Flexible Traffic Signal Control via Multi-objective Reinforcement Learning

Reinforcement learning in neurofuzzy traffic signal control

Reinforcement Learning For Adaptive Traffic Signal Control

By 2050, two-thirds of the world’s 9.6 billion people will live in urban areas [2]. In many cities, opportunities to expand urban road networks are limited, so existing roads will need to more efficiently accommodate higher volumes of traffic. Consequently, there is a pressing need for technologically viable, low-cost solutions that can work with existing infrastructure to help alleviate increa...

Multi-Objective Reinforcement Learning

In multi-objective reinforcement learning (MORL) the agent is provided with multiple feedback signals when performing an action. These signals can be independent, complementary or conflicting. Hence, MORL is the process of learning policies that optimize multiple criteria simultaneously. In this abstract, we briefly describe our extensions to single-objective multi-armed bandits and reinforceme...

Why Multi-objective Reinforcement Learning?

We argue that multi-objective methods are underrepresented in RL research, and present three scenarios to justify the need for explicitly multi-objective approaches. Key to these scenarios is that although the utility the user derives from a policy — which is what we ultimately aim to optimize — is scalar, it is sometimes impossible, undesirable or infeasible to formulate the problem as single-...

Multi-Objective Deep Reinforcement Learning

We propose Deep Optimistic Linear Support Learning (DOL) to solve highdimensional multi-objective decision problems where the relative importances of the objectives are not known a priori. Using features from the high-dimensional inputs, DOL computes the convex coverage set containing all potential optimal solutions of the convex combinations of the objectives. To our knowledge, this is the fir...