“Learning and Querying Fast Generative Models for Reinforcement Learning”, 2018-02-08 (; similar):
A key challenge in model-based reinforcement learning (RL) is to synthesize computationally efficient and accurate environment models.
We show that carefully designed generative models that learn and operate on compact state representations, so-called state-space models, substantially reduce the computational costs for predicting outcomes of sequences of actions.
Extensive experiments establish that state-space models accurately capture the dynamics of Atari games from the Arcade Learning Environment from raw pixels. The computational speed-up of state-space models while maintaining high accuracy makes their application in RL feasible: We demonstrate that agents which query these models for decision making outperform strong model-free baselines on the game Ms. Pacman, demonstrating the potential of using learned environment models for planning.