Marathon Environments: Multi-Agent Continuous Control Benchmarks in a Modern Video Game Engine

02/25/2019
by   Joe Booth, et al.
0

Recent advances in deep reinforcement learning in the paradigm of locomotion using continuous control have raised the interest of game makers for the potential of digital actors using active ragdoll. Currently, the available options to develop these ideas are either researchers' limited codebase or proprietary closed systems. We present Marathon Environments, a suite of open source, continuous control benchmarks implemented on the Unity game engine, using the Unity ML- Agents Toolkit. We demonstrate through these benchmarks that continuous control research is transferable to a commercial game engine. Furthermore, we exhibit the robustness of these environments by reproducing advanced continuous control research, such as learning to walk, run and backflip from motion capture data; learning to navigate complex terrains; and by implementing a video game input control system. We show further robustness by training with alternative algorithms found in OpenAI.Baselines. Finally, we share strategies for significantly reducing the training time.

READ FULL TEXT

page 3

page 4

12/07/2021

Godot Reinforcement Learning Agents

We present Godot Reinforcement Learning (RL) Agents, an open-source inte...
01/02/2018

DeepMind Control Suite

The DeepMind Control Suite is a set of continuous control tasks with a s...
09/07/2018

Unity: A General Platform for Intelligent Agents

Recent advances in Deep Reinforcement Learning and Robotics have been dr...
07/25/2019

Google Research Football: A Novel Reinforcement Learning Environment

Recent progress in the field of reinforcement learning has been accelera...
11/15/2020

Tonic: A Deep Reinforcement Learning Library for Fast Prototyping and Benchmarking

Deep reinforcement learning has been one of the fastest growing fields o...
04/20/2016

Procedural urban environments for FPS games

This paper presents a novel approach to procedural generation of urban m...
06/12/2020

Realistic Physics Based Character Controller

Over the course of the last several years there was a strong interest in...