{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:6EKVWULUOC6VBCV75MCVZ4H5K2","short_pith_number":"pith:6EKVWULU","canonical_record":{"source":{"id":"2003.12151","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2020-03-24T12:50:48Z","cross_cats_sorted":["cs.LG","cs.SY","eess.SY"],"title_canon_sha256":"e78aae9206280f4b006176e6b3e1a2b8fe94850b1b3f65ba77a959d57687bd2b","abstract_canon_sha256":"c5f54dc989fd9df5b2efe329fb08b2618f89a9af77973787b2625894e332370f"},"schema_version":"1.0"},"canonical_sha256":"f1155b517470bd508abfeb055cf0fd568bc5cb30fe70c21d8cd23af2712b6d91","source":{"kind":"arxiv","id":"2003.12151","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2003.12151","created_at":"2026-07-05T05:14:54Z"},{"alias_kind":"arxiv_version","alias_value":"2003.12151v3","created_at":"2026-07-05T05:14:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.12151","created_at":"2026-07-05T05:14:54Z"},{"alias_kind":"pith_short_12","alias_value":"6EKVWULUOC6V","created_at":"2026-07-05T05:14:54Z"},{"alias_kind":"pith_short_16","alias_value":"6EKVWULUOC6VBCV7","created_at":"2026-07-05T05:14:54Z"},{"alias_kind":"pith_short_8","alias_value":"6EKVWULU","created_at":"2026-07-05T05:14:54Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:6EKVWULUOC6VBCV75MCVZ4H5K2","target":"record","payload":{"canonical_record":{"source":{"id":"2003.12151","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2020-03-24T12:50:48Z","cross_cats_sorted":["cs.LG","cs.SY","eess.SY"],"title_canon_sha256":"e78aae9206280f4b006176e6b3e1a2b8fe94850b1b3f65ba77a959d57687bd2b","abstract_canon_sha256":"c5f54dc989fd9df5b2efe329fb08b2618f89a9af77973787b2625894e332370f"},"schema_version":"1.0"},"canonical_sha256":"f1155b517470bd508abfeb055cf0fd568bc5cb30fe70c21d8cd23af2712b6d91","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:14:54.366625Z","signature_b64":"icwSQMNeBG+GZz8IeOBK+Dnf1j1LBaOm/EJMrkwiEm+cezAUUas1ke4/7dzR2TC7Dm3udiBGtY3iUnGBqU0qBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f1155b517470bd508abfeb055cf0fd568bc5cb30fe70c21d8cd23af2712b6d91","last_reissued_at":"2026-07-05T05:14:54.366087Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:14:54.366087Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2003.12151","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":"2026-07-05T05:14:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OKjVuOzr0tiTcrRKeoiL3J/Vda1xju1b+HS6wXbOHv8oYJBFM9ch92ZH2047cPmHB1Z28yTsihiWTZtPxgR6Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T01:27:45.337589Z"},"content_sha256":"d43c8cb091fa0b697d57f631cbee77805f76924ff3450cb55f1e339fb93145be","schema_version":"1.0","event_id":"sha256:d43c8cb091fa0b697d57f631cbee77805f76924ff3450cb55f1e339fb93145be"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:6EKVWULUOC6VBCV75MCVZ4H5K2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Q-Learning in Regularized Mean-field Games","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SY","eess.SY"],"primary_cat":"math.OC","authors_text":"Berkay Anahtarci, Can Deha Kariksiz, Naci Saldi","submitted_at":"2020-03-24T12:50:48Z","abstract_excerpt":"In this paper, we introduce a regularized mean-field game and study learning of this game under an infinite-horizon discounted reward function. Regularization is introduced by adding a strongly concave regularization function to the one-stage reward function in the classical mean-field game model. We establish a value iteration based learning algorithm to this regularized mean-field game using fitted Q-learning. The regularization term in general makes reinforcement learning algorithm more robust to the system components. Moreover, it enables us to establish error analysis of the learning algo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.12151","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/2003.12151/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":"2026-07-05T05:14:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"u/ODEmYtuQDkXPTbzUyWJfN4PRCXB+86v7sjK19iqBV6wSawDjhZoMyVZPvk0urLvEwHtIwNpwKDX1U9NNFxDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T01:27:45.338088Z"},"content_sha256":"de6cdc2fd6c2b93979bcfb38d78475691d65c751893de45f2e266f75a651ae24","schema_version":"1.0","event_id":"sha256:de6cdc2fd6c2b93979bcfb38d78475691d65c751893de45f2e266f75a651ae24"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6EKVWULUOC6VBCV75MCVZ4H5K2/bundle.json","state_url":"https://pith.science