APES: a Python toolbox for simulating reinforcement learning environments
This provides a tool for researchers and practitioners in reinforcement learning to more easily build and test environments, but it is incremental as it builds on existing grid-world simulation concepts.
The authors tackled the challenge of designing and simulating reinforcement learning environments by introducing APES, a customizable Python toolbox for creating 2D grid-world environments, which supports features like field-of-vision simulation, item placement, and multi-agent interaction.
Assisted by neural networks, reinforcement learning agents have been able to solve increasingly complex tasks over the last years. The simulation environment in which the agents interact is an essential component in any reinforcement learning problem. The environment simulates the dynamics of the agents' world and hence provides feedback to their actions in terms of state observations and external rewards. To ease the design and simulation of such environments this work introduces $\texttt{APES}$, a highly customizable and open source package in Python to create 2D grid-world environments for reinforcement learning problems. $\texttt{APES}$ equips agents with algorithms to simulate any field of vision, it allows the creation and positioning of items and rewards according to user-defined rules, and supports the interaction of multiple agents.