Efficient Active Imitation Learning with Random Network Distillation

Understand

Developing agents for complex and underspecified tasks, where no clear objective exists, remains challenging but offers many opportunities.

• This is especially true in video games, where simulated players (bots) need to play realistically, and there is no clear reward to evaluate them.
• While imitation learning has shown promise in such domains, these methods often fail when agents encounter out-of-distribution scenarios during deployment.
• Expanding the training dataset is a common solution, but it becomes impractical or costly when relying on human demonstrations.