417.417. Softmax Exploration

In this problem, we will implement the Softmax exploration strategy for reinforcement learning. The Softmax algorithm chooses the action with the highest probability based on the estimated rewards.

**Example:** Consider a simple grid world where an agent can move up, down, left, or right. The agent receives a reward of 1 for reaching a goal state and -1 for hitting a wall.

**Constraints:** Implement the Softmax algorithm with a temperature parameter that controls the exploration-exploitation trade-off.

import numpy as np

def softmax_exploration(rewards, temperature):

# Your code here

pass