TY - UNPB
T1 - skrl: Modular and Flexible Library for Reinforcement Learning
AU - Serrano-Muñoz, Antonio
AU - Chrysostomou, Dimitrios
AU - Bøgh, Simon
AU - Arana-Arexolaleiba, Nestor
PY - 2022/2/8
Y1 - 2022/2/8
N2 - skrl is an open-source modular library for reinforcement learning written in Python and designed with a focus on readability, simplicity, and transparency of algorithm implementations. Apart from supporting environments that use the traditional OpenAI Gym interface, it allows loading, configuring, and operating NVIDIA Isaac Gym environments, enabling the parallel training of several agents with adjustable scopes, which may or may not share resources, in the same execution. The library's documentation can be found at this https URL and its source code is available on GitHub at url{this https URL.
AB - skrl is an open-source modular library for reinforcement learning written in Python and designed with a focus on readability, simplicity, and transparency of algorithm implementations. Apart from supporting environments that use the traditional OpenAI Gym interface, it allows loading, configuring, and operating NVIDIA Isaac Gym environments, enabling the parallel training of several agents with adjustable scopes, which may or may not share resources, in the same execution. The library's documentation can be found at this https URL and its source code is available on GitHub at url{this https URL.
KW - Reinforcement Learning
KW - Artificial Intelligence (AI)
KW - Machine Learning
KW - Robotics
KW - Software
KW - Reinforcement Learning
KW - Kunstig Intelligens
KW - Maskinlæring
KW - Robotics
KW - Software
UR - https://skrl.readthedocs.io/en/latest/
UR - https://github.com/Toni-SM/skrl
U2 - 10.48550/arXiv.2202.03825
DO - 10.48550/arXiv.2202.03825
M3 - Preprint
VL - abs/2202.03825
T3 - CoRR
SP - 1
EP - 6
BT - skrl: Modular and Flexible Library for Reinforcement Learning
ER -