paper-with-me

Papers

Distributionally Robust Reinforcement Learning with Interactive Data Collection: Fundamental Hardness and Near-Optimal Algorithm

2024-04-04 · Miao Lu, Han Zhong, Tong Zhang, Jose Blanchet

The sim-to-real gap, which represents the disparity between training and testing environments, poses a significant challenge in reinforcement learning (RL). A promising approach to addressing this challenge is distributionally robust RL, often framed as a robust Markov decision process (RMDP). In this framework, the objective is to find a robust policy that achieves good performance under the worst-case scenario among all environments within a pre-specified uncertainty set centered around the training environment. Unlike previous work, which relies on a generative model or a pre-collected offline dataset enjoying good coverage of the deployment environment, we tackle robust RL via interactive data collection, where the learner interacts with the training environment only and refines the policy through trial and error. In this robust RL paradigm, two main challenges emerge: managing distributional robustness while striking a balance between exploration and exploitation during data collection. Initially, we establish that sample-efficient learning without additional assumptions is unattainable owing to the curse of support shift; i.e., the potential disjointedness of the distributional supports between the training and testing environments. To circumvent such a hardness result, we introduce the vanishing minimal value assumption to RMDPs with a total-variation (TV) distance robust set, postulating that the minimal value of the optimal robust value function is zero. We prove that such an assumption effectively eliminates the support shift issue for RMDPs with a TV distance robust set, and present an algorithm with a provable sample complexity guarantee. Our work makes the initial step to uncovering the inherent difficulty of robust RL via interactive data collection and sufficient conditions for designing a sample-efficient algorithm accompanied by sharp sample complexity analysis.

📄 PDF Abstract BibTeX arXiv:2404.03578

Code (0)

등록된 구현이 없습니다.

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 Online Markov Game with Linear Function Approximation

2025-11-11 · Zewu Zheng, Yuanyuan Lin arxiv

The sim-to-real gap, where agents trained in a simulator face significant performance degradation during testing, is a fundamental challenge in reinforcement learning. Extansive works adopt the framework of distributiona…

Reinforcement Learning

Risk-Averse Model Uncertainty for Distributionally Robust Safe Reinforcement Learning

2023-09-21 · NeurIPS 2023 11

Many real-world domains require safe decision making in uncertain environments. In this work, we introduce a deep reinforcement learning framework for approaching this important problem. We consider a distribution over t…

Distributionally Robust Learning

2021-08-20 · Ruidi Chen, Ioannis Ch. Paschalidis

This monograph develops a comprehensive statistical learning framework that is robust to (distributional) perturbations in the data using Distributionally Robust Optimization (DRO) under the Wasserstein metric. Beginning…

Decision Makingregression

Quantile Geometry Regularization for Distributional Reinforcement Learning

2026-05-05 · Zhaofan Zhang, Minghao Yang, Rufeng Chen, Sihong Xie 외 arxiv

Quantile-based distributional reinforcement learning methods learn return distributions through sampled quantile regression, but their bootstrapped target quantiles may induce distorted or degenerate distribution estimat…

Reinforcement LearningAtari Games

Interactive Trajectory Planning with Learning-based Distributionally Robust Model Predictive Control and Markov Systems

2026-05-08 · Erik Börve, Nikolce Murgovski, Morteza Haghir Chehreghani, Leo Laine arxiv

We investigate interactive trajectory planning subject to uncertainty in the decisions of surrounding agents. To control the ego-agent, we aim to first learn the decision distribution and solve a Stochastic Model Predict…

Trajectory Planning