{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2012:UYJCRZCM74TNQBQQKRB5KCC5PY","short_pith_number":"pith:UYJCRZCM","canonical_record":{"source":{"id":"1202.5298","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SY","submitted_at":"2012-02-23T20:53:18Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"e650ca3af18ded9bfc4d9a54fd0684f308bc41a26bc512dc66920f2c3beb35ab","abstract_canon_sha256":"94808e64adf6fa75a399f07643e940d3057dbe5d23fb49fb87c0792782b8a3f8"},"schema_version":"1.0"},"canonical_sha256":"a61228e44cff26d806105443d5085d7e308600b27bdb72b897d01e3d8ce95bc8","source":{"kind":"arxiv","id":"1202.5298","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1202.5298","created_at":"2026-05-18T03:41:58Z"},{"alias_kind":"arxiv_version","alias_value":"1202.5298v2","created_at":"2026-05-18T03:41:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1202.5298","created_at":"2026-05-18T03:41:58Z"},{"alias_kind":"pith_short_12","alias_value":"UYJCRZCM74TN","created_at":"2026-05-18T12:27:25Z"},{"alias_kind":"pith_short_16","alias_value":"UYJCRZCM74TNQBQQ","created_at":"2026-05-18T12:27:25Z"},{"alias_kind":"pith_short_8","alias_value":"UYJCRZCM","created_at":"2026-05-18T12:27:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2012:UYJCRZCM74TNQBQQKRB5KCC5PY","target":"record","payload":{"canonical_record":{"source":{"id":"1202.5298","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SY","submitted_at":"2012-02-23T20:53:18Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"e650ca3af18ded9bfc4d9a54fd0684f308bc41a26bc512dc66920f2c3beb35ab","abstract_canon_sha256":"94808e64adf6fa75a399f07643e940d3057dbe5d23fb49fb87c0792782b8a3f8"},"schema_version":"1.0"},"canonical_sha256":"a61228e44cff26d806105443d5085d7e308600b27bdb72b897d01e3d8ce95bc8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:41:58.814860Z","signature_b64":"WVB8d7cBxN3Lk1h7qSctSCiWxwUYq1CC/EoTMoKkgxrnNYVbKSiobSDqTSADrPI272NNi0hIPhLy8GAGoFQlBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a61228e44cff26d806105443d5085d7e308600b27bdb72b897d01e3d8ce95bc8","last_reissued_at":"2026-05-18T03:41:58.814328Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:41:58.814328Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1202.5298","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T03:41:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Mg5ZpsFwCFQWF558zdDoT6FT3sG7bua5DKo805JdzOogpPmbU6V9gCRQeYKGhYIqUmbzloq/hW/XEk/2zSnmDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T21:22:11.893666Z"},"content_sha256":"ae46d0c3713abba1ea4b611b9a96138ed80410e4a1d842d938733ec68f66b3b8","schema_version":"1.0","event_id":"sha256:ae46d0c3713abba1ea4b611b9a96138ed80410e4a1d842d938733ec68f66b3b8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2012:UYJCRZCM74TNQBQQKRB5KCC5PY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Min Max Generalization for Two-stage Deterministic Batch Mode Reinforcement Learning: Relaxation Schemes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.SY","authors_text":"Bernard Boigelot, Damien Ernst, Quentin Louveaux, Raphael Fonteneau","submitted_at":"2012-02-23T20:53:18Z","abstract_excerpt":"We study the minmax optimization problem introduced in [22] for computing policies for batch mode reinforcement learning in a deterministic setting. First, we show that this problem is NP-hard. In the two-stage case, we provide two relaxation schemes. The first relaxation scheme works by dropping some constraints in order to obtain a problem that is solvable in polynomial time. The second relaxation scheme, based on a Lagrangian relaxation where all constraints are dualized, leads to a conic quadratic programming problem. We also theoretically prove and empirically illustrate that both relaxat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1202.5298","kind":"arxiv","version":2},"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":"2026-05-18T03:41:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ULSJvZ/UXpRuNJa6bTtNVfdkWepHhGDDZFS5aGjPMC82HvTIZXslbfpFS+XxgNtuyWl6OV6Qktt5+v/dCnDRDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T21:22:11.894356Z"},"content_sha256":"fd046cc56b7a94b5f6dd81a3f68522576c121ad3b88aa389ff5da0b683ab7d2c","schema_version":"1.0","event_id":"sha256:fd046cc56b7a94b5f6dd81a3f68522576c121ad3b88aa389ff5da0b683ab7d2c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UYJCRZCM74TNQBQQKRB5KCC5PY/bundle.json","state_url":"https://pith.science/pith/UYJCRZCM74TNQBQQKRB5KCC5PY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UYJCRZCM74TNQBQQKRB5KCC5PY/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":"2026-06-06T21:22:11Z","links":{"resolver":"https://pith.science/pith/UYJCRZCM74TNQBQQKRB5KCC5PY","bundle":"https://pith.science/pith/UYJCRZCM74TNQBQQKRB5KCC5PY/bundle.json","state":"https://pith.science/pith/UYJCRZCM74TNQBQQKRB5KCC5PY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UYJCRZCM74TNQBQQKRB5KCC5PY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2012:UYJCRZCM74TNQBQQKRB5KCC5PY","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":"94808e64adf6fa75a399f07643e940d3057dbe5d23fb49fb87c0792782b8a3f8","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SY","submitted_at":"2012-02-23T20:53:18Z","title_canon_sha256":"e650ca3af18ded9bfc4d9a54fd0684f308bc41a26bc512dc66920f2c3beb35ab"},"schema_version":"1.0","source":{"id":"1202.5298","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1202.5298","created_at":"2026-05-18T03:41:58Z"},{"alias_kind":"arxiv_version","alias_value":"1202.5298v2","created_at":"2026-05-18T03:41:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1202.5298","created_at":"2026-05-18T03:41:58Z"},{"alias_kind":"pith_short_12","alias_value":"UYJCRZCM74TN","created_at":"2026-05-18T12:27:25Z"},{"alias_kind":"pith_short_16","alias_value":"UYJCRZCM74TNQBQQ","created_at":"2026-05-18T12:27:25Z"},{"alias_kind":"pith_short_8","alias_value":"UYJCRZCM","created_at":"2026-05-18T12:27:25Z"}],"graph_snapshots":[{"event_id":"sha256:fd046cc56b7a94b5f6dd81a3f68522576c121ad3b88aa389ff5da0b683ab7d2c","target":"graph","created_at":"2026-05-18T03:41:58Z","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":"We study the minmax optimization problem introduced in [22] for computing policies for batch mode reinforcement learning in a deterministic setting. First, we show that this problem is NP-hard. In the two-stage case, we provide two relaxation schemes. The first relaxation scheme works by dropping some constraints in order to obtain a problem that is solvable in polynomial time. The second relaxation scheme, based on a Lagrangian relaxation where all constraints are dualized, leads to a conic quadratic programming problem. We also theoretically prove and empirically illustrate that both relaxat","authors_text":"Bernard Boigelot, Damien Ernst, Quentin Louveaux, Raphael Fonteneau","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SY","submitted_at":"2012-02-23T20:53:18Z","title":"Min Max Generalization for Two-stage Deterministic Batch Mode Reinforcement Learning: Relaxation Schemes"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1202.5298","kind":"arxiv","version":2},"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:ae46d0c3713abba1ea4b611b9a96138ed80410e4a1d842d938733ec68f66b3b8","target":"record","created_at":"2026-05-18T03:41:58Z","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":"94808e64adf6fa75a399f07643e940d3057dbe5d23fb49fb87c0792782b8a3f8","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SY","submitted_at":"2012-02-23T20:53:18Z","title_canon_sha256":"e650ca3af18ded9bfc4d9a54fd0684f308bc41a26bc512dc66920f2c3beb35ab"},"schema_version":"1.0","source":{"id":"1202.5298","kind":"arxiv","version":2}},"canonical_sha256":"a61228e44cff26d806105443d5085d7e308600b27bdb72b897d01e3d8ce95bc8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a61228e44cff26d806105443d5085d7e308600b27bdb72b897d01e3d8ce95bc8","first_computed_at":"2026-05-18T03:41:58.814328Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:41:58.814328Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WVB8d7cBxN3Lk1h7qSctSCiWxwUYq1CC/EoTMoKkgxrnNYVbKSiobSDqTSADrPI272NNi0hIPhLy8GAGoFQlBA==","signature_status":"signed_v1","signed_at":"2026-05-18T03:41:58.814860Z","signed_message":"canonical_sha256_bytes"},"source_id":"1202.5298","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ae46d0c3713abba1ea4b611b9a96138ed80410e4a1d842d938733ec68f66b3b8","sha256:fd046cc56b7a94b5f6dd81a3f68522576c121ad3b88aa389ff5da0b683ab7d2c"],"state_sha256":"a5125dce3f5566012c7869c4cd01f271bebad25bfa697ed3bfc8b2a6cd5c42c3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+ER8K7Ud+36zGGfZywYQZuI0D/k19rZ3QZmPj8mA7lgaPIofYNPgN7o3r3v0FlKb1i3Qk3F7MS/6dU55zT6QCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-06T21:22:11.898213Z","bundle_sha256":"5e1f62b780c39047e40ec1108ee953265bec0f50188e1f363eae8516606fff84"}}