AI Agent optimized by Artificial Bee Colony(ABC) Algorithm to play Cartpole Game

The traditional Artificial Bee Colony Algorithm is used to train the neural network. The training of neural network involves a task of finding optimal weights and bias values. The Artificial Bee Colony (ABC) Algorithm increases the rewards gained over different evolution of the network policy parameters. The ABC algorithm-based policy network is then compared with Deep Q-Network (DQN) based agent to see the performance comparison of both the optimization methods. The DQN uses policy gradient approach to find the optimal policy network parameters while Evolutionary strategy approach uses the Artificial Bee Colony (ABC) algorithm.