mlsanityData to 14 Oct 2026

Constrained Policy Optimization for Provably Fair Order Matching

arXiv 2604.06522 ↗First posted 7 Apr 2026cs.GT math.DS math.OCcited by 0

On the map: Deep reinforcement learning methods → Adversarial robustness and RL in finance

Abstract (arXiv)

Automated matching engines execute millions of orders per session, yet systematic asymmetries in latency, order size, and market access compound into persistent execution disparities that erode participant trust. We formulate provably fair order matching as a Constrained Markov Decision Process and propose CPO-FOAM (Constrained Policy Optimization with Feedback-Optimized Adaptive Margins). An inner loop computes an analytic trust-region step on the Fisher information manifold; a PID-controlled outer loop dynamically tightens safety margins, suppressing the sawtooth oscillations endemic to Lagrangian methods under non-stationary dynamics. Group fairness (demographic parity, equalized odds) enters the CMDP cost vector while individual Lipschitz fairness is enforced deterministically via spectral normalization. We prove BIBO stability and that the integral term drives steady-state violations to zero. On LOBSTER NASDAQ data across six market regimes, CPO-FOAM recovers 95.9% of unconstrained throughput at 2.5% constraint violation frequency; on crypto-asset LOB data under MEV injection it captures 98.4% of the reward envelope at 3.2% CVF. The method scales sub-linearly to M=8 constraints, settles on-chain within one Ethereum block, and yields a 2.1X reward improvement on Safety-Gymnasium, confirming domain-agnostic generalization.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Adversarial robustness and RL in finance, one of 15 directions in Deep reinforcement learning methods. Builds on 15 of its 36 references that are in the map. First posted on arXiv 7 Apr 2026.

Builds on

15 of 36 references.

References · 15

  1. 2017Proximal Policy Optimization Algorithmscited by 15,215
  2. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 5,045
  3. 2015High-Dimensional Continuous Control Using Generalized Advantage Estimationcited by 2,026
  4. 2016Equality of Opportunity in Supervised Learningcited by 2,007
  5. 2018Spectral Normalization for Generative Adversarial Networkscited by 1,636
  6. 2017Constrained Policy Optimizationcited by 983
  7. 2018Reward Constrained Policy Optimizationcited by 417
  8. 2020Responsive Safety in Reinforcement Learning by PID Lagrangian Methodscited by 316
  9. 2018Regularisation of Neural Networks by Enforcing Lipschitz Continuitycited by 314
  10. 2023Safety-Gymnasium: A Unified Safe Reinforcement Learning Benchmarkcited by 143
  11. 2019IPO: Interior-point Policy Optimization under Constraintscited by 132
  12. 2014IPFS - Content Addressed, Versioned, P2P File Systemcited by 70
3 more
  1. 2019Algorithms for Fairness in Sequential Decision Makingcited by 56
  2. 2023JAX-LOB: A GPU-Accelerated limit order book simulator to unlock large scale reinforcement learning for tradingcited by 14
  3. 2019An analysis of Uniswap marketscited by 12

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Safe and Compliant Cross-Market Trade Execution via Constrained RL and Zero-Knowledge Audits
  2. 2025Fairness-Aware Reinforcement Learning (FAReL): A Framework for Transparent and Balanced Sequential Decision-Making
  3. 2026FARE: Deep Reinforcement Learning For Fair Exposure Constrained Uncertainty Aware Financial Content Personalization
  4. 2026Behavioral Privacy Leakage in Agentic Negotiation: Formalizing and Mitigating Inference Attacks via Randomized Policies
  5. 2026Optimize Wider, Not Deeper: Consensus Aggregation for Policy Optimization
  6. 2026Diverse Approaches to Optimal Execution Schedule Generation
  7. 2026Fairness Aware Reward Optimization
  8. 2025Matching Markets Meet LLMs: Algorithmic Reasoning with Ranked Preferences