Timezone: »

Model-based Lifelong Reinforcement Learning with Bayesian Exploration
Haotian Fu · Shangqun Yu · Michael Littman · George Konidaris

Wed Nov 30 09:00 AM -- 11:00 AM (PST) @ Hall J #224

We propose a model-based lifelong reinforcement-learning approach that estimates a hierarchical Bayesian posterior distilling the common structure shared across different tasks. The learned posterior combined with a sample-based Bayesian exploration procedure increases the sample efficiency of learning across a family of related tasks. We first derive an analysis of the relationship between the sample complexity and the initialization quality of the posterior in the finite MDP setting. We next scale the approach to continuous-state domains by introducing a Variational Bayesian Lifelong Reinforcement Learning algorithm that can be combined with recent model-based deep RL methods, and that exhibits backward transfer. Experimental results on several challenging domains show that our algorithms achieve both better forward and backward transfer performance than state-of-the-art lifelong RL methods.

Author Information

Haotian Fu (Brown University)
Shangqun Yu (Brown University)
Michael Littman (Brown University)
George Konidaris (Brown University)

More from the Same Authors