Create an intelligent agent in Python that can navigate a maze to find the exit. The maze will be represented as a 2D grid of characters, where: 'X' represents a wall '' represents an open space 'S' represents the starting position of the agent 'E' represents the exit of the maze The agent can move in four directions: up, down, left, and right. Challenge: Implement two approaches: 1. Depth-First Search (DFS): The agent explores the maze using a depth-first search algorithm, backtracking when it reaches a dead end. The goal is to find the exit as quickly as possible. 2. Q-Learning: 。 The agent learns through trial and error, receiving rewards for getting closer to the exit and penalties for hitting walls. 。 Implement a simple Q-learning algorithm where the agent updates its Q-values based on the rewards it receives. The Q-values represent the estimated future reward for taking a particular action from a specific state.

Create an intelligent agent in Python that can navigate a maze to find the exit. The maze will be represented as a 2D grid of characters, where: 'X' represents a wall '' represents an open space 'S' represents the starting position of the agent 'E' represents the exit of the maze The agent can move in four directions: up, down, left, and right. Challenge: Implement two approaches: 1. Depth-First Search (DFS): The agent explores the maze using a depth-first search algorithm, backtracking when it reaches a dead end. The goal is to find the exit as quickly as possible. 2. Q-Learning: 。 The agent learns through trial and error, receiving rewards for getting closer to the exit and penalties for hitting walls. 。 Implement a simple Q-learning algorithm where the agent updates its Q-values based on the rewards it receives. The Q-values represent the estimated future reward for taking a particular action from a specific state.