The python script shown is my implementation of OpenAI's 8x8 frozen lake enviornment. I watched Stanford's CS234 course in reinforcemnt learning, and implemented (from scratch) a model free, finite state system which uses Q learning to get the agent to make optimal decisions. In the end the agent was able to solve the puzzle 60% of the time in under 100 steps.
adianliusie / gym-frozen-lake Goto Github PK
View Code? Open in Web Editor NEWreinforcement learning done on an open AI gym enviornment