mlsanityData to 7 Oct 2026

A priori Estimates for Deep Residual Network in Continuous-time Reinforcement Learning

arXiv 2402.16899 ↗First posted 24 Feb 2024cs.LG cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Deep reinforcement learning excels in numerous large-scale practical applications. However, existing performance analyses ignores the unique characteristics of continuous-time control problems, is unable to directly estimate the generalization error of the Bellman optimal loss and require a boundedness assumption. Our work focuses on continuous-time control problems and proposes a method that is applicable to all such problems where the transition function satisfies semi-group and Lipschitz properties. Under this method, we can directly analyze the a priori generalization error of the Bellman optimal loss. The core of this method lies in two transformations of the loss function. To complete the transformation, we propose a decomposition method for the maximum operator. Additionally, this analysis method does not require a boundedness assumption. Finally, we obtain an a priori generalization error without the curse of dimensionality.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 27 of its 50 references that are in the map. First posted on arXiv 24 Feb 2024.

Builds on

27 of 50 references.

References · 27

  1. 2017Proximal Policy Optimization Algorithmscited by 14,441
  2. 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,635
  3. 2015Trust Region Policy Optimizationcited by 2,503
  4. 2015Deep Reinforcement Learning with Double Q-learningcited by 1,704
  5. 2020Sharpness-Aware Minimization for Efficiently Improving Generalizationcited by 1,404
  6. 2017Rainbow: Combining Improvements in Deep Reinforcement Learningcited by 774
  7. 2017Spectrally-normalized margin bounds for neural networkscited by 681
  8. 2018Learning and Generalization in Overparameterized Neural Networks, Going Beyond Two Layerscited by 340
  9. 2018Stronger generalization bounds for deep nets via a compression approachcited by 306
  10. 2015Norm-Based Capacity Control in Neural Networkscited by 299
  11. 2020Reinforcement Learning for Combinatorial Optimization: A Surveycited by 235
  12. 2019A Theoretical Analysis of Deep Q-Learningcited by 212
15 more
  1. 2021Reinforcement learning based recommender systems: A surveycited by 187
  2. 2017Spectral Norm Regularization for Improving the Generalizability of Deep Learningcited by 178
  3. 2018Turning Big data into tiny data: Constant-size coresets for k-means, PCA and projective clusteringcited by 94
  4. 2018A Priori Estimates of the Population Risk for Two-layer Neural Networkscited by 76
  5. 2022Avoiding Overfitting: A Survey on Regularization Methods for Convolutional Neural Networkscited by 55
  6. 2021Risk Bounds and Rademacher Complexity in Batch Reinforcement Learningcited by 42
  7. 2018Reinforcement Learning for UAV Attitude Controlcited by 40
  8. 2020Reinforcement Learning with General Value Function Approximation: Provably Efficient Approach via Bounded Eluder Dimensioncited by 36
  9. 2021Reinforcement Learning for Quantitative Tradingcited by 24
  10. 2018Approximation and Estimation for High-Dimensional Deep Learning Networkscited by 22
  11. 2019A Priori Estimates of the Population Risk for Residual Networkscited by 14
  12. 2019Optimizing for Interpretability in Deep Neural Networks with Tree Regularizationcited by 13
  13. 2021An L2 Analysis of Reinforcement Learning in High Dimensions with Kernel and Neural Network Approximationcited by 13
  14. 2018Capacity Control of ReLU Neural Networks by Basis-path Normcited by 10
  15. 2014Rate of Convergence and Error Bounds for LSTD(λ)cited by 8

Built on by

Not cited yet.