… This paper serves as a guide to the application of multi-objective methods to difficult … single-objective reinforcementlearning and planning methods who wish to adopt a multi-objective …
K Van Moffaert, A Nowé - The Journal of Machine Learning Research, 2014 - jmlr.org
… The Pyramid MDP is a new and simple multi-objectivebenchmark, which we introduce in this paper. A visual representation of the world is depicted in Figure 7 (a). The agent starts in …
… To this aim, we propose a benchmark Python framework that supports both single-policy and multi-policy approaches to solving MODRL problems. Our framework is generic and highly …
… the multi-objective environments. We propose a novel multi-objectivereinforcementlearning … , together with a few benchmark environments. We build further on this work and perform …
… benchmark the quality of our algorithms, we propose the first non-trivial high-dimensional multi-objective … From raw visual input, an agent in Minecart must learn to adapt to the day’s …
… work on multi-objective optimization and reinforcement learning. … for multi-objective RL, together with a few benchmark … of these benchmark environments using the multiobjective Q-…
… (3) At empirical level, we provide new evaluation metrics and benchmark environments for MORL and apply our algorithm to a wider variety of domains including two complex larger …
K Li, T Zhang, R Wang - IEEE transactions on cybernetics, 2020 - ieeexplore.ieee.org
… Extensive experiments have been conducted to study the DRL-MOA and various benchmark … Murata, “A multi-objective genetic local search algorithm and its application to flowshop …