Файл:Human-level control through deep reinforcement learning.pdf
Volodymyr Mnih1*, Koray Kavukcuoglu1*, David Silver1*, Andrei A. Rusu1, Joel Veness1, Marc G. Bellemare1, Alex Graves1, Martin Riedmiller1, Andreas K. Fidjeland1, Georg Ostrovski1, Stig Petersen1, Charles Beattie1, Amir Sadik1, Ioannis Antonoglou1, Helen King1, Dharshan Kumaran1, Daan Wierstra1, Shane Legg1 & Demis Hassabis1
The theory of reinforcement learning provides a normative account, deeply rooted in psychological2 and neuroscientific perspectives on animal behaviour, of how agents may optimize their control of an environment. To use reinforcement learning successfully in situations approaching real-world complexity, however, agents are confronted with a difficult task: they must derive efficient representations of the environment from high-dimensional sensory inputs, and use these to generalize past experience to new situations. Remarkably, humans and other animals seem to solve this problem through a harmonious combination of reinforcement learning and hierarchical sensory processing systems4,5, the former evidenced by a wealth of neural data revealing notable parallels between the phasic signals emitted by dopaminergic neurons and temporal difference reinforcement learning algorithms3. While reinforcement learning agents have achieved some successes in a variety of domains 6–8, their applicability has previously been limited to domains in which useful features can be hand crafted, or to domains with fully observed, low-dimensional state spaces. Here we use recent advances in training deep neural networks 9–11 to develop a novel artificial agent, termed a deep Q-network,that can learn successful policies directly from high-dimensional sensory inputs using end-to-end reinforcement learning. We tested this agent on the challenging domain of classic Atari 2600 games12. We demonstrate that the deep Q-network agent, receiving only the pixels and the game score as inputs, was able to surpass the performance of all previous algorithms and achieve a level comparable to that of aprofessional human games tester across a set of 49 games, using the same algorithm, network architecture and hyperparameters. This work bridges the divide between high-dimensional sensory inputs and actions, resulting in the first artificial agent that is capable of learning to excel at a diverse array of challenging tasks.
Нажмите на дату/время, чтобы просмотреть, как тогда выглядел файл.
|текущий||14:26, 22 декабря 2016||0 × 0 (4,39 МБ)||Slikos|
- Вы не можете перезаписать этот файл.