In this project, I have used the provided banana collection environment and trained a DQN agent to lear to collect more and more bananas.

A reward of +1 is provided for collecting a yellow banana, and a reward of -1 is provided for collecting a blue banana. Thus, the goal of the agent is to collect as many yellow bananas as possible while avoiding blue bananas.

The state space has 37 dimensions and contains the agent's velocity, along with ray-based perception of objects around agent's forward direction. Given this information, the agent has to learn how to best select actions. Four discrete actions are available, corresponding to:

• 0 - move forward.
• 1 - move backward.
• 2 - turn left.
• 3 - turn right.

The task is episodic, and in order to solve the environment, the agent must get an average score of +13 over 100 consecutive episodes. The training of the model ends when average score in 13+ for two successive 100 episode interval

1. Download the environment from one of the links below. You need only select the environment that matches your operating system:

   • Linux: click here
   • Mac OSX: click here
   • Windows (32-bit): click here
   • Windows (64-bit): click here

   (For Windows users) Check out this link if you need help with determining if your computer is running a 32-bit version or 64-bit version of the Windows operating system.

   (For AWS) If you'd like to train the agent on AWS (and have not enabled a virtual screen), then please use this link to obtain the environment.

2. Place the file in the DRLND GitHub repository, in the p1_navigation/ folder, and unzip (or decompress) the file.

Before the installation, install Unity environment from UnityHub, 2018 version Follow the installation of the AI-RL repository here(https://github.com/udacity/deep-reinforcement-learning) with certain modifications to the requirements. In the root folder of the repo, find requirements.txt in the python folder, change the following

• tensorflow==1.7.1 to tensorflow==1.15
• torch==0.4.0 to torch

Follow the instructions in Navigation.ipynb to get started with training your own agent!

The model architecture is stored in [model] folder.

• model.py contains the neural network, Qnetwork, which acts as the brain of the agent. Its based on PyTorch
• dqn_agent.py contains Agent class, an instance of which is the agent that learns to navigate the banana field. For more understanding of how DQN works, follow the paper here