DeepAveragers: Offline Reinforcement Learning by Solving Derived Non-Parametric MDPs

Aayam Shrestha, Stefan Lee, Prasad Tadepalli, Alan Fern

Abstract

We study an approach to offline reinforcement learning (RL) based on optimally solving finitely-represented MDPs derived from a static dataset of experience. This approach can be applied on top of any learned representation and has the potential to easily support multiple solution objectives as well as zero-shot adjustment to changing environments and goals. Our main contribution is to introduce the Deep Averagers with Costs MDP (DAC-MDP) and to investigate its solutions for offline RL. DAC-MDPs are a non-parametric model that can leverage deep representations and account for limited data by introducing costs for exploiting under-represented parts of the model. In theory, we show conditions that allow for lower-bounding the performance of DAC-MDP solutions. We also investigate the empirical behavior in a number of environments, including those with image-based observations. Overall, the experiments demonstrate that the framework can work in practice and scale to large complex offline RL problems.
BibTeX
@inproceedings{shrestha2021deepaveragers,
  author = {Aayam Shrestha and Stefan Lee and Prasad Tadepalli and Alan Fern},
  title = {{DeepAveragers: Offline Reinforcement Learning by Solving Derived Non-Parametric MDPs}},
  booktitle = {International Conference on Learning Representations},
  year = {2021},
  url = {https://openreview.net/forum?id=eMP1j9efXtX},
}
Figure