DEEP REINFORCEMENT LEARNING MODEL FOR PLAYING FLAPPY BIRD

WHAT IS IT?

Its a deep learning model for Playing Flappy bird. Here the states of agent is decided by the neural net then by using dynamic programming and reinforcement learning agent is trained. Pipeline is a convolution neural network followed by a agent trained with a variant of Q-learning, whose input is raw pixels and whose output is a value function estimating future rewards.

HOW TO USE?

To run The Inference Script run this command python run.py

WHAT ARE THE REQUIREMENTS?

To get all the requirements and dependencies installed run the command For GPU - pip install -r gpu_requirements.txt For CPU - pip install -r cpu_requirements.txt