Is Meta Learning a Good Application?

meta RL has been used in a number of robotics papers at the moment for some pretty cool effects. In addition to the robot locomotion problem one application area we go into is the meta learning from multi agent rl problem and they're kind of just to summarize concisely you can view other agents as defining the task so if you have a distribution of other agents that pretty clearly creates for you a distribution of tasks and you can directly apply metalearning.