Reinforcement learning with prediction-based rewards

OpenAI · 7 years ago · 4

Researchers developed Random Network Distillation, a reinforcement learning method that uses prediction errors as curiosity rewards to drive exploration in agents. The approach achieved higher average scores than human players on Montezuma's Revenge, a notoriously difficult exploration-heavy video game. This enables RL agents to solve environments where traditional reward signals provide insufficient guidance for discovery.