Based on the helicopter simulator from Andrew Ng's group, agents must control a helicopter which is attempting to stably hover. Challenges include:
Get more details on the Helicopter domain.
Download the training Helicopter domain.
Competitors must code a general purpose RL agent. Agents are tested on a variety of different MDPs which do not exhibit systematic structure between themselves. This forces the agent to learn quickly and reason flexibly about general MDPs. Challenges include:
Get more details on the Polyathlon domain.
Download the training Polyathlon domain.
Get more details on the Invasive species domain.
Download the training invasive species domain.