We know that scaling RL by stitching it together with deep nets works. This brings excitement to all keen on understanding and building autonomous agents solving hard real world problems. But, we have only seen early results brought about by excellent engineering innovations, barring a few fundamental revisits to RL, e.g. distributional perspective on RL.

The latter has shown even greater promise, thankfully. We need more revisits like these. We need to take a step back and examine the building blocks of RL, deep nets, training regimens, and the nature of dynamic systems, to see how and when these complement each other. This may lead to novel learning schemes and substrates. In so doing, we will find ways to make RL work orders of magnitude better than it does today. We want RL to be data efficient, to generalise, and to go wild.

This repo is to aggregate all the work (being) done along these lines.

These meetings are distributed by nature, therefore can be accessed through https://appear.in/wildrl