DOP: Deep Optimistic Planning with Approximate Value Function Evaluation

摘要

Research on reinforcement learning has demonstrated promising results in manifold applications and domains. Still, efficiently learning effective robot behaviors is very difficult, due to unstructured scenarios, high uncertainties, and large state dimensionality (e.g. multi-agent systems or hyper-redundant robots). To alleviate this problem, we present DOP, a deep model-based reinforcement learning algorithm, that attacks the curse of dimensionality and reduces the computational demand of the planning process while achieving good performance.