Reinforcement learning with prediction-based rewards
OpenAI's Random Network Distillation (RND) uses prediction-based curiosity to exceed average human performance on Montezuma's Revenge for the first time.
Excerpt
We’ve developed Random Network Distillation (RND), a prediction-based method for encouraging reinforcement learning agents to explore their environments through curiosity, which for the first time exceeds average human performance on Montezuma’s Revenge.
Read at source: https://openai.com/index/reinforcement-learning-with-prediction-based-rewards