You're currently viewing an old version of this dataset. To see the current version, click here.

Multitask Representation Learning in Linear MDPs

The dataset is used for multitask representation learning in linear MDPs. It contains 80 different tasks, each with a different destination position, fire configuration, and action deviation probability p.

Data and Resources

Cite this as

Rui Lu, Gao Huang, Simon S. Du (2024). Dataset: Multitask Representation Learning in Linear MDPs. https://doi.org/10.57702/vexzjqzd

DOI retrieved: December 16, 2024

Additional Info

Field Value
Created December 16, 2024
Last update December 16, 2024
Defined In https://doi.org/10.48550/arXiv.2106.08053
Author Rui Lu
More Authors
Gao Huang
Simon S. Du
Homepage https://arxiv.org/abs/2002.09434