BRIDGE dataset

The BRIDGE dataset is a collection of 155 deterministic MDPs, each with a horizon of 100 time steps. The dataset is used to evaluate the performance of reinforcement learning algorithms.

Data and Resources

Cite this as

Cassidy Laidlaw, Stuart Russell, Banghua Zhu, Anca Dragan (2024). Dataset: BRIDGE dataset. https://doi.org/10.57702/8iubmtjz

DOI retrieved: December 16, 2024

Additional Info

Field Value
Created December 16, 2024
Last update December 16, 2024
Author Cassidy Laidlaw
More Authors
Stuart Russell
Banghua Zhu
Anca Dragan