Skip to content

Releases: jimkon/Deep-Reinforcement-Learning-in-Large-Discrete-Action-Spaces

Wolpertinger (Continuous)

19 Jan 11:33
@jimkon jimkon
wolp-v3
02f8e5c

Choose a tag to compare

View all tags
Wolpertinger (Continuous) Latest
Latest

Fully functional agent for multi-dimensional continuous actions spaces ONLY.
New graphs.

Assets 2
Loading

Wolpertinger

27 Dec 14:50
@jimkon jimkon
wolp-v1
e951221

Choose a tag to compare

View all tags
Wolpertinger

Fully functional Wolpertinger algorithm

Loading