Avalon Reinforcement Learning Environment
Kanjun and Josh discuss Avalon, a fast 3D simulator and benchmark for reinforcement learning. They explain how it provides a shared reward function across tasks and forces agents to learn various behaviors. They also touch on the challenges of sparse rewards and the potential for future expansions.In this clip
From this podcast

The Gradient
Kanjun Qiu and Josh Albrecht: Generally Intelligent
Related Questions