It Takes Four to Tango: Multiagent Selfplay for Automatic Curriculum Generation

Understand

We are interested in training general-purpose reinforcement learning agents that can solve a wide variety of goals.

• Training such agents efficiently requires automatic generation of a goal curriculum.
• This is challenging as it requires (a) exploring goals of increasing difficulty, while ensuring that the agent (b) is exposed to a diverse set of goals in a sample efficient manner and (c) does not catastrophically forget previously solved goals.
• We propose Curriculum Self Play (CuSP), an automated goal generation framework that seeks to satisfy these desiderata by virtue of a multi-player game with four agents.