Solve LunarLander-v2 with Deep Q-learning
the LL environ- ment is a simulated environment where the agent needs to successfully and safely land the aircraft in the designated area. The lunar lander has 4 discrete actions, do nothing, fire the left orientation engine, fire the main engine, and fire the right orientation engine. The states of the lander are represented as 8-dimensional vectors: (x, y, vx, vy, θ, vθ, lef tleg, rightleg), x and y are the x and y-coordinates of the lunar lander’s position on the screen.