Approximate dynamic programming algorithms, such as approximate value iteration, have been successfully applied to many complex reinforcement learning tasks, and a better approximate dynamic programming algorithm is expected to further extend the applicability of reinforcement learning to various tasks. In this paper w…
On-device research index
arXiv research
A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
168,657 papers · 148 categories
Trend · papers per month
48 results for “approximate dynamic programming”
Approximate dynamic programming is a popular method for solving large Markov decision processes. This paper describes a new class of approximate dynamic programming (ADP) methods- distributionally robust ADP-that address the curse of dimensionality by minimizing a pessimistic bound on the policy loss. This approach tur…
Framework optimizes battery storage for markets by separating long-term degradation from short-term market dynamics.
problem Intractable computation due to timescale mismatch between battery degradation and market dynamics.
method Approximate dynamic programming with value function approximation and pseudo-time encoding.
result Policy outperforms benchmarks in real-time market scenarios.
Paper approximates solutions for complex decision processes with limited precision.
problem Approximating the set of all solutions for Multi-objective Markov Decision Processes.
method Limited precision approach based on White's multi-objective value-iteration dynamic programming algorithm.
result The number of calculated solutions is tractable and approximates the true Pareto front.
New method for optimistic planning in MDPs using regularization.
problem Optimistic planning in infinite-horizon discounted MDPs.
method Regularized dynamic programming for approximate value iteration.
result Achieves near-optimal statistical guarantees in learning policies.
Scalable Autonomous Vehicle Safety Validation through Dynamic Programming and Scene Decompositioncs.RO
New approach uses dynamic programming to efficiently discover failures in autonomous vehicle simulations.
problem Efficiently discovering rare failure events in autonomous vehicle simulations.
method Approximate dynamic programming and scene decomposition to estimate failure distribution.
result Increased number of failures discovered compared to baseline approaches.
Real-world problems of operations research are typically high-dimensional and combinatorial. Linear programs are generally used to formulate and efficiently solve these large decision problems. However, in multi-period decision problems, we must often compute expected downstream values corresponding to current decision…
We introduce a novel numerical approach for a class of stochastic dynamic programs which arise as discretizations of backward stochastic differential equations or semi-linear partial differential equations. Solving such dynamic programs numerically requires the approximation of nested conditional expectations, i.e., it…
We describe an approximate dynamic programming (ADP) approach to compute approximations of the optimal strategies and of the minimal losses that can be guaranteed in discounted repeated games with vector-valued losses. Such games prominently arise in the analysis of regret in repeated decision-making in adversarial env…
Reinforcement learning has gained wide popularity as a technique for simulation-driven approximate dynamic programming. A less known aspect is that the very reasons that make it effective in dynamic programming can also be leveraged for using it for distributed schemes for certain matrix computations involving non-nega…
This paper develops algorithms for high-dimensional stochastic control problems based on deep learning and dynamic programming. Unlike classical approximate dynamic programming approaches, we first approximate the optimal policy by means of neural networks in the spirit of deep reinforcement learning, and then the valu…
Deep learning solves dynamic programming with recursive utility.
problem Challenges in solving high-dimensional discrete-time dynamic programming problems with recursive utility.
method Certainty Equivalent Learning (CEL) algorithm that learns certainty-equivalent value directly with neural networks.
result Accurate value and policy approximations in high-dimensional problems, comparable to VFI in some cases.
The design of multiple experiments is commonly undertaken via suboptimal strategies, such as batch (open-loop) design that omits feedback or greedy (myopic) design that does not account for future effects. This paper introduces new strategies for the optimal design of sequential experiments. First, we rigorously formul…
Algorithm selects best model based on state, reducing costs.
problem Choosing the best model among many in different states of the world.
method Reinforcement learning algorithm to estimate optimal policy.
result Algorithm consistently selects optimal model based on covariates.
Approximate dynamic programming (ADP) has proven itself in a wide range of applications spanning large-scale transportation problems, health care, revenue management, and energy systems. The design of effective ADP algorithms has many dimensions, but one crucial factor is the stepsize rule used to update a value functi…
Study optimal liquidation strategies on Uniswap v2/v3 considering price impact.
problem Optimal liquidation of large positions on Uniswap v2/v3 under transient price impact.
method Dynamic programming and numerical approximation for Uniswap v3, closed-form solutions for v2.
result Obtained optimal strategies for both Uniswap v2 and v3, showing how liquidity profile influences them.
