{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:ODGLASTCTC5LPQCHZ5BH6HXQM7","short_pith_number":"pith:ODGLASTC","schema_version":"1.0","canonical_sha256":"70ccb04a6298bab7c047cf427f1ef067f16830562d9aa1660b64b98b40307f12","source":{"kind":"arxiv","id":"2003.01820","version":2},"attestation_state":"computed","paper":{"title":"Robust Market Making via Adversarial Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","stat.ML"],"primary_cat":"q-fin.TR","authors_text":"Rahul Savani, Thomas Spooner","submitted_at":"2020-03-03T22:40:57Z","abstract_excerpt":"We show that adversarial reinforcement learning (ARL) can be used to produce market marking agents that are robust to adversarial and adaptively-chosen market conditions. To apply ARL, we turn the well-studied single-agent model of Avellaneda and Stoikov [2008] into a discrete-time zero-sum game between a market maker and adversary. The adversary acts as a proxy for other market participants that would like to profit at the market maker's expense. We empirically compare two conventional single-agent RL agents with ARL, and show that our ARL approach leads to: 1) the emergence of risk-averse be"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2003.01820","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-fin.TR","submitted_at":"2020-03-03T22:40:57Z","cross_cats_sorted":["cs.AI","cs.LG","stat.ML"],"title_canon_sha256":"7f5ab2ce68d4b657debc46052d2778d99ea8e5e5e176652680859c01ceb3659e","abstract_canon_sha256":"43f63e296431c62a392096754f21e18cc695c29e3cd649209148d3e86e702ab5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:17:17.154067Z","signature_b64":"L4d6kbV3+oYkh2c2uAD375mxgZu3kkstO0ruWl4wGVCu6N938DmPqyJyl1otLuuwStjbNfBYm2hj4KKRhKONBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"70ccb04a6298bab7c047cf427f1ef067f16830562d9aa1660b64b98b40307f12","last_reissued_at":"2026-07-05T01:17:17.153579Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:17:17.153579Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Robust Market Making via Adversarial Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","stat.ML"],"primary_cat":"q-fin.TR","authors_text":"Rahul Savani, Thomas Spooner","submitted_at":"2020-03-03T22:40:57Z","abstract_excerpt":"We show that adversarial reinforcement learning (ARL) can be used to produce market marking agents that are robust to adversarial and adaptively-chosen market conditions. To apply ARL, we turn the well-studied single-agent model of Avellaneda and Stoikov [2008] into a discrete-time zero-sum game between a market maker and adversary. The adversary acts as a proxy for other market participants that would like to profit at the market maker's expense. We empirically compare two conventional single-agent RL agents with ARL, and show that our ARL approach leads to: 1) the emergence of risk-averse be"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.01820","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2003.01820/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2003.01820","created_at":"2026-07-05T01:17:17.153639+00:00"},{"alias_kind":"arxiv_version","alias_value":"2003.01820v2","created_at":"2026-07-05T01:17:17.153639+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.01820","created_at":"2026-07-05T01:17:17.153639+00:00"},{"alias_kind":"pith_short_12","alias_value":"ODGLASTCTC5L","created_at":"2026-07-05T01:17:17.153639+00:00"},{"alias_kind":"pith_short_16","alias_value":"ODGLASTCTC5LPQCH","created_at":"2026-07-05T01:17:17.153639+00:00"},{"alias_kind":"pith_short_8","alias_value":"ODGLASTC","created_at":"2026-07-05T01:17:17.153639+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ODGLASTCTC5LPQCHZ5BH6HXQM7","json":"https://pith.science/pith/ODGLASTCTC5LPQCHZ5BH6HXQM7.json","graph_json":"https://pith.science/api/pith-number/ODGLASTCTC5LPQCHZ5BH6HXQM7/graph.json","events_json":"https://pith.science/api/pith-number/ODGLASTCTC5LPQCHZ5BH6HXQM7/events.json","paper":"https://pith.science/paper/ODGLASTC"},"agent_actions":{"view_html":"https://pith.science/pith/ODGLASTCTC5LPQCHZ5BH6HXQM7","download_json":"https://pith.science/pith/ODGLASTCTC5LPQCHZ5BH6HXQM7.json","view_paper":"https://pith.science/paper/ODGLASTC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2003.01820&json=true","fetch_graph":"https://pith.science/api/pith-number/ODGLASTCTC5LPQCHZ5BH6HXQM7/graph.json","fetch_events":"https://pith.science/api/pith-number/ODGLASTCTC5LPQCHZ5BH6HXQM7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ODGLASTCTC5LPQCHZ5BH6HXQM7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ODGLASTCTC5LPQCHZ5BH6HXQM7/action/storage_attestation","attest_author":"https://pith.science/pith/ODGLASTCTC5LPQCHZ5BH6HXQM7/action/author_attestation","sign_citation":"https://pith.science/pith/ODGLASTCTC5LPQCHZ5BH6HXQM7/action/citation_signature","submit_replication":"https://pith.science/pith/ODGLASTCTC5LPQCHZ5BH6HXQM7/action/replication_record"}},"created_at":"2026-07-05T01:17:17.153639+00:00","updated_at":"2026-07-05T01:17:17.153639+00:00"}