NovelGym: A Flexible Ecosystem for Hybrid Planning and Learning Agents Designed for Open Worlds
This provides a tool for researchers developing AI agents for real-world applications like autonomous vehicles and robots, but it is incremental as it focuses on simulation and benchmarking rather than new algorithms.
The paper tackles the need for evaluating AI agents in open-world scenarios by introducing NovelGym, a flexible ecosystem for simulating gridworld environments, which serves as a platform for benchmarking reinforcement learning and hybrid planning and learning agents.
As AI agents leave the lab and venture into the real world as autonomous vehicles, delivery robots, and cooking robots, it is increasingly necessary to design and comprehensively evaluate algorithms that tackle the ``open-world''. To this end, we introduce NovelGym, a flexible and adaptable ecosystem designed to simulate gridworld environments, serving as a robust platform for benchmarking reinforcement learning (RL) and hybrid planning and learning agents in open-world contexts. The modular architecture of NovelGym facilitates rapid creation and modification of task environments, including multi-agent scenarios, with multiple environment transformations, thus providing a dynamic testbed for researchers to develop open-world AI agents.