445.445. Inverse Reinforcement Learning

Implement inverse reinforcement learning, a type of reinforcement learning where an agent learns the reward function from expert demonstrations. **Example:** Consider a simple navigation task where an expert demonstrates how to navigate from a start state to a goal state. The goal is to learn the reward function that encourages the expert's behavior. **Constraints:** Use NumPy for numerical computations and ensure the learned reward function is close to the expert's reward function.