search

dfridovi / rl

A homebrewed C++ library for reinforcement learning.
https://dfridovi.github.io/rl
Other
0 stars 0 forks source link

Try a deep net for the inverted pendulum Q function #3

Closed dfridovi closed 7 years ago

dfridovi commented 7 years ago

If this doesn't work well immediately, try out fixed Q targets.

dfridovi commented 7 years ago

Tried it out. Fixed Q targets still an option, but some other stuff to try first.