There are two main approaches to improving the sample efficiency of reinforcement learning methods - using hierarchical methods and expert demonstrations.
We demonstrate a reinforcement learning agent which uses a compositional recurrent neural network that takes as input an LTL formula and determines satisfying actions.
Rapid online adaptation to changing tasks is an important problem in machine learning and, recently, a focus of meta-reinforcement learning.
Sample inefficiency of deep reinforcement learning methods is a major obstacle for their use in real-world applications.
We present Hierarchical Deep Q-Network (HDQfD) that took first place in the MineRL competition.