Scalarized multi-objective reinforcement learning: Novel design techniques
By Kristof Van Moffaert, Mădălina M. Drugan, Ann Nowé. IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning, 2013
304 citations recorded by the source corpus.
Subfields: Artificial Intelligence, Computational Theory and Mathematics
View Paper: https://www.semanticscholar.org/paper/f51265b88ce01e7e3c12fa9b8dc84dfd0a73975c
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Sergey Levine
- Pieter Abbeel
- Nicolas Manfred Otto Heess
- Chelsea Finn
- Ruslan Salakhutdinov
- Yoshua Bengio
- Karthik Narasimhan
- Leonard Hasenclever
In Computational Theory and Mathematics
- Nicolas Manfred Otto Heess
- Leonard Hasenclever
- Martin A. Riedmiller
- Ann Nowé
- Kristof Van Moffaert
- Abbas Abdolmaleki
- Raia Hadsell
- Sergey Levine
Citations in the corpus
- A Generalized Algorithm for Multi-Objective Reinforcement Learning and Policy Adaptation (2019, background): “The most common strategy is to perform multiple runs of a single-policy method over different preferences [7, 18].”
- Multi-objective reinforcement learning using sets of pareto dominating policies (2014, methodology): “The set of Pareto optimal policies is referred to as the Pareto front.”
- A Distributional View on Multi-Objective Policy Optimization (2020, background): “Often this scalarization is linear, but other choices have also been explored (Van Moffaert et al., 2013).”