DPDP combines neural heuristics with DP for vehicle routing problems.
problem Vehicle routing problems with large scale.
method Deep Policy Dynamic Programming (DPDP) that uses a neural network policy to prioritize and restrict the DP state space.
result DPDP improves upon classical DP algorithms and outperforms neural approaches for TSP, VRP, and TSPTW.
New algorithm tackles dynamic assortment optimization with knapsack constraints.
problem Optimizing retailer's assortment decisions under resource constraints with multi-nomial choice modeling.
method Epoch-based re-solving algorithm that transforms MNL's fractional structure into a linear program with slack variables.
result Regret scales logarithmically with time horizon and resource capacities.
Optimal Control Theory optimizes neural networks, improving robustness and efficiency.
problem Optimizing deep neural networks (DNNs) for better performance and efficiency.
method Integrating Optimal Control Theory with Backpropagation to develop a new optimizer.
result Optimal Control Theoretic Neural Optimizer (OCNOpt) improves upon existing methods in robustness and efficiency.
The paper analyzes error propagation in dynamic programming for stochastic control and option pricing.
problem Error propagation in dynamic programming for stochastic control and option pricing.
method Formulated a general dynamic programming framework, used RKHSs for nonparametric regression, and Monte Carlo subsampling for estimating continuation value.
result Proposed a rigorous error decomposition and control mechanism for error propagation in dynamic programming.
In this paper, we propose a novel policy iteration method, called dynamic policy programming (DPP), to estimate the optimal policy in the infinite-horizon Markov decision processes. We prove the finite-iteration and asymptotic l\infty-norm performance-loss bounds for DPP in the presence of approximation/estimation erro…
Unified framework for model- and value-optimistic reinforcement learning.
problem Designing and analyzing algorithms for episodic reinforcement learning.
method Lagrangian duality for a unified view of optimism.
result Unified algorithms with both efficient implementation and probabilistic analysis.
Deep learning solves complex stochastic control with jumps.
problem Solving high-dimensional stochastic control tasks with jumps.
method Model-based approach using two neural networks, iteratively trained with objectives derived from the Hamilton-Jacobi-Bellman equation.
result Demonstrates effectiveness in solving complex high-dimensional stochastic control tasks.
We generalize the primal-dual methodology, which is popular in the pricing of early-exercise options, to a backward dynamic programming equation associated with time discretization schemes of (reflected) backward stochastic differential equations (BSDEs). Taking as an input some approximate solution of the backward dyn…
Combines dynamic programming and neural networks for optimal portfolio execution in regime-switching markets.
problem Optimal execution in a market with multiple regimes and non-linear impact costs.
method Four-step numerical framework: approximated orthogonal portfolios, dynamic program for schedule, neural network optimization.
result Neural network optimized strategy outperforms traditional methods in both CRRA and mean-variance objectives.
The paper proposes a mixture model with segmentation for heterogeneous functional data.
problem Heterogeneity in time and population for functional data.
method Mixture model with segmentation of time, maximum likelihood estimator, EM algorithm with dynamic programming.
result The method is consistent and identifiable, and illustrated on simulated and real datasets.
Theoretical and Numerical Analysis of Approximate Dynamic Programming with Approximation Errorseess.SY
This study is aimed at answering the famous question of how the approximation errors at each iteration of Approximate Dynamic Programming (ADP) affect the quality of the final results considering the fact that errors at each iteration affect the next iteration. To this goal, convergence of Value Iteration scheme of ADP…
Real Time Dynamic Programming (RTDP) is an online algorithm based on Dynamic Programming (DP) that acts by 1-step greedy planning. Unlike DP, RTDP does not require access to the entire state space, i.e., it explicitly handles the exploration. This fact makes RTDP particularly appealing when the state space is large and…
We consider large-scale Markov decision processes (MDPs) with parameter uncertainty, under the robust MDP paradigm. Previous studies showed that robust MDPs, based on a minimax approach to handle uncertainty, can be solved using dynamic programming for small to medium sized problems. However, due to the "curse of dimen…
Develops a dynamic mean field theory for reinforcement learning.
problem Finite state and action Bayesian reinforcement learning in large state spaces.
method Analogies with statistical physics, interpreting probabilities as couplings and values as spins, solving mean field equations.
result State-action values are statistically independent in the asymptotic state space limit, with exact or approximate equations for computation.
Optimizes trading in CFMMs and exchanges using deep learning.
problem Optimizing trading strategies in CFMMs and exchanges.
method Develops a model accounting for interaction between CFMMs and exchanges, employs deep Galerkin method to solve dynamic programming equation.
result Optimal strategy outperforms naïve strategies and is not prone to price slippage.
