• Computer Science
  • Published in ArXiv 2018

Meta-Learning for Multi-objective Reinforcement Learning

@article{Chen2018MetaLearningFM,
  title={Meta-Learning for Multi-objective Reinforcement Learning},
  author={Xiao Dong Chen and Ali Ghadirzadeh and M{\aa}rten Bj{\"o}rkman and Patric Jensfelt},
  journal={ArXiv},
  year={2018},
  volume={abs/1811.03376}
}
Abstract-Multi-objective reinforcement learning (MORL) is the generalization of standard reinforcement learning (RL) approaches to solve sequential decision making problems that consist of several, possibly conflicting, objectives. [...] Key ResultWe evaluated our method on obtaining Pareto optimal policies using a number of continuous control problems with high degrees of freedom. Expand Abstract
8
Twitter Mentions

References

Publications referenced by this paper.
SHOWING 1-10 OF 20 REFERENCES

Policy gradient approaches for multi-objective sequential decision making

  • 2014 International Joint Conference on Neural Networks (IJCNN)
  • 2014
VIEW 5 EXCERPTS
HIGHLY INFLUENTIAL

Multiobjective Reinforcement Learning: A Comprehensive Overview

  • IEEE Transactions on Systems, Man, and Cybernetics: Systems
  • 2015
VIEW 5 EXCERPTS
HIGHLY INFLUENTIAL

Deep predictive policy training using reinforcement learning

  • 2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
  • 2017
VIEW 1 EXCERPT