Deep Reinforcement Learning with Spiking Q-learning
This work addresses the problem of high energy consumption in AI for control tasks, offering a more efficient alternative, though it is incremental as it builds on existing SNN and RL techniques.
The authors tackled the challenge of developing an energy-efficient deep reinforcement learning method using spiking neural networks (SNNs) by proposing the deep spiking Q-network (DSQN), which outperformed ANN-based DQN on most of 17 Atari games and showed superior stability and robustness to adversarial attacks.
With the help of special neuromorphic hardware, spiking neural networks (SNNs) are expected to realize artificial intelligence (AI) with less energy consumption. It provides a promising energy-efficient way for realistic control tasks by combining SNNs with deep reinforcement learning (RL). There are only a few existing SNN-based RL methods at present. Most of them either lack generalization ability or employ Artificial Neural Networks (ANNs) to estimate value function in training. The former needs to tune numerous hyper-parameters for each scenario, and the latter limits the application of different types of RL algorithm and ignores the large energy consumption in training. To develop a robust spike-based RL method, we draw inspiration from non-spiking interneurons found in insects and propose the deep spiking Q-network (DSQN), using the membrane voltage of non-spiking neurons as the representation of Q-value, which can directly learn robust policies from high-dimensional sensory inputs using end-to-end RL. Experiments conducted on 17 Atari games demonstrate the DSQN is effective and even outperforms the ANN-based deep Q-network (DQN) in most games. Moreover, the experiments show superior learning stability and robustness to adversarial attacks of DSQN.