Reinforced optimal controlmath.OC
Improved reinforcement method for optimal control problems.
problem Optimal control problems with limited computational cost.
method Reinforced least squares Monte Carlo method for stochastic control problems.
result Significant improvement in method's efficiency and accuracy.
BNN-DP improves robustness analysis of Bayesian Neural Networks.
problem Ensuring robustness of Bayesian Neural Networks against adversarial attacks.
method Dynamic Programming applied to Bayesian Neural Networks as stochastic dynamical systems.
result BNN-DP provides tighter and more efficient bounds on prediction ranges compared to existing methods.
Optimal transport is #P-hard when components are independent, even with approximate solutions.
problem Computational complexity of optimal transport with independent marginals.
method Proved #P-hardness and developed a pseudo-polynomial time approximation algorithm.
result Optimal transport is #P-hard even with independent components and approximate solutions.
Paper addresses underestimation bias in double Q-learning, proposing a method to improve learning performance.
problem Underestimation bias in double Q-learning leading to non-optimal fixed points.
method Proposes a simple approach using approximate dynamic programming to bound the target value.
result Significant improvement in learning performance over baseline algorithms in Atari benchmark tasks.
Under a Bayesian framework, we formulate the fully sequential sampling and selection decision in statistical ranking and selection as a stochastic control problem, and derive the associated Bellman equation. Using value function approximation, we derive an approximately optimal allocation policy. We show that this poli…
High-frequency trading strategy boosts battery storage profits.
problem Maximizing revenue for battery energy storage systems in intraday markets.
method Adapted dynamic programming for continuous intraday markets, considering limit order book dynamics.
result Dynamic programming strategy outperforms standard re-optimization methods, increasing profits by 58% and 14% respectively.
In this paper, we analyze dynamic programming as a novel approach to solve the problem of maximizing the profits of a bank. The mathematical model of the problem and the description of a bank's work is described in this paper. The problem is then approached using the method of dynamic programming. Dynamic programming m…
In this paper we consider regularized convex cone programming problems. In particular, we first propose an iterative hard thresholding (IHT) method and its variant for solving regularized box constrained convex programming. We show that the sequence generated by these methods converges to a local minimizer.…
New methods improve global optimisation for expensive functions using lookahead strategies.
problem Optimising expensive functions without gradient info in high dimensions.
method Nonmyopic acquisition strategies based on approximate dynamic programming.
result Nonmyopic methods outperform myopic approaches in various applications.
New algorithms for efficient return distribution approximation in reinforcement learning.
problem Efficiently approximating unknown return distributions in reinforcement learning.
method Introduced novel distributional dynamic programming algorithms for arbitrary probabilistic reward mechanisms.
result Proved error bounds for the algorithms in Wasserstein and Kolmogorov--Smirnov distances.
FVI method calculates bicausal OT with neural networks, outperforming other methods.
problem Computing bicausal optimal transport with adapted coupling structures.
method FVI method using multilayer neural networks to approximate value functions.
result FVI method outperforms linear programming and Sinkhorn methods in scalability.
Probabilistic programming languages can simplify the development of machine learning techniques, but only if inference is sufficiently scalable. Unfortunately, Bayesian parameter estimation for highly coupled models such as regressions and state-space models still scales poorly; each MCMC transition takes linear time i…
This paper improves dynamic hedging accuracy using genetic programming to forecast implied volatilities.
problem Improving the accuracy of dynamic hedging using implied volatilities.
method The paper uses genetic programming to forecast implied volatilities and tests the performance of these forecasts in dynamic hedging strategies.
result Genetic programming-generated implied volatilities improve hedging accuracy compared to static training methods.
dynestyx: A library for probabilistic programming of dynamical systems
problem integrating state-space models into probabilistic programming languages
method a unified interface for specifying priors and performing inference
result principled uncertainty quantification for state and parameters
Paper tackles non-Markovian control problems with new learning methods.
problem Non-Markovian stochastic control problems with unknown parameters.
method Off-model training and importance sampling for deep neural network approximation.
result Quantitative error bounds for adaptive learning under model uncertainty.
New method uses dynamic programming for meta continual learning.
problem Challenges of generalization and catastrophic forgetting in sequential learning.
method Developed a theoretical framework using dynamic programming for meta continual learning.
result Theoretical and practical method achieves better accuracy than existing methods.
Study optimal investment strategies for an insurer in two currency markets.
problem Maximizing expected exponential utility of terminal wealth for an insurer in two currency markets.
method Dynamic programming method applied to solve Hamilton-Jacobi-Bellman equations.
result Optimal investment strategies and value functions are derived.