Policy gradient methods hold great potential for solving complex continuous control tasks. Still, their training efficiency can be improved by exploiting structure within the optimization problem. Recent work indicates that supervised learning can be accelerated by leveraging the fact that gradients lie in a low-dimensional and slowly-changing subspace. In this paper, we conduct a thorough evaluation of this phenomenon for two popular deep policy gradient methods on various simulated benchmark tasks. Our results demonstrate the existence of such gradient subspaces despite the continuously changing data distribution inherent to reinforcement learning. These findings reveal promising directions for future work on more efficient reinforcement learning, e.g., through improving parameter-space exploration or enabling second-order optimization.

翻译：策略梯度方法在解决复杂连续控制任务中具有巨大潜力。然而，通过利用优化问题中的结构特性，其训练效率仍有提升空间。近期研究表明，利用梯度位于低维且缓慢变化子空间这一特性，可以加速监督学习过程。本文针对两种主流的深度策略梯度方法，在多种模拟基准任务上对该现象进行了全面评估。实验结果表明，尽管强化学习固有的数据分布持续变化，此类梯度子空间仍然存在。这些发现为未来研究更高效的强化学习方法指明了方向，例如通过改进参数空间探索或实现二阶优化。