The course covers Q studying, SARSA, double Q studying, deep Q studying, and coverage gradient strategies. These algorithms are employed in a lot of environments from the open AI health club, together with area invaders, breakout, and others. The deep studying portion makes use of Tensorflow and PyTorch.

The course begins with extra trendy algorithms, akin to deep q studying and coverage gradient strategies, and demonstrates the ability of reinforcement studying.

Then the course teaches a number of the elementary ideas that energy all reinforcement studying algorithms. These are illustrated by coding up some algorithms that predate deep studying, however are nonetheless foundational to the innovative. These are studied in a number of the extra conventional environments from the OpenAI health club, just like the cart pole downside.

If the coupon just isn’t opening, disable Adblock, or strive one other browser.

Leave a comment

Your email address will not be published. Required fields are marked *