/PPO_Reacher

Robotics Arm Control in Unity ML with Proximal Policy Optimization (PPO)

Primary LanguageASP

PPO for Reacher UnityML

This is an implementation of the Proximal Policy Optimization (Schulmann et al, 2017) for the Reacher environment in Unity ML Trained Agent

Project Details

Environment

In the Reacher environment, where a double-jointed arm can move to target locations. A reward of +0.1 is provided for each step that the agent's hand is in the goal location. Thus, the goal of the agent is to maintain its position at the target location for as many time steps as possible.

The observation space consists of 33 variables corresponding to position, rotation, velocity, and angular velocities of the arm. Each action is a vector with four numbers, corresponding to torque applicable to two joints. Every entry in the action vector should be a number between -1 and 1.

Distributed Training

This project uses the parallel version of the Reacher environment. The version contains 20 identical agents, each with its own copy of the environment. The learning algorithm PPO used here uses multiple (non-interacting, parallel) copies of the same agent to distribute the task of gathering experience.

Solving the environment

The environment is considered solved, when the average (over 100 episodes) of those average scores is at least +30.

Getting Started

  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 (version 1) or this link (version 2) to obtain the "headless" version of the environment. You will not be able to watch the agent without enabling a virtual screen, but you will be able to train the agent. (To watch the agent, you should follow the instructions to enable a virtual screen, and then download the environment for the Linux operating system above.)

  2. See file requirements.txt for python dependencies.

Instructions

Run PPO.ipynb to run the agent.

Files

  • PPO.ipynb - load the environment explore the environment, train the agent or run the trained agent
  • agent.py contains the agent class
  • model.py contains the neural network models the agents employ.
  • ppo_checkpoint.pth contains trained model weights
  • REPORT.md contains description of implementation, results, and ideas for future work.

Reference