Exploring the envirements in http://gym.openai.com/ and training AI agents to play them
note: Each done notebook starts with a desciption of the aproach used
Environments Learnt:
- CartPole-v0 using KMeans and TD learning with full backup the agent managed to achieve the max score and stabilize in less than 100 episodes
Environments in progress
- AirRaid-ram-v0