23724

Mastering Atari with Discrete World Models

Danijar Hafner, Timothy Lillicrap, Mohammad Norouzi, Jimmy Ba
Google Brain
arXiv:2010.02193 [cs.LG], (5 Oct 2020)

@misc{hafner2020mastering,

   title={Mastering Atari with Discrete World Models},

   author={Danijar Hafner and Timothy Lillicrap and Mohammad Norouzi and Jimmy Ba},

   year={2020},

   eprint={2010.02193},

   archivePrefix={arXiv},

   primaryClass={cs.LG}

}

Download Download (PDF)   View View   Source Source   Source codes Source codes

Package:

422

views

Intelligent agents need to generalize from past experience to achieve goals in complex environments. World models facilitate such generalization and allow learning behaviors from imagined outcomes to increase sample-efficiency. While learning world models from image inputs has recently become feasible for some tasks, modeling Atari games accurately enough to derive successful behaviors has remained an open challenge for many years. We introduce DreamerV2, a reinforcement learning agent that learns behaviors purely from predictions in the compact latent space of a powerful world model. The world model uses discrete representations and is trained separately from the policy. DreamerV2 constitutes the first agent that achieves human-level performance on the Atari benchmark of 55 tasks by learning behaviors inside a separately trained world model. With the same computational budget and wall-clock time, DreamerV2 reaches 200M frames and exceeds the final performance of the top single-GPU agents IQN and Rainbow.
No votes yet.
Please wait...

* * *

* * *

HGPU group © 2010-2020 hgpu.org

All rights belong to the respective authors

Contact us: