Asynchronous Methods for Deep Reinforcement Learning
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.
Topik & Kata Kunci
Penulis (8)
Volodymyr Mnih
Adrià Puigdomènech Badia
Mehdi Mirza
Alex Graves
T. Lillicrap
Tim Harley
David Silver
K. Kavukcuoglu
Akses Cepat
PDF tidak tersedia langsung
Cek di sumber asli →- Tahun Terbit
- 2016
- Bahasa
- en
- Total Sitasi
- 9855×
- Sumber Database
- Semantic Scholar
- Akses
- Open Access ✓