ToriLLE: Learning Environment for Hand-to-Hand Combat
This provides a platform for researchers in reinforcement learning to test agents in a competitive, humanoid fighting domain, but it is incremental as it adapts an existing game.
The authors tackled the need for a learning environment for hand-to-hand combat by presenting ToriLLE, based on the video game Toribash, and demonstrated its applicability for evaluating self-play methods and machine learning agents against human players.
We present Toribash Learning Environment (ToriLLE), a learning environment for machine learning agents based on the video game Toribash. Toribash is a MuJoCo-like environment of two humanoid character fighting each other hand-to-hand, controlled by changing actuation modes of the joints. Competitive nature of Toribash as well its focused domain provide a platform for evaluating self-play methods, and evaluating machine learning agents against human players. In this paper we describe the environment with ToriLLE's capabilities and limitations, and experimentally show its applicability as a learning environment. The source code of the environment and conducted experiments can be found at https://github.com/Miffyli/ToriLLE.