418.418. Experience Replay

In this problem, we will implement an Experience Replay buffer for reinforcement learning. The Experience Replay buffer stores a sequence of experiences and allows the agent to sample from the buffer to train the model.

**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 Experience Replay buffer with a capacity of 1000 experiences and a sampling method that returns a random experience from the buffer.

import numpy as np

class ExperienceReplay:

def __init__(self, capacity):

# Your code here

pass

def add_experience(self, experience):

# Your code here

pass

def sample_experience(self):

# Your code here

pass