TOWARD LEARNING HUMAN-LIKE, SAFE AND COMFORTABLE CAR-FOLLOWING POLICIES WITH A NOVEL DEEP REINFORCEMENT LEARNING APPROACH

Toward Learning Human-Like, Safe and Comfortable Car-Following Policies With a Novel Deep Reinforcement Learning Approach

In this paper, we present an advanced adaptive cruise control (ACC) concept powered by Deep Reinforcement Learning (DRL) that generates safe, human-like, and comfortable car-following policies.Unlike the current trend in developing DRL-based ACC systems, we propose defining the action space of the DRL agent with discrete actions rather than continu

read more

Galactic Evolution Showing a Constant Circulating Speed of Stars in a Galactic Disc without Requiring Dark Matter

It is an unsolved mystery that the rotation velocity of a galactic disc is same at any radial distances.The presence of dark matter is expected, but not observed.Here we propose a novel scheme for the evolution of the initial cosmic energy to current galaxies.According to the energy circulation theory, which we previously reported, the fundamental

read more