this context, we propose a decentralized MARL algorithm and we prove the near-optimality of its policy updates. Furthermore, we study the global policy-updating dynamics for a general class of best-reply based algorithms and derive a closed-form"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.13539","kind":"arxiv","version":1},"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/2303.13539/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":"2026-07-05T08:00:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sKrTnJHk9ne4h9Mv3cGszpi4f/5DjkY6QKm7uIW5jAh6nAGrmteejS6EJdTD8/x00xAJ5uS6fMFNqZTrk/DHBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T02:12:02.335321Z"},"content_sha256":"a46ff2cacbbd08e2821fd2eb49f8d5d78e766ff8bdb1c18cba9c58edf8e5f544","schema_version":"1.0","event_id":"sha256:a46ff2cacbbd08e2821fd2eb49f8d5d78e766ff8bdb1c18cba9c58edf8e5f544"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/75KAXS2PRX7W6H5LSZXQUN2LG7/bundle.json","state_url":"https://pith.science/pith/75KAXS2PRX7W6H5LSZXQUN2LG7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/75KAXS2PRX7W6H5LSZXQUN2LG7/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":"2026-08-15T02:12:02Z","links":{"resolver":"https://pith.science/pith/75KAXS2PRX7W6H5LSZXQUN2LG7","bundle":"https://pith.science/pith/75KAXS2PRX7W6H5LSZXQUN2LG7/bundle.json","state":"https://pith.science/pith/75KAXS2PRX7W6H5LSZXQUN2LG7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/75KAXS2PRX7W6H5LSZXQUN2LG7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:75KAXS2PRX7W6H5LSZXQUN2LG7","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":"7d8ef0ff6efbbd62c8df109caddbfd4c78ee7f14fa6bb7068040a26482150308","cross_cats_sorted":["cs.GT"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-03-16T14:25:16Z","title_canon_sha256":"12afae21d870c4b8756763515b360426d8d6d626df360d521dbc0c488dcccfb2"},"schema_version":"1.0","source":{"id":"2303.13539","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.13539","created_at":"2026-07-05T08:00:59Z"},{"alias_kind":"arxiv_version","alias_value":"2303.13539v1","created_at":"2026-07-05T08:00:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.13539","created_at":"2026-07-05T08:00:59Z"},{"alias_kind":"pith_short_12","alias_value":"75KAXS2PRX7W","created_at":"2026-07-05T08:00:59Z"},{"alias_kind":"pith_short_16","alias_value":"75KAXS2PRX7W6H5L","created_at":"2026-07-05T08:00:59Z"},{"alias_kind":"pith_short_8","alias_value":"75KAXS2P","created_at":"2026-07-05T08:00:59Z"}],"graph_snapshots":[{"event_id":"sha256:a46ff2cacbbd08e2821fd2eb49f8d5d78e766ff8bdb1c18cba9c58edf8e5f544","target":"graph","created_at":"2026-07-05T08:00:59Z","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/2303.13539/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Stochastic games are a popular framework for studying multi-agent reinforcement learning (MARL). Recent advances in MARL have focused primarily on games with finitely many states. In this work, we study multi-agent learning in stochastic games with general state spaces and an information structure in which agents do not observe each other's actions. In this context, we propose a decentralized MARL algorithm and we prove the near-optimality of its policy updates. Furthermore, we study the global policy-updating dynamics for a general class of best-reply based algorithms and derive a closed-form","authors_text":"Awni Altabaa, Bora Yongacoglu, Serdar Y\\\"uksel","cross_cats":["cs.GT"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-03-16T14:25:16Z","title":"Decentralized Multi-Agent Reinforcement Learning for Continuous-Space Stochastic Games"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.13539","kind":"arxiv","version":1},"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":"sha256:5cccbc8ac44046a496ef34865b2f07a6b86b7450328682b9d1d20a37464900c5","target":"record","created_at":"2026-07-05T08:00:59Z","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":"7d8ef0ff6efbbd62c8df109caddbfd4c78ee7f14fa6bb7068040a26482150308","cross_cats_sorted":["cs.GT"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-03-16T14:25:16Z","title_canon_sha256":"12afae21d870c4b8756763515b360426d8d6d626df360d521dbc0c488dcccfb2"},"schema_version":"1.0","source":{"id":"2303.13539","kind":"arxiv","version":1}},"canonical_sha256":"ff540bcb4f8dff6f1fab966f0a374b37e18e3267879b71e803a1837513fa513c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ff540bcb4f8dff6f1fab966f0a374b37e18e3267879b71e803a1837513fa513c","first_computed_at":"2026-07-05T08:00:59.160332Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:00:59.160332Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bjcCZQ0INii2ipBo0cnhxbYmloU2o6nHDMlHqp46gxIYlvaFkaz6KhFDBuo6PxGzp3dMRssnEzp5CkvCDoQoCg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:00:59.160799Z","signed_message":"canonical_sha256_bytes"},"source_id":"2303.13539","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5cccbc8ac44046a496ef34865b2f07a6b86b7450328682b9d1d20a37464900c5","sha256:a46ff2cacbbd08e2821fd2eb49f8d5d78e766ff8bdb1c18cba9c58edf8e5f544"],"state_sha256":"b28ffc0cd01b312b03bde7bfbed002cc0f7903b68645bc9480aeb3a80f9a3289"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pFR9tC5ShWa6KjeVSE8/B2+W09qSAcrqC4YizOSxiGBsQRaILVkpwqTNKOyMli1q7h6v1b7QVdisKNCxZze2Dw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T02:12:02.341994Z","bundle_sha256":"f0b868c77ca7707f6abd70a86d9af210f7620b8ef3a6da4a34c744c589dafa3f"}}