You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
A text-based grid world framework for reinforcement learning agents to play around in. In general, the goal for the agent is to solve the maze in as few steps as possible. This is done using plenty of reinforcement learning algorithms including policy iteration, value iteration, sarsa, monte carlo methods, and iterative policy evaluation.