Deep Learning for Dynamic Programming with Recursive Utility Using First-order Conditions

• URL: http://arxiv.org/abs/2607.09461v1
• Date: Fri, 10 Jul 2026 14:36:28 GMT
• Title: Deep Learning for Dynamic Programming with Recursive Utility Using First-order Conditions
• Abstract summary: This paper proposes the certainty-equivalent first-order learning (CEFOL) algorithm, a deep learning algorithm for solving discrete-time dynamic programming problems with recursive utility.<n>By introducing a separate neural network to represent the certainty equivalent, CEFOL enables the exploitation of the Bellman and model-specific first-order optimality conditions.<n>In addition to certainty equivalent, CEFOL also uses neural networks to learn the value functions, policy functions, and Lagrange multipliers.<n>We apply the algorithm to risk-sensitive and Epstein--Zin consumption-saving problems, a small-noise robust-control problem, and
• Score: 11.870588188339168
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: This paper proposes the certainty-equivalent first-order learning (CEFOL) algorithm, a deep learning algorithm for solving discrete-time dynamic programming problems with recursive utility. Dynamic programming with recursive utility is challenging because nonlinear certainty equivalent appears in the Bellman equation and the first-order optimality conditions but is difficult to evaluate. By introducing a separate neural network to represent the certainty equivalent, CEFOL enables the exploitation of the Bellman and model-specific first-order optimality conditions. In addition to certainty equivalent, CEFOL also uses neural networks to learn the value functions, policy functions, and Lagrange multipliers by using model-specific first-order conditions to construct residuals for minimization. By using first-order and KKT residuals to learn the policy, CEFOL directly accommodates general equality and inequality constraints on the controls, including occasionally binding constraints, without requiring penalty functions or problem-specific reformulations. We apply the algorithm to risk-sensitive and Epstein--Zin consumption-saving problems, a small-noise robust-control problem, and a DSGE model with recursive preferences and stochastic volatility. Across these applications, out-of-sample Bellman diagnostics and model-specific optimality residuals, including Euler or first-order residuals where applicable, are generally of order 1.0e-4 to 1.0e-3 over the relevant state regions, with larger values mainly near binding constraints, and the learned value and policy functions closely match VFI benchmarks when available. The CEFOL algorithm also works for dynamic programming problems with expected utility, as expected utility is a special case of recursive utility.

