Distributionally Robust Deep Q-Learning

• URL: http://arxiv.org/abs/2505.19058v1
• Date: Sun, 25 May 2025 09:22:06 GMT
• Title: Distributionally Robust Deep Q-Learning
• Authors: Chung I Lu, Julian Sester, Aijia Zhang,
• Abstract summary: We propose a novel distributionally robust $Q$-learning algorithm for continuous state spaces.<n>The uncertainty is taken into account by considering the worst-case transition from a ball around a reference probability measure.<n>This approach allows us to modify the Deep Q-Network algorithm to optimise for the worst case state transition.
• Score: 2.9767565026354186
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We propose a novel distributionally robust $Q$-learning algorithm for the non-tabular case accounting for continuous state spaces where the state transition of the underlying Markov decision process is subject to model uncertainty. The uncertainty is taken into account by considering the worst-case transition from a ball around a reference probability measure. To determine the optimal policy under the worst-case state transition, we solve the associated non-linear Bellman equation by dualising and regularising the Bellman operator with the Sinkhorn distance, which is then parameterized with deep neural networks. This approach allows us to modify the Deep Q-Network algorithm to optimise for the worst case state transition. We illustrate the tractability and effectiveness of our approach through several applications, including a portfolio optimisation task based on S\&{P}~500 data.

Related papers

• Reinforcement Learning in Switching Non-Stationary Markov Decision Processes: Algorithms and Convergence Analysis [6.399565088857091]
  We introduce Switching Non-Stationary Markov Decision Processes (SNS-MDP), where environments switch over time based on an underlying Markov chain.<n>Under a fixed policy, the value function of an SNS-MDP admits a closed-form solution determined by the Markov chain's statistical properties.<n>We show how this framework can effectively guide decision-making in complex, time-varying contexts.
  arXiv  Detail & Related papers  (2025-03-24T12:05:30Z)
• An Efficient On-Policy Deep Learning Framework for Stochastic Optimal Control [14.832859803172846]
  We present a novel on-policy algorithm for solving optimal control (SOC) problems.<n>By leveraging the Girsanov theorem, our method directly computes on-policy gradients of the SOC objective without expensive backpropagation through differential equations or adjoint problem solutions.<n> Experimental results demonstrate substantial improvements in both computational speed and memory efficiency compared to existing approaches.
  arXiv  Detail & Related papers  (2024-10-07T16:16:53Z)
• Optimization Proxies using Limited Labeled Data and Training Time -- A Semi-Supervised Bayesian Neural Network Approach [3.26805553822503]
  Constrained optimization problems arise in various engineering systems such as inventory and power grids.<n>Standard deep neural network (DNN) based machine learning proxies are ineffective in practical settings where labeled data is scarce and training times are limited.
  arXiv  Detail & Related papers  (2024-10-04T02:10:20Z)
• Regularized Q-Learning with Linear Function Approximation [2.765106384328772]
  We consider a bi-level optimization formulation of regularized Q-learning with linear functional approximation.<n>We show that, under certain assumptions, the proposed algorithm converges to a stationary point in the presence of Markovian noise.
  arXiv  Detail & Related papers  (2024-01-26T20:45:40Z)
• Model-Based Epistemic Variance of Values for Risk-Aware Policy Optimization [59.758009422067]
  We consider the problem of quantifying uncertainty over expected cumulative rewards in model-based reinforcement learning. We propose a new uncertainty Bellman equation (UBE) whose solution converges to the true posterior variance over values. We introduce a general-purpose policy optimization algorithm, Q-Uncertainty Soft Actor-Critic (QU-SAC) that can be applied for either risk-seeking or risk-averse policy optimization.
  arXiv  Detail & Related papers  (2023-12-07T15:55:58Z)
• Learning to Optimize with Stochastic Dominance Constraints [103.26714928625582]
  In this paper, we develop a simple yet efficient approach for the problem of comparing uncertain quantities. We recast inner optimization in the Lagrangian as a learning problem for surrogate approximation, which bypasses apparent intractability. The proposed light-SD demonstrates superior performance on several representative problems ranging from finance to supply chain management.
  arXiv  Detail & Related papers  (2022-11-14T21:54:31Z)
• Structural Estimation of Markov Decision Processes in High-Dimensional State Space with Finite-Time Guarantees [39.287388288477096]
  We consider the task of estimating a structural model of dynamic decisions by a human agent based upon the observable history of implemented actions and visited states. This problem has an inherent nested structure: in the inner problem, an optimal policy for a given reward function is identified while in the outer problem, a measure of fit is maximized. We propose a single-loop estimation algorithm with finite time guarantees that is equipped to deal with high-dimensional state spaces.
  arXiv  Detail & Related papers  (2022-10-04T00:11:38Z)
• Amortized Conditional Normalized Maximum Likelihood: Reliable Out of Distribution Uncertainty Estimation [99.92568326314667]
  We propose the amortized conditional normalized maximum likelihood (ACNML) method as a scalable general-purpose approach for uncertainty estimation. Our algorithm builds on the conditional normalized maximum likelihood (CNML) coding scheme, which has minimax optimal properties according to the minimum description length principle. We demonstrate that ACNML compares favorably to a number of prior techniques for uncertainty estimation in terms of calibration on out-of-distribution inputs.
  arXiv  Detail & Related papers  (2020-11-05T08:04:34Z)
• 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)
• Robust Reinforcement Learning with Wasserstein Constraint [49.86490922809473]
  We show the existence of optimal robust policies, provide a sensitivity analysis for the perturbations, and then design a novel robust learning algorithm. The effectiveness of the proposed algorithm is verified in the Cart-Pole environment.
  arXiv  Detail & Related papers  (2020-06-01T13:48:59Z)
• Upper Confidence Primal-Dual Reinforcement Learning for CMDP with Adversarial Loss [145.54544979467872]
  We consider online learning for episodically constrained Markov decision processes (CMDPs) We propose a new emphupper confidence primal-dual algorithm, which only requires the trajectories sampled from the transition model. Our analysis incorporates a new high-probability drift analysis of Lagrange multiplier processes into the celebrated regret analysis of upper confidence reinforcement learning.
  arXiv  Detail & Related papers  (2020-03-02T05:02:23Z)

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.