Recent model-free reinforcement learning algorithms have proposed incorporating learned dynamics models as a source of additional data with the intention of reducing sample complexity. Such methods hold the promise of incorporating imagined data coupled with a notion of model uncertainty to accelerate the learning of continuous control tasks. Unfortunately, they rely on heuristics that limit usage of the dynamics model. We present model-based value expansion, which controls for uncertainty in the model by only allowing imagination to fixed depth. By enabling wider use of learned dynamics models within a model-free reinforcement learning algorithm, we improve value estimation, which, in turn, reduces the sample complexity of learning.
@article{arxiv.1803.00101,
title = {Model-Based Value Estimation for Efficient Model-Free Reinforcement Learning},
author = {Vladimir Feinberg and Alvin Wan and Ion Stoica and Michael I. Jordan and Joseph E. Gonzalez and Sergey Levine},
journal= {arXiv preprint arXiv:1803.00101},
year = {2018}
}