Semantic Scholar Open Access 2016 9855 sitasi

Asynchronous Methods for Deep Reinforcement Learning

Volodymyr Mnih Adrià Puigdomènech Badia Mehdi Mirza Alex Graves T. Lillicrap +3 lainnya

Abstrak

We propose a conceptually simple and lightweight framework for deep reinforcement learning that uses asynchronous gradient descent for optimization of deep neural network controllers. We present asynchronous variants of four standard reinforcement learning algorithms and show that parallel actor-learners have a stabilizing effect on training allowing all four methods to successfully train neural network controllers. The best performing method, an asynchronous variant of actor-critic, surpasses the current state-of-the-art on the Atari domain while training for half the time on a single multi-core CPU instead of a GPU. Furthermore, we show that asynchronous actor-critic succeeds on a wide variety of continuous motor control problems as well as on a new task of navigating random 3D mazes using a visual input.

Penulis (8)

V

Volodymyr Mnih

A

Adrià Puigdomènech Badia

M

Mehdi Mirza

A

Alex Graves

T

T. Lillicrap

T

Tim Harley

D

David Silver

K

K. Kavukcuoglu

Format Sitasi

Mnih, V., Badia, A.P., Mirza, M., Graves, A., Lillicrap, T., Harley, T. et al. (2016). Asynchronous Methods for Deep Reinforcement Learning. https://www.semanticscholar.org/paper/69e76e16740ed69f4dc55361a3d319ac2f1293dd

Akses Cepat

PDF tidak tersedia langsung

Cek di sumber asli →
Lihat di Sumber
Informasi Jurnal
Tahun Terbit
2016
Bahasa
en
Total Sitasi
9855×
Sumber Database
Semantic Scholar
Akses
Open Access ✓