GriddlyJS: A Web IDE for Reinforcement Learning

07/13/2022
by   Christopher Bamford, et al.
7

Progress in reinforcement learning (RL) research is often driven by the design of new, challenging environments – a costly undertaking requiring skills orthogonal to that of a typical machine learning researcher. The complexity of environment development has only increased with the rise of procedural-content generation (PCG) as the prevailing paradigm for producing varied environments capable of testing the robustness and generalization of RL agents. Moreover, existing environments often require complex build processes, making reproducing results difficult. To address these issues, we introduce GriddlyJS, a web-based Integrated Development Environment (IDE) based on the Griddly engine. GriddlyJS allows researchers to visually design and debug arbitrary, complex PCG grid-world environments using a convenient graphical interface, as well as visualize, evaluate, and record the performance of trained agent models. By connecting the RL workflow to the advanced functionality enabled by modern web standards, GriddlyJS allows publishing interactive agent-environment demos that reproduce experimental results directly to the web. To demonstrate the versatility of GriddlyJS, we use it to quickly develop a complex compositional puzzle-solving environment alongside arbitrary human-designed environment configurations and their solutions for use in automatic curriculum learning and offline RL. The GriddlyJS IDE is open source and freely available at <https://griddly.ai>.

READ FULL TEXT

page 5

page 7

page 16

page 19

page 20

page 24

page 25

page 26

research
09/27/2021

MiniHack the Planet: A Sandbox for Open-Ended Reinforcement Learning Research

The progress in deep reinforcement learning (RL) is heavily driven by th...
research
01/21/2022

Environment Generation for Zero-Shot Compositional Reinforcement Learning

Many real-world problems are compositional - solving them requires compl...
research
06/21/2023

AdCraft: An Advanced Reinforcement Learning Benchmark Environment for Search Engine Marketing Optimization

We introduce AdCraft, a novel benchmark environment for the Reinforcemen...
research
11/18/2020

Using Unity to Help Solve Intelligence

In the pursuit of artificial general intelligence, our most significant ...
research
10/24/2022

Avalon: A Benchmark for RL Generalization Using Procedurally Generated Worlds

Despite impressive successes, deep reinforcement learning (RL) systems s...
research
06/09/2022

Deep Surrogate Assisted Generation of Environments

Recent progress in reinforcement learning (RL) has started producing gen...

Please sign up or login with your details

Forgot password? Click here to reset