Empirical Policy Evaluation with Supergraphs

2020-02-18 · Daniel Vial, Vijay Subramanian

We devise and analyze algorithms for the empirical policy evaluation problem in reinforcement learning. Our algorithms explore backward from high-cost states to find high-value ones, in contrast to forward approaches that work forward from all states. While several papers have demonstrated the utility of backward exploration empirically, we conduct rigorous analyses which show that our algorithms can reduce average-case sample complexity from $O(S \log S)$ to as low as $O(\log S)$.

📄 PDF Abstract BibTeX arXiv:2002.07905

Code (0)

등록된 구현이 없습니다.

Tasks

reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

GFlowNet Foundations

2021-11-17 · Yoshua Bengio, Salem Lahlou, Tristan Deleu, Edward J. Hu 외

Generative Flow Networks (GFlowNets) have been introduced as a method to sample a diverse set of candidates in an active learning context, with a training objective that makes them approximately sample in proportion to a…

Active Learning

A Parallel Framework for Parametric Maximum Flow Problems in Image Segmentation

2015-09-20 · Vlad Olaru, Mihai Florea, Cristian Sminchisescu

This paper presents a framework that supports the implementation of parallel solutions for the widespread parametric maximum flow computational routines used in image segmentation algorithms. The framework is based on su…

GPU Image Segmentation Segmentation Semantic Segmentation

Doubly Optimal Policy Evaluation for Reinforcement Learning

2024-10-03 · Shuze Liu, Claire Chen, Shangtong Zhang

Policy evaluation estimates the performance of a policy by (1) collecting data from the environment and (2) processing raw data into a meaningful estimate. Due to the sequential nature of reinforcement learning, any impr…

reinforcement-learning Reinforcement Learning

Robust On-Policy Sampling for Data-Efficient Policy Evaluation in Reinforcement Learning

2021-11-29 · Rujie Zhong, Duohan Zhang, Lukas Schäfer, Stefano V. Albrecht 외

Reinforcement learning (RL) algorithms are often categorized as either on-policy or off-policy depending on whether they use data from a target policy of interest or from a different behavior policy. In this paper, we st…

Offline RL reinforcement-learning Reinforcement Learning (RL)

Cross-Validated Off-Policy Evaluation

2024-05-24 · Matej Cief, Branislav Kveton, Michal Kompan

We study estimator selection and hyper-parameter tuning in off-policy evaluation. Although cross-validation is the most popular method for model selection in supervised learning, off-policy evaluation relies mostly on th…

Model Selection Off-policy evaluation