论文标题
持续控制的强化学习可以在物理引擎之间推广吗?
Can Reinforcement Learning for Continuous Control Generalize Across Physics Engines?
论文作者
论文摘要
强化学习(RL)算法应尽可能多地了解环境,而不是生成环境的物理引擎的特性。有多种算法可以在基于物理引擎的环境中解决该任务,但是到目前为止,还没有做任何工作可以理解RL算法是否可以跨物理引擎概括。在这项工作中,我们比较了各种控制任务上各种深层增强学习算法的概括性能。我们的结果表明,Mujoco是将学习转移到其他引擎的最佳引擎。另一方面,在Pybullet训练时,算法都没有概括。我们还发现,如果可以将随机种子的效果最小化,则各种算法具有有希望的普遍性。
Reinforcement learning (RL) algorithms should learn as much as possible about the environment but not the properties of the physics engines that generate the environment. There are multiple algorithms that solve the task in a physics engine based environment but there is no work done so far to understand if the RL algorithms can generalize across physics engines. In this work, we compare the generalization performance of various deep reinforcement learning algorithms on a variety of control tasks. Our results show that MuJoCo is the best engine to transfer the learning to other engines. On the other hand, none of the algorithms generalize when trained on PyBullet. We also found out that various algorithms have a promising generalizability if the effect of random seeds can be minimized on their performance.