OpenAI Gym

This is the foundational environment to how any Reinforcement Learning algorithm works.

Documentation: https://www.gymlibrary.dev/

Really simple baseline code

import gym
env = gym.make('MountainCar-v0')
while True:
   env.render()
   observation = env.reset()
   action = env.action_space.sample()
   observation, reward, done, info = env.step(action)
   if done:
	   print("Episode finished after {} timesteps".format(t+1))
	   break
env.close()

https://towardsdatascience.com/reinforcement-learning-with-openai-d445c2c687d2

https://towardsdatascience.com/getting-started-with-openai-gym-d2ac911f5cbc#:~:

Personal Learnings

Instead of env.step(), you can do env.vec_step() to step in parallel?