We will first understand the cartpole environment of OpenAI gym.
We will then proceed to make a simple hard-coded policy, make the agent with that policy, and examine the performance.
Then we train a neural network and observe the performance.
Later, we learn a concept named credit assignment problem, understand the policy gradients algorithm, and implement it to observe its effect in the improvement of the game.
Taking you to the next exercise in seconds...
Want to create exercises like this yourself? Click here.
No hints are availble for this assesment
Answer is not availble for this assesment
Loading comments...