Reinforcement-Learning-Maze
Reinforcement-Learning-Maze copied to clipboard
Various ways to learn a computer to escape from a maze. From random walk to a simple neural network.
Results
1
Reinforcement-Learning-Maze issues
Sort by
recently updated
recently updated
newest added
Hello, how do you set the reward value for each action in the environment, and what is the basis for judging?Thank you for your answer.