Playing Atari with Deep Reinforcement Learning
Volodymyr Mnih, Koray Kavukcuoglu, David Silver, Alex Graves, Ioannis Antonoglou + 2 more
TLDR
This paper introduces a deep convolutional neural network trained with reinforcement learning to play Atari games directly from raw pixel inputs, outperforming previous methods and human experts on several games.
Key contributions
- Developed the first deep reinforcement learning model to learn control policies from high-dimensional sensory input (raw pixels).
- Used a convolutional neural network combined with a variant of Q-learning to estimate future rewards.
- Demonstrated superior performance on seven Atari 2600 games, surpassing previous methods on six and human experts on three.
Why it matters
This paper is significant because it bridges deep learning and reinforcement learning to enable agents to learn complex control tasks directly from raw sensory data without manual feature engineering. It established a foundational approach for training AI systems that can learn effective policies in high-dimensional environments, influencing subsequent research in deep reinforcement learning and autonomous decision-making.
Original Abstract
We present the first deep learning model to successfully learn control policies directly from high-dimensional sensory input using reinforcement learning. The model is a convolutional neural network, trained with a variant of Q-learning, whose input is raw pixels and whose output is a value function estimating future rewards. We apply our method to seven Atari 2600 games from the Arcade Learning Environment, with no adjustment of the architecture or learning algorithm. We find that it outperforms all previous approaches on six of the games and surpasses a human expert on three of them.
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.