PyBulletGym tasks

The dataset used in the paper is a collection of experiences sampled from a replay buffer, used to train and evaluate the proposed Multi-step DDPG (MDDPG) and Mixed Multi-step DDPG (MMDDPG) algorithms.

Data and Resources

Cite this as

Lingheng Meng, Rob Gorbet, Dana Kuli´c (2024). Dataset: PyBulletGym tasks. https://doi.org/10.57702/rx0zo9rw

DOI retrieved: December 3, 2024

Additional Info

Field Value
Created December 3, 2024
Last update December 3, 2024
Author Lingheng Meng
More Authors
Rob Gorbet
Dana Kuli´c
Homepage https://github.com/openai/spinningup