Simon Willison’s Weblog

31st October 2018

Reinforcement Learning with Prediction-Based Rewards (via) Fascinating result: by teaching a reinforcement learning agent that plays video games to optimize for "unfamiliar states" - states where it cannot predict what will happen next - the agent does a much better job of playing some games.

... for the first time exceeds average human performance on Montezuma’s Revenge. RND achieves state-of-the-art performance, periodically finds all 24 rooms and solves the first level without using demonstrations or having access to the underlying state of the game.