Skip to content

Latest commit

 

History

History
76 lines (48 loc) · 3.53 KB

README.md

File metadata and controls

76 lines (48 loc) · 3.53 KB

Navigation_RL_Agent

Training an RL agent to solve unity's Banana navigation environment.

Project Details:

Overview: Broad goal is to train an agent to successfully navigate Unity's large square world environment of yellow and blue bananas.

Goal & Rewards: 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.

State Space: The state space has 37 dimensions and contains the agent's velocity, along with ray-based perception of objects around the agent's forward direction.

Action Space: Four discrete actions are available, corresponding to:

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

Solving condition: The task is episodic, and in order to solve the environment, the agent must get an average score of +13 over 100 consecutive episodes.

Getting Started:

Setting up the python environment and installing dependencies

  1. Create (and activate) a new environment with Python 3.6.

  • Linux or Mac:

    conda create --name navigation python=3.6 source activate navigation

  • Windows:

    conda create --name navigation python=3.6

    activate navigation

  1. Clone the repository, Then, install several dependencies.

    git clone https://github.com/ramanshrivastava/navigantion_rl.git

    pip install torch

    pip install numpy

    pip install matplotlib

  2. Create an IPython kernel for the navigation environment.

    python -m ipykernel install --user --name navigation --display-name "navigation"

  3. Before running code in a notebook, change the kernel to match the navigation environment by using the drop-down Kernel menu.

Download the Unity Environment

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

(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.

  1. Place the file in the navigation_rl GitHub repository, in the root folder, and unzip (or decompress) the file.

Instructions:

  1. Open the Navigation.ipynb jupyter notebook and execute each code cell to train the agent.
  2. Once the necessary packages are imported as a next step provode the file_name for the UnityEnvironment
  3. Execute the rest of the cells as it is there after
  4. provide the PATH for .pt file in the code cell 7 and 8 to save and load model weights.