arXiv (Cornell University) · 2019 · 108 citations · 36 references
ComputingDecision SciencesMachine LearningMarkov Decision ProcessesOptimizationOptimal ControlPolicy LearningReinforcement LearningReward DesignExpected Return AnalysisFew-shot LearningMultiobjective Reinforcement LearningOptimal PoliciesParametric RepresentationReward Function Design
We introduce a new algorithm for multi-objective reinforcement learning (MORL) with linear preferences, with the goal of enabling few-shot adaptation to new tasks. In MORL, the aim is to learn policies over multiple competing objectives whose relative importance (preferences) is unknown to the agent. While this alleviates dependence on scalar reward design, the expected return of a policy can change significantly with varying preferences, making it challenging to learn a single model to produce optimal policies under different preference conditions. We propose a generalized version of the Bellman equation to learn a single parametric representation for optimal policies over the space of all possible preferences. After an initial learning phase, our agent can execute the optimal policy under any given preference, or automatically infer an underlying preference with very few samples. Experiments across four different domains demonstrate the effectiveness of our approach.
36
Laurens van der Maaten, Geoffrey E. Hinton · Journal of Machine Learning Research · 2008 · 35.7K citations
Human-level control through deep reinforcement learning
Volodymyr Mnih, Koray Kavukcuoglu, David Silver et al. · Nature · 2015 · 30K citations
Continuous control with deep reinforcement learning
Timothy Lillicrap, Jonathan J. Hunt, Alexander Pritzel et al. · arXiv (Cornell University) · 2016 · 6.8K citations · Full text
Computing, Computer Science, Physics +17
Christopher J. Watkins, Peter Dayan · Machine Learning · 1992 · 3.7K citations