/pith/6EKVWULUOC6VBCV75MCVZ4H5K2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6EKVWULUOC6VBCV75MCVZ4H5K2/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":"2026-08-06T01:27:45Z","links":{"resolver":"https://pith.science/pith/6EKVWULUOC6VBCV75MCVZ4H5K2","bundle":"https://pith.science/pith/6EKVWULUOC6VBCV75MCVZ4H5K2/bundle.json","state":"https://pith.science/pith/6EKVWULUOC6VBCV75MCVZ4H5K2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6EKVWULUOC6VBCV75MCVZ4H5K2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:6EKVWULUOC6VBCV75MCVZ4H5K2","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":"c5f54dc989fd9df5b2efe329fb08b2618f89a9af77973787b2625894e332370f","cross_cats_sorted":["cs.LG","cs.SY","eess.SY"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2020-03-24T12:50:48Z","title_canon_sha256":"e78aae9206280f4b006176e6b3e1a2b8fe94850b1b3f65ba77a959d57687bd2b"},"schema_version":"1.0","source":{"id":"2003.12151","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2003.12151","created_at":"2026-07-05T05:14:54Z"},{"alias_kind":"arxiv_version","alias_value":"2003.12151v3","created_at":"2026-07-05T05:14:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.12151","created_at":"2026-07-05T05:14:54Z"},{"alias_kind":"pith_short_12","alias_value":"6EKVWULUOC6V","created_at":"2026-07-05T05:14:54Z"},{"alias_kind":"pith_short_16","alias_value":"6EKVWULUOC6VBCV7","created_at":"2026-07-05T05:14:54Z"},{"alias_kind":"pith_short_8","alias_value":"6EKVWULU","created_at":"2026-07-05T05:14:54Z"}],"graph_snapshots":[{"event_id":"sha256:de6cdc2fd6c2b93979bcfb38d78475691d65c751893de45f2e266f75a651ae24","target":"graph","created_at":"2026-07-05T05:14:54Z","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/2003.12151/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we introduce a regularized mean-field game and study learning of this game under an infinite-horizon discounted reward function. Regularization is introduced by adding a strongly concave regularization function to the one-stage reward function in the classical mean-field game model. We establish a value iteration based learning algorithm to this regularized mean-field game using fitted Q-learning. The regularization term in general makes reinforcement learning algorithm more robust to the system components. Moreover, it enables us to establish error analysis of the learning algo","authors_text":"Berkay Anahtarci, Can Deha Kariksiz, Naci Saldi","cross_cats":["cs.LG","cs.SY","eess.SY"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2020-03-24T12:50:48Z","title":"Q-Learning in Regularized Mean-field Games"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.12151","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:d43c8cb091fa0b697d57f631cbee77805f76924ff3450cb55f1e339fb93145be","target":"record","created_at":"2026-07-05T05:14:54Z","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":"c5f54dc989fd9df5b2efe329fb08b2618f89a9af77973787b2625894e332370f","cross_cats_sorted":["cs.LG","cs.SY","eess.SY"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2020-03-24T12:50:48Z","title_canon_sha256":"e78aae9206280f4b006176e6b3e1a2b8fe94850b1b3f65ba77a959d57687bd2b"},"schema_version":"1.0","source":{"id":"2003.12151","kind":"arxiv","version":3}},"canonical_sha256":"f1155b517470bd508abfeb055cf0fd568bc5cb30fe70c21d8cd23af2712b6d91","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f1155b517470bd508abfeb055cf0fd568bc5cb30fe70c21d8cd23af2712b6d91","first_computed_at":"2026-07-05T05:14:54.366087Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:14:54.366087Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"icwSQMNeBG+GZz8IeOBK+Dnf1j1LBaOm/EJMrkwiEm+cezAUUas1ke4/7dzR2TC7Dm3udiBGtY3iUnGBqU0qBg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:14:54.366625Z","signed_message":"canonical_sha256_bytes"},"source_id":"2003.12151","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d43c8cb091fa0b697d57f631cbee77805f76924ff3450cb55f1e339fb93145be","sha256:de6cdc2fd6c2b93979bcfb38d78475691d65c751893de45f2e266f75a651ae24"],"state_sha256":"03de7e92cf08c0ded54c3403f172a97db29f77a3d1f669cf49ace3b9972839be"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Mnr4sPJzrJG1QhJipouwt1JpOBfKD3BEPVj5ZYZrSF1s9AsWBR4v8CDMbZIwm3glHU6hFIwY6ZGkT1iEuhxLDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T01:27:45.343296Z","bundle_sha256":"1ee4724d3cf36acadf707ce37f2be7482b09323728efa21303e25f78c0ffe8cb"}}