Offline Learning for Planning: A Summary

TL;DR

This paper reviews offline learning methods for autonomous agents, focusing on how to leverage existing data to optimize policies without further environment interaction, and discusses practical and theoretical aspects of these approaches.

Contribution

It summarizes state-of-the-art offline learning algorithms that incorporate uncertainty constraints and discusses their practical utility and potential improvements using generative models.

Findings

Offline learning reduces the need for costly environment interactions.

Uncertainty-dependent constraints help mitigate distributional mismatch.

Generative Adversarial Networks can estimate distributional shifts.

Abstract

The training of autonomous agents often requires expensive and unsafe trial-and-error interactions with the environment. Nowadays several data sets containing recorded experiences of intelligent agents performing various tasks, spanning from the control of unmanned vehicles to human-robot interaction and medical applications are accessible on the internet. With the intention of limiting the costs of the learning procedure it is convenient to exploit the information that is already available rather than collecting new data. Nevertheless, the incapability to augment the batch can lead the autonomous agents to develop far from optimal behaviours when the sampled experiences do not allow for a good estimate of the true distribution of the environment. Offline learning is the area of machine learning concerned with efficiently obtaining an optimal policy with a batch of previously collected experiences without further interaction with the environment. In this paper we adumbrate the ideas motivating the development of the state-of-the-art offline learning baselines. The listed methods consist in the introduction of epistemic uncertainty dependent constraints during the classical resolution of a Markov Decision Process, with and without function approximators, that aims to alleviate the bad effects of the distributional mismatch between the available samples and real world. We provide comments on the practical utility of the theoretical bounds that justify the application of these algorithms and suggest the utilization of Generative Adversarial Networks to estimate the distributional shift that affects all of the proposed model-free and model-based approaches.