{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2012:LIIBYJE4FISLMPLHCYJJ5EGOTO","short_pith_number":"pith:LIIBYJE4","canonical_record":{"source":{"id":"1301.0580","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2012-12-12T15:57:02Z","cross_cats_sorted":[],"title_canon_sha256":"8d6e47711a35aca07c84b8fe9dd37ed59c859689e7c4ce009b0b9e73fb7e3fd7","abstract_canon_sha256":"8edfc4a4a7c83e9ba3ef9fc4face89c32e8656d4334e633d00d882d133359875"},"schema_version":"1.0"},"canonical_sha256":"5a101c249c2a24b63d6716129e90ce9bb5ca97fac8c546fe0a078a001d674944","source":{"kind":"arxiv","id":"1301.0580","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2012:LIIBYJE4FISLMPLHCYJJ5EGOTO","target":"record","payload":{"canonical_record":{"source":{"id":"1301.0580","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2012-12-12T15:57:02Z","cross_cats_sorted":[],"title_canon_sha256":"8d6e47711a35aca07c84b8fe9dd37ed59c859689e7c4ce009b0b9e73fb7e3fd7","abstract_canon_sha256":"8edfc4a4a7c83e9ba3ef9fc4face89c32e8656d4334e633d00d882d133359875"},"schema_version":"1.0"},"canonical_sha256":"5a101c249c2a24b63d6716129e90ce9bb5ca97fac8c546fe0a078a001d674944","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:37:18.390856Z","signature_b64":"1kYF1/fH86pK1i24+0TEegPK6vvcEeRhiTbGX+aVnMotKG8FdN9U6s2GSYg+p+WXNhfErAYn6MyxRaKJPXUFBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5a101c249c2a24b63d6716129e90ce9bb5ca97fac8c546fe0a078a001d674944","last_reissued_at":"2026-05-18T03:37:18.390437Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:37:18.390437Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1301.0580","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":"2026-05-18T03:37:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"n1atpWmyhh5pWYYgKw0iBEXPTXRuN7TrZFC43vw8XtzNSXNeCVW/MHViMUKN68K1yAPjTwwrjxU5MEUMchjGBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-07T21:04:44.180896Z"},"content_sha256":"bf9e6540e813b0ce8d754d683188b1ad2ede1b7b19db7ffc0eee0baf6f98a08a","schema_version":"1.0","event_id":"sha256:bf9e6540e813b0ce8d754d683188b1ad2ede1b7b19db7ffc0eee0baf6f98a08a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2012:LIIBYJE4FISLMPLHCYJJ5EGOTO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Value Function Approximation in Zero-Sum Markov Games","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Michail Lagoudakis, Ron Parr","submitted_at":"2012-12-12T15:57:02Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1301.0580","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":""},"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":"2026-05-18T03:37:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kuBedZ1LXJlGIQ1YAJ2FM/lfqjesEcyVjEToWJ1PL11/krBo+z/NF/UiaAWFRgUcDgATqffxinySK3hGA4MaAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-07T21:04:44.181598Z"},"content_sha256":"90f1b029ccb9202459740668687d86b11aa84885c53fc10d6be2219c03351ebd","schema_version":"1.0","event_id":"sha256:90f1b029ccb9202459740668687d86b11aa84885c53fc10d6be2219c03351ebd"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LIIBYJE4FISLMPLHCYJJ5EGOTO/bundle.json","state_url":"https://pith.science/pith/LIIBYJE4FISLMPLHCYJJ5EGOTO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LIIBYJE4FISLMPLHCYJJ5EGOTO/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":"2026-06-07T21:04:44Z","links":{"resolver":"https://pith.science/pith/LIIBYJE4FISLMPLHCYJJ5EGOTO","bundle":"https://pith.science/pith/LIIBYJE4FISLMPLHCYJJ5EGOTO/bundle.json","state":"https://pith.science/pith/LIIBYJE4FISLMPLHCYJJ5EGOTO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LIIBYJE4FISLMPLHCYJJ5EGOTO/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Cju7hk5KDO6b3TNT17CAw+a4kfrOpVLWFrSMq2y+XGHPFvH0uSPYkOC8q1fDp2m2L1fEoM+9UD/sh/UGWSkBBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-07T21:04:44.185588Z","bundle_sha256":"43f8b93454ef6682e4b0a091d98ebb3abaec04f560362d78f9573140ade7e774"}}