{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2012:LIIBYJE4FISLMPLHCYJJ5EGOTO","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":"8edfc4a4a7c83e9ba3ef9fc4face89c32e8656d4334e633d00d882d133359875","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2012-12-12T15:57:02Z","title_canon_sha256":"8d6e47711a35aca07c84b8fe9dd37ed59c859689e7c4ce009b0b9e73fb7e3fd7"},"schema_version":"1.0","source":{"id":"1301.0580","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1301.0580","created_at":"2026-05-18T03:37:18Z"},{"alias_kind":"arxiv_version","alias_value":"1301.0580v1","created_at":"2026-05-18T03:37:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1301.0580","created_at":"2026-05-18T03:37:18Z"},{"alias_kind":"pith_short_12","alias_value":"LIIBYJE4FISL","created_at":"2026-05-18T12:27:14Z"},{"alias_kind":"pith_short_16","alias_value":"LIIBYJE4FISLMPLH","created_at":"2026-05-18T12:27:14Z"},{"alias_kind":"pith_short_8","alias_value":"LIIBYJE4","created_at":"2026-05-18T12:27:14Z"}],"graph_snapshots":[{"event_id":"sha256:90f1b029ccb9202459740668687d86b11aa84885c53fc10d6be2219c03351ebd","target":"graph","created_at":"2026-05-18T03:37:18Z","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":"This paper investigates value function approximation in the context of zero-sum Markov games, which can be viewed as a generalization of the Markov decision process (MDP) framework to the two-agent case.  We generalize error bounds from MDPs to Markov games and describe generalizations of reinforcement learning algorithms to Markov games. We present a generalization of the optimal stopping problem to a two-player simultaneous move Markov game.  For this special problem, we provide stronger bounds and can guarantee convergence for LSTD and temporal difference learning with linear value function","authors_text":"Michail Lagoudakis, Ron Parr","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2012-12-12T15:57:02Z","title":"Value Function Approximation in Zero-Sum Markov Games"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1301.0580","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:bf9e6540e813b0ce8d754d683188b1ad2ede1b7b19db7ffc0eee0baf6f98a08a","target":"record","created_at":"2026-05-18T03:37:18Z","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":"8edfc4a4a7c83e9ba3ef9fc4face89c32e8656d4334e633d00d882d133359875","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2012-12-12T15:57:02Z","title_canon_sha256":"8d6e47711a35aca07c84b8fe9dd37ed59c859689e7c4ce009b0b9e73fb7e3fd7"},"schema_version":"1.0","source":{"id":"1301.0580","kind":"arxiv","version":1}},"canonical_sha256":"5a101c249c2a24b63d6716129e90ce9bb5ca97fac8c546fe0a078a001d674944","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5a101c249c2a24b63d6716129e90ce9bb5ca97fac8c546fe0a078a001d674944","first_computed_at":"2026-05-18T03:37:18.390437Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:37:18.390437Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1kYF1/fH86pK1i24+0TEegPK6vvcEeRhiTbGX+aVnMotKG8FdN9U6s2GSYg+p+WXNhfErAYn6MyxRaKJPXUFBg==","signature_status":"signed_v1","signed_at":"2026-05-18T03:37:18.390856Z","signed_message":"canonical_sha256_bytes"},"source_id":"1301.0580","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bf9e6540e813b0ce8d754d683188b1ad2ede1b7b19db7ffc0eee0baf6f98a08a","sha256:90f1b029ccb9202459740668687d86b11aa84885c53fc10d6be2219c03351ebd"],"state_sha256":"ce79d3f42f8b8183fcf6efefcf1559d3518a498c782943adb7b61afa08927cba"}