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

Aayam Kumar Shrestha, Stefan Lee, Prasad Tadepalli, Alan Fern

Keywords: Offline Reinforcement Learning, Planning

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.

One-sentence Summary: The paper introduces and investigates an offline RL approach based on optimally solving a finite-state MDP that is derived from the experience dataset using any latent state representation.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Code: [ maximecb/gym-miniworld](https://github.com/maximecb/gym-miniworld) + [ 1 community implementation](https://paperswithcode.com/paper/?openreview=eMP1j9efXtX)