Matheus Portela

Results 7 comments of Matheus Portela

This problem is also happening with me. Has any progress been made?

I'm also having this issue with RVM v1.29.12. As suggested by @aurangzaib-danial, adding `rvm use default &> /dev/null` to the end of my `~/.zshrc` works for now.

Apparently, even in cart pole scenario, the results aren't being consistent, since testing games score much less than learning ones. Some possible causes: * Wrong implementation of Q-learning * State...

@Skalwalker yes, it could, although my guess is that the state space is too large for the scenario where the Pac-Man is alone in the field (which I used to...

Small update on this task: Q-learning is working quite well with the cart-pole experiment. After about 500 simulations, the agent learn to control the inverted pendulum for ~10 seconds and,...

One more thing to test: simply selecting behaviors instead of actions.