Skip to content

Releases: GPUOpen-LibrariesAndSDKs/ScholaExamples

ScholaExamples v1.1.0

01 Apr 15:43
Compare
Choose a tag to compare

What's New in ScholaExamples v1.1.0

This update features minor updates to the examples to make them compatible with Schola v1.1, a new example called RaceTrack, and updates to Pong so that it uses the new Camera Sensors.

New Example

  • RaceTrack: A new demo featuring a car that learns to follow a spline-based track.

Updated Example

  • Pong: The Pong example has been updated to utilize the new Camera Sensors introduced in Schola v1.1.

Documentation

Comprehensive interactive html documentation including guides, API Documentation, and installation instructions can be found at GPUOpen. For this release new Documentation has been added to Schola detailing how to build the Tag example, as well as an index of all the examples.

Prerequisites

ScholaExamples v1.0.0

03 Feb 12:37
Compare
Choose a tag to compare

Introducing ScholaExamples v1.0.0

Welcome to ScholaExamples. The initial release of ScholaExamples features 6 environments demonstrating the usage of Schola to train and utilize agents in Unreal Engine.

Included Examples

Basic

This environment features an agent that can move in the X-dimension and receives a small reward for going five steps in one direction and a bigger reward for going in the opposite direction.

MazeSolver: Using Raycasts

This environment features a static maze that the agent learns to solve as fast as possible. The agent observers the environment using raycasts, moves by teleporting in 2 dimensions and is given a reward for getting closer to the goal.

3DBall: Physics Based Environments

This environment features an agent that is trying to balance a ball on-top of itself. The agent can rotate itself and receives a reward every step until the ball falls.

BallShooter: Building Your Own Actuator

This environment features a rotating turret that learns to aim and shoot at randomly targets. The agent can rotate in either direction, and detects the targets by using a cone shaped ray-cast.

Pong: Collaborative Training

This environment features two agents playing a collaborative game of pong. The agents receive a reward every step as long as the ball has not hit the wall behind either agent. The game ends when the ball hits the wall behind either agent.

Tag: Competitive Multi-Agent Training

This environment features a 3v1 game of tag, where one agent(the runner) has to run away from the other agents which are trying to collide with it. The agents move using forward, left and right movement input, and observe the environment with a combination of ray-casts and global position data.

Documentation

Comprehensive interactive html documentation including guides, API Documentation, and installation instructions can be found at GPUOpen. Currently, BallShooter and MazeSolver have comprehensive documentation explaining all the various parts of the environment.

Prerequisites