Rainbow: Combining Improvements in Deep Reinforcement Learning
This work addresses the challenge of integrating complementary extensions for researchers and practitioners in reinforcement learning, though it is incremental as it combines existing methods.
The paper tackled the problem of combining multiple independent improvements to the DQN algorithm in deep reinforcement learning, resulting in state-of-the-art performance on the Atari 2600 benchmark in terms of data efficiency and final performance.
The deep reinforcement learning community has made several independent improvements to the DQN algorithm. However, it is unclear which of these extensions are complementary and can be fruitfully combined. This paper examines six extensions to the DQN algorithm and empirically studies their combination. Our experiments show that the combination provides state-of-the-art performance on the Atari 2600 benchmark, both in terms of data efficiency and final performance. We also provide results from a detailed ablation study that shows the contribution of each component to overall performance.