Multi-objective Reinforcement Learning through Continuous Pareto Manifold Approximation

DOI10.1613/jair.4961zbMath1386.68137OpenAlexW2535247013MaRDI QIDQ2829188

Matteo Pirotta, Marcello Restelli, Simone Parisi

Publication date: 27 October 2016

Published in: Journal of Artificial Intelligence Research (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1613/jair.4961

Mathematics Subject Classification ID

Multi-objective and goal programming (90C29) Learning and adaptive systems in artificial intelligence (68T05)

Related Items (6)

Necessary and sufficient Karush-Kuhn-Tucker conditions for multiobjective Markov chains optimality ⋮ Unnamed Item ⋮ Computing multiobjective Markov chains handled by the extraproximal method ⋮ Efficient Multi-objective Reinforcement Learning via Multiple-gradient Descent with Iteratively Discovered Weight-Vector Sets ⋮ The hard lessons and shifting modeling trends of COVID-19 dynamics: multiresolution modeling approach ⋮ Using the Manhattan distance for computing the multiobjective Markov chains problem

This page was built for publication: Multi-objective Reinforcement Learning through Continuous Pareto Manifold Approximation