Efficient Model-Based Reinforcement Learning through Optimistic Policy Search and Planning


METADATA ONLY
Loading...

Date

2021

Publication Type

Conference Paper

ETH Bibliography

yes

Citations

Altmetric
METADATA ONLY

Data

Rights / License

Abstract

Model-based reinforcement learning algorithms with probabilistic dynamical models are amongst the most data-efficient learning methods. This is often attributed to their ability to distinguish between epistemic and aleatoric uncertainty. However, while most algorithms distinguish these two uncertainties for learning the model, they ignore it when optimizing the policy, which leads to greedy and insufficient exploration. At the same time, there are no practical solvers for optimistic exploration algorithms. In this paper, we propose a practical optimistic exploration algorithm (H-UCRL). H-UCRL reparameterizes the set of plausible models and hallucinates control directly on the epistemic uncertainty. By augmenting the input space with the hallucinated inputs, H-UCRL can be solved using standard greedy planners. Furthermore, we analyze H-UCRL and construct a general regret bound for well-calibrated models, which is provably sublinear in the case of Gaussian Process models. Based on this theoretical foundation, we show how optimistic exploration can be easily combined with state-of-the-art reinforcement learning algorithms and different probabilistic models. Our experiments demonstrate that optimistic exploration significantly speeds-up learning when there are penalties on actions, a setting that is notoriously difficult for existing model-based reinforcement learning algorithms.

Publication status

published

Book title

Advances in Neural Information Processing Systems 33

Journal / series

Volume

Pages / Article No.

14156 - 14170

Publisher

Curran

Event

34th Annual Conference on Neural Information Processing Systems (NeurIPS 2020)

Edition / version

Methods

Software

Geographic location

Date collected

Date created

Subject

Organisational unit

03908 - Krause, Andreas / Krause, Andreas check_circle

Notes

Due to the Coronavirus (COVID-19) the conference was conducted virtually.

Funding

815943 - Reliable Data-Driven Decision Making in Cyber-Physical Systems (EC)

Related publications and datasets