Challenges Facing the Reinforcement Learning (RL) Community

Reinforcement Learning (RL) is a powerful subfield of AI that can be used to solve a wide range of problems. However, the reinforcement learning community faces a number of challenges. One challenge is the need for better methods for debugging and troubleshooting reinforcement learning algorithms during learning and during implementation, especially in multi-agent partially observed settings where full state observability is not maintained by all agents in every step of their decision making. In the multi-agent partially observed setting, most of the time the agents are making their own independent observations of some underlying state process and the agents usually have a very few select ways of cooperating effectively to solve a difficult task including: distributed learning algorithms, communication protocols, and social norms or conventions such as setting a pre-defined order of decision making. Combining agent observations with a sensor fusion center or leader agent is also possible to coordinate decision making better.