Unified Distributed Environment
This addresses the challenge for RL researchers of managing disparate simulation environments, though it appears incremental as it builds on existing virtualization concepts.
The paper tackles the problem of integrating diverse simulation platforms for reinforcement learning research by proposing Unified Distributed Environment (UDE), a toolkit that enables environment virtualization and remote execution while maintaining a unified interface, resulting in support for multi-agent training and compatibility with existing RL toolkits.
We propose Unified Distributed Environment (UDE), an environment virtualization toolkit for reinforcement learning research. UDE is designed to integrate environments built on any simulation platform such as Gazebo, Unity, Unreal, and OpenAI Gym. Through environment virtualization, UDE enables offloading the environment for execution on a remote machine while still maintaining a unified interface. The UDE interface is designed to support multi-agent by default. With environment virtualization and its interface design, the agent policies can be trained in multiple machines for a multi-agent environment. Furthermore, UDE supports integration with existing major RL toolkits for researchers to leverage the benefits. This paper discusses the components of UDE and its design decisions.