… is an important conflict: should we learn over actions, training a reinforcement learning
agent to discover the best actions to take, or should we learn over algorithms, trying to discover …

… In this paper we propose to tackle the large-scale fleet management problem using
reinforcement learning, and propose a contextual multi-agent reinforcement learning framework …

… In this paper, we scale-up our “compressed… -large networks due to the high-dimensionality
of their input space. The approach is demonstrated successfully on two reinforcement learning …

Reinforcement learning (RL) is a promising data-driven approach for adaptive traffic signal …
enhance its learning power. However, the centralized RL is infeasible for large-scale ATSC …

… reinforcement learning (DRL)-based method that allows unmanned aerial vehicles (UAVs)
to execute navigation tasks in large-scale … in a virtual large-scale complex environment and …

In recent years, on-policy reinforcement learning (RL) has been successfully applied to many
different continuous control tasks. While RL algorithms are often conceptually simple, their …

… Our approach and empirical results highlight how reinforcement learning agents can benefit
from direct access to a large collection of raw interaction data at inference time, through a …

… (2) Reinforcement learning based virtual links mapping model: In order to achieve the …
tree network for the largescale tasks allocation, we have proposed a reinforcement learning-based …

… search for better results in large-scale solution space more effectively. In this paper, we
propose a large-scale optimization algorithm called reinforcement learning level-based particle …

… Such challenge is even more outstanding when forming control decisions on a largescale …
a problem by proposing a cooperative deep reinforcement learning (Coder) framework. The …