paper-with-me

Papers

Distributionally Robust Off-Dynamics Reinforcement Learning: Provable Efficiency with Linear Function Approximation

2024-02-23 · Zhishuai Liu, Pan Xu

We study off-dynamics Reinforcement Learning (RL), where the policy is trained on a source domain and deployed to a distinct target domain. We aim to solve this problem via online distributionally robust Markov decision processes (DRMDPs), where the learning algorithm actively interacts with the source domain while seeking the optimal performance under the worst possible dynamics that is within an uncertainty set of the source domain's transition kernel. We provide the first study on online DRMDPs with function approximation for off-dynamics RL. We find that DRMDPs' dual formulation can induce nonlinearity, even when the nominal transition kernel is linear, leading to error propagation. By designing a $d$-rectangular uncertainty set using the total variation distance, we remove this additional nonlinearity and bypass the error propagation. We then introduce DR-LSVI-UCB, the first provably efficient online DRMDP algorithm for off-dynamics RL with function approximation, and establish a polynomial suboptimality bound that is independent of the state and action space sizes. Our work makes the first step towards a deeper understanding of the provable efficiency of online DRMDPs with linear function approximation. Finally, we substantiate the performance and robustness of DR-LSVI-UCB through different numerical experiments.

📄 PDF Abstract BibTeX arXiv:2402.15399

Code (1)

panxulab/distributionally-robust-lsvi-ucb 공식 구현

Tasks

Reinforcement Learning (RL)

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically

Similar Papers 제목 키워드 기반

Distributionally Robust Model-based Reinforcement Learning with Large State Spaces

2023-09-05 · Shyam Sundhar Ramesh, Pier Giuseppe Sessa, Yifan Hu, Andreas Krause 외

Three major challenges in reinforcement learning are the complex dynamical systems with large state spaces, the costly data acquisition processes, and the deviation of real-world dynamics from the training environment de…

Gaussian ProcessesModel-based Reinforcement Learningreinforcement-learningReinforcement Learning

Upper and Lower Bounds for Distributionally Robust Off-Dynamics Reinforcement Learning

2024-09-30 · Zhishuai Liu, Weixin Wang, Pan Xu

We study off-dynamics Reinforcement Learning (RL), where the policy training and deployment environments are different. To deal with this environmental perturbation, we focus on learning policies robust to uncertainties …

2kComputational EfficiencyReinforcement Learning (RL)

Distributionally Robust Federated Averaging

2021-02-25 · NeurIPS 2020 12 · Yuyang Deng, Mohammad Mahdi Kamani, Mehrdad Mahdavi

In this paper, we study communication efficient distributed algorithms for distributionally robust federated learning via periodic averaging with adaptive sampling. In contrast to standard empirical risk minimization, du…

Federated Learning

DROMO: Distributionally Robust Offline Model-based Policy Optimization

2021-09-15 · Ruizhen Liu, Dazhi Zhong, Zhicong Chen

We consider the problem of offline reinforcement learning with model-based control, whose goal is to learn a dynamics model from the experience replay and obtain a pessimism-oriented agent under the learned model. Curren…

modelUncertainty Quantification

Extracting Latent State Representations with Linear Dynamics from Rich Observations

2020-06-29 · Abraham Frandsen, Rong Ge

Recently, many reinforcement learning techniques were shown to have provable guarantees in the simple case of linear dynamics, especially in problems like linear quadratic regulators. However, in practice, many reinforce…

Positionreinforcement-learningReinforcement LearningReinforcement Learning (RL)