In the pursuit of artificial general intelligence, our most significant measure of progress is an agent’s ability to achieve goals in a wide range of environments . Existing platforms for constructing such environments are constrained by technologies they are founded on . We present our use of Unity, a widelyrecognized and comprehensive game engine, to create more diverse, complex,virtual simulations . We also introduce a practical approach topackaging and re-distributing environments in a way that attempts to improve the robustness and reproducibility of experiment results . We hopethat others can draw inspiration from how we adapted Unity to our needs, and anticipate increasingly varied and complex environments to emerge from our approach as familiarity grows . We hope to use Unity to develop our approach to develop new models of reinforcement learning. To illustrate theversatility of our approach compared to other solutions,

Author(s) : Tom Ward, Andrew Bolt, Nik Hemmings, Simon Carter, Manuel Sanchez, Ricardo Barreira, Seb Noury, Keith Anderson, Jay Lemmon, Jonathan Coe, Piotr Trochim, Tom Handley, Adrian Bolton

Links : PDF - Abstract

Code :

Keywords : environments - approach - unity - develop - intelligence -

Leave a Reply

Your email address will not be published. Required fields are marked *