Become a member
Sign in
Diving deeper into Reinforcement Learning with Q-Learning
13.4K
43
Thomas Simonini
Tript Sharma
Tript Sharma
Sep 2, 2018 · 1 min read

Hi Thomas,

I ran the code for FrozenLake and it gave a score of 0.0622. Why is the score so low? How can it be increased, I have tried tweaking LR, Total no. of episodes etc.

P.S: Thank you for the tutorial. It cleared my concepts.

    Tript Sharma

    Written by

    Tript Sharma

    Write the first response

    Discover Medium

    Welcome to a place where words matter. On Medium, smart voices and original ideas take center stage - with no ads in sight. Watch

    Make Medium yours

    Follow all the topics you care about, and we’ll deliver the best stories for you to your homepage and inbox. Explore

    Become a member

    Get unlimited access to the best stories on Medium — and support writers while you’re at it. Just $5/month. Upgrade
    AboutHelpLegal