Deep Reinforcement Learning on a Budget: 3D Control and Reasoning Without a Supercomputer

04/03/2019
by   Edward Beeching, et al.
22

An important goal of research in Deep Reinforcement Learning in mobile robotics is to train agents capable of solving complex tasks, which require a high level of scene understanding and reasoning from an egocentric perspective. When trained from simulations, optimal environments should satisfy a currently unobtainable combination of high-fidelity photographic observations, massive amounts of different environment configurations and fast simulation speeds. In this paper we argue that research on training agents capable of complex reasoning can be simplified by decoupling from the requirement of high fidelity photographic observations. We present a suite of tasks requiring complex reasoning and exploration in continuous, partially observable 3D environments. The objective is to provide challenging scenarios and a robust baseline agent architecture that can be trained on mid-range consumer hardware in under 24h. Our scenarios combine two key advantages: (i) they are based on a simple but highly efficient 3D environment (ViZDoom) which allows high speed simulation (12000fps); (ii) the scenarios provide the user with a range of difficulty settings, in order to identify the limitations of current state of the art algorithms and network architectures. We aim to increase accessibility to the field of Deep-RL by providing baselines for challenging scenarios where new ideas can be iterated on quickly. We argue that the community should be able to address challenging problems in reasoning of mobile agents without the need for a large compute infrastructure.

READ FULL TEXT
research
10/13/2022

Harfang3D Dog-Fight Sandbox: A Reinforcement Learning Research Platform for the Customized Control Tasks of Fighter Aircrafts

The advent of deep learning (DL) gave rise to significant breakthroughs ...
research
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...
research
02/04/2019

Obstacle Tower: A Generalization Challenge in Vision, Control, and Planning

The rapid pace of research in Deep Reinforcement Learning has been drive...
research
04/03/2023

Enabling A Network AI Gym for Autonomous Cyber Agents

This work aims to enable autonomous agents for network cyber operations ...
research
04/17/2018

Terrain RL Simulator

We provide 89 challenging simulation environments that range in difficul...
research
06/03/2022

Challenges to Solving Combinatorially Hard Long-Horizon Deep RL Tasks

Deep reinforcement learning has shown promise in discrete domains requir...
research
03/03/2023

CoRL: Environment Creation and Management Focused on System Integration

Existing reinforcement learning environment libraries use monolithic env...

Please sign up or login with your details

Forgot password? Click here to reset