Intro to Transition Probabilities and OpenAI Gym Library - Reinforcement Learning Tutorial

#machinelearning #reinforcementlearning #reinforcement #machinelearningtutorial #machinelearningengineer #datascience #datasciencecareer #datasciencetutorial #controlengineering #controltheory #controltheory #controlsystems #dynamicprogramming #dynamicalsystems
It takes a significant amount of time and energy to create these free video tutorials. You can support my efforts in this way:
- You Can also press the Thanks YouTube Dollar button

The post accompanying this video is given here:

In this video tutorial, we introduce important concepts for understanding reinforcement learning algorithms. These concepts are transition probabilities, transition states, terminal states, episodes, and rewards. We use the OpenAI Gym Python library to illustrate these concepts. More precisely, we use the Frozen Lake environment.

[aleksandarhaber]

It takes a significant amount of time and energy to create these free video tutorials. You can support my efforts in this way:
- You Can also press the Thanks YouTube Dollar button

[northstar]

Best RL lectures on YouTube, you explains everything very clear and understandable. Thank you so much.

[yoruichi]

Such a underrated teacher.
Thank you for these amazing videos.

[chieesntra]

in the defined mathematic probability equation (1), the A(t-1) should = a not = s (probably a typo) as you defined in the statement above

[rashidiqbal]

Thank you so much for your hard work in this series. I have a question at 17:25, why the probability is P1 + P2 + P3? Why not P1 + P2 + P3 + P4, is the current state having four actions for the next state, up, down, left, and right. Please let me know why you aren't taking the up Probability?
Thank you