Conditional imitation learning (CIL) trains deep neural networks, in an end-to-end manner, to mimic human driving. This approach has demonstrated suitable vehicle control when following roads, avoiding obstacles, or taking specific turns at intersections reach a destination. Unfortunately, performance dramatically decreases deployed unseen environments and is inconsistent against varying weathe...

Parameter-driven simulations are an effective and efficient method for reasoning about a wide range of commonsense scenarios that can complement the use of logical formalizations. The advantage of simulation is its simplified knowledge elicitation process: rather than building complex logical formulae, simulations are constructed by simply selecting numerical values and graphical structures. In...

Reinforcement learning addresses the question of how an autonomous agent can learn to choose optimal actions to achieve its goals. Efficient exploration is of fundamental importance for autonomous agents that learn to act. Previous approaches to exploration in reinforcement learning usually address exploration in the case when the environment is fully observable. In contrast, we study the case ...

Originated from America, the student-oriented flipped classroom, which focuses on the individual demands and expressions of students, has become a hot topic in education fields in and out of China, along with the development of information technology and updating of teaching ideas. This study attempts to establish a "task driven and ability targeted" flipped classroom mode, with creation class ...