Related papers

• Deep Learning for Dynamic Programming with Recursive Utility [12.828016037720907]
  We propose the first deep learning algorithm, the Certainty Equivalent Learning (CEL) algorithm, for solving high-dimensional discrete-time dynamic programming problems.<n>CEL learns certainty-equivalent value directly with neural networks and jointly approximates value functions, policy functions, and certainty-equivalent functions.<n>CEL delivers accurate value and policy approximations, remains effective in high-dimensional problems, achieves accuracy comparable to VFI in the small-noise robust-control case, and produces out-of-sample Bellman errors.
  arXiv  Detail & Related papers  (2026-07-05T12:43:03Z)
• A Single-Loop Bilevel Deep Learning Method for Optimal Control of Obstacle Problems [10.846737757627638]
  We propose a single-loop bilevel deep learning method, which is mesh-free, scalable to high-dimensional and complex domains, and avoids repeated solution of discretized subproblems.<n>The proposed method achieves satisfactory accuracy while reducing computational cost compared to classical numerical methods.
  arXiv  Detail & Related papers  (2026-01-07T17:30:42Z)
• Single-loop Algorithms for Stochastic Non-convex Optimization with Weakly-Convex Constraints [49.76332265680669]
  This paper examines a crucial subset of problems where both the objective and constraint functions are weakly convex.<n>Existing methods often face limitations, including slow convergence rates or reliance on double-loop designs.<n>We introduce a novel single-loop penalty-based algorithm to overcome these challenges.
  arXiv  Detail & Related papers  (2025-04-21T17:15:48Z)
• Efficiently Training Deep-Learning Parametric Policies using Lagrangian Duality [55.06411438416805]
  Constrained Markov Decision Processes (CMDPs) are critical in many high-stakes applications.<n>This paper introduces a novel approach, Two-Stage Deep Decision Rules (TS- DDR) to efficiently train parametric actor policies.<n>It is shown to enhance solution quality and to reduce computation times by several orders of magnitude when compared to current state-of-the-art methods.
  arXiv  Detail & Related papers  (2024-05-23T18:19:47Z)
• A Penalty-Based Guardrail Algorithm for Non-Decreasing Optimization with Inequality Constraints [1.5498250598583487]
  Traditional mathematical programming solvers require long computational times to solve constrained minimization problems. We propose a penalty-based guardrail algorithm (PGA) to efficiently solve them.
  arXiv  Detail & Related papers  (2024-05-03T10:37:34Z)
• Sub-linear Regret in Adaptive Model Predictive Control [56.705978425244496]
  We present STT-MPC (Self-Tuning Tube-based Model Predictive Control), an online oracle that combines the certainty-equivalence principle and polytopic tubes. We analyze the regret of the algorithm, when compared to an algorithm initially aware of the system dynamics.
  arXiv  Detail & Related papers  (2023-10-07T15:07:10Z)
• Probabilistic Reach-Avoid for Bayesian Neural Networks [71.67052234622781]
  We show that an optimal synthesis algorithm can provide more than a four-fold increase in the number of certifiable states. The algorithm is able to provide more than a three-fold increase in the average guaranteed reach-avoid probability.
  arXiv  Detail & Related papers  (2023-10-03T10:52:21Z)
• A Subgame Perfect Equilibrium Reinforcement Learning Approach to Time-inconsistent Problems [4.314956204483074]
  We establish a subgame perfect equilibrium reinforcement learning framework for time-inconsistent (TIC) problems. We propose a new class of algorithms, called backward policy iteration (BPI), that solves SPERL and addresses both challenges. To demonstrate the practical usage of BPI as a training framework, we adapt standard RL simulation methods and derive two BPI-based training algorithms.
  arXiv  Detail & Related papers  (2021-10-27T09:21:35Z)
• Zeroth and First Order Stochastic Frank-Wolfe Algorithms for Constrained Optimization [13.170519806372075]
  Problems of convex optimization with two sets of constraints arise frequently in the context of semidefinite programming. Since projection onto the first set of constraints is difficult, it becomes necessary to explore projection-free algorithms. The efficacy of the proposed algorithms is tested on relevant applications of sparse matrix estimation, clustering via semidefinite relaxation, and uniform sparsest cut problem.
  arXiv  Detail & Related papers  (2021-07-14T08:01:30Z)
• Gaussian Process-based Min-norm Stabilizing Controller for Control-Affine Systems with Uncertain Input Effects and Dynamics [90.81186513537777]
  We propose a novel compound kernel that captures the control-affine nature of the problem. We show that this resulting optimization problem is convex, and we call it Gaussian Process-based Control Lyapunov Function Second-Order Cone Program (GP-CLF-SOCP)
  arXiv  Detail & Related papers  (2020-11-14T01:27:32Z)
• Logistic Q-Learning [87.00813469969167]
  We propose a new reinforcement learning algorithm derived from a regularized linear-programming formulation of optimal control in MDPs. The main feature of our algorithm is a convex loss function for policy evaluation that serves as a theoretically sound alternative to the widely used squared Bellman error.
  arXiv  Detail & Related papers  (2020-10-21T17:14:31Z)
• Combining Deep Learning and Optimization for Security-Constrained Optimal Power Flow [94.24763814458686]
  Security-constrained optimal power flow (SCOPF) is fundamental in power systems. Modeling of APR within the SCOPF problem results in complex large-scale mixed-integer programs. This paper proposes a novel approach that combines deep learning and robust optimization techniques.
  arXiv  Detail & Related papers  (2020-07-14T12:38:21Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.