论文标题
通过多视图探索最大化来应对视觉控制
Tackling Visual Control via Multi-View Exploration Maximization
论文作者
论文摘要
我们提出MEM：用于应对复杂的视觉控制任务的多视图探索最大化。据我们所知，MEM是将多视图表示学习和内在奖励驱动探索（RL）结合在一起的第一种方法。更具体地说，MEM首先提取多视图观测值的特定和共享信息，以在进行学习功能上执行RL之前形成高质量的功能，从而使代理商能够完全理解环境并产生更好的操作。此外，MEM基于熵最大化，将多视图特征转化为固有的奖励，以鼓励探索。结果，MEM可以显着促进RL药物的样本效率和泛化能力，从而促进具有高维观测和备用奖励空间的现实世界中的问题。我们评估来自DeepMind Control Suite和Procgen Games的各种任务的MEM。广泛的仿真结果表明，MEM可以实现出色的性能，并以简单的体系结构和更高效率胜过基准测试方案。
We present MEM: Multi-view Exploration Maximization for tackling complex visual control tasks. To the best of our knowledge, MEM is the first approach that combines multi-view representation learning and intrinsic reward-driven exploration in reinforcement learning (RL). More specifically, MEM first extracts the specific and shared information of multi-view observations to form high-quality features before performing RL on the learned features, enabling the agent to fully comprehend the environment and yield better actions. Furthermore, MEM transforms the multi-view features into intrinsic rewards based on entropy maximization to encourage exploration. As a result, MEM can significantly promote the sample-efficiency and generalization ability of the RL agent, facilitating solving real-world problems with high-dimensional observations and spare-reward space. We evaluate MEM on various tasks from DeepMind Control Suite and Procgen games. Extensive simulation results demonstrate that MEM can achieve superior performance and outperform the benchmarking schemes with simple architecture and higher efficiency.
