AI-Project-3-Reinforcement-Learning-LSTM-Search
PublicDeveloped Deep Q Learning for Cartpole and FrozenLake, explored LSTM networks for temporal modeling, and implemented search algorithms, including A*, Min-Max, and CSP solutions.
Developed Deep Q Learning for Cartpole and FrozenLake, explored LSTM networks for temporal modeling, and implemented search algorithms, including A*, Min-Max, and CSP solutions.