We investigate the challenge of parametrizing policies for reinforcement learning (RL) in high-dimensional continuous action spaces. Our objective is to develop a multimodal policy that overcomes limitations inherent in the commonly-used Gaussian parameterization. To achieve this, we propose a principled framework that models the continuous RL policy as a generative model of optimal trajectories. By conditioning the policy on a latent variable, we derive a novel variational bound as the optimization objective, which promotes exploration of the environment. We then present a practical model-based RL method, called Reparameterized Policy Gradient (RPG), which leverages the multimodal policy parameterization and learned world model to achieve strong exploration capabilities and high data efficiency. Empirical results demonstrate that our method can help agents evade local optima in tasks with dense rewards and solve challenging sparse-reward environments by incorporating an object-centric intrinsic reward. Our method consistently outperforms previous approaches across a range of tasks. Code and supplementary materials are available on the project page https://haosulab.github.io/RPG/

我们研究了在高维连续动作空间中参数化强化学习（RL）策略的挑战。我们的目标是开发一种多模式策略，以克服常用的高斯参数化方法固有的限制。为了实现这一目标，我们提出了一个原则性框架，将连续RL策略建模为最优轨迹的生成模型。通过将策略条件化于潜变量，我们导出了一种新颖的变分下界作为优化目标，以促进环境的探索。然后，我们提出了一种实用的基于模型的RL方法，称为重新参数化策略梯度（RPG），它利用多模式策略参数化和学习的世界模型来实现强大的探索能力和高效数据利用率。实证结果表明，我们的方法可以帮助Agent在具有密集奖励的任务中避免局部最优值，并通过结合面向对象的内在奖励来解决具有挑战性的稀疏奖励环境。我们的方法在各种任务中始终优于以前的方法。项目页面提供了代码和补充材料。

多模态轨迹优化的重参数化策略学习