DNS: Determinantal Point Process Based Neural Network Sampler for Ensemble Reinforcement Learning
This work addresses the computational bottleneck for researchers and practitioners using ensemble methods in reinforcement learning, offering an incremental improvement to existing algorithms.
The paper tackles the high computation cost of training ensemble neural networks in deep reinforcement learning by proposing DNS, a Determinantal Point Process based sampler that selects a subset of networks for backpropagation, reducing training time and achieving higher average cumulative reward with less than 50% computation in FLOPS compared to baseline REDQ.
Application of ensemble of neural networks is becoming an imminent tool for advancing the state-of-the-art in deep reinforcement learning algorithms. However, training these large numbers of neural networks in the ensemble has an exceedingly high computation cost which may become a hindrance in training large-scale systems. In this paper, we propose DNS: a Determinantal Point Process based Neural Network Sampler that specifically uses k-dpp to sample a subset of neural networks for backpropagation at every training step thus significantly reducing the training time and computation cost. We integrated DNS in REDQ for continuous control tasks and evaluated on MuJoCo environments. Our experiments show that DNS augmented REDQ outperforms baseline REDQ in terms of average cumulative reward and achieves this using less than 50% computation when measured in FLOPS.