@inproceedings{huang2022towards,
author = {Huang, Jiawei and Chen, Jinglin and Zhao, Li and Qin, Tao and Jiang, Nan and Liu, Tie-Yan},
title = {Towards Deployment-Efficient Reinforcement Learning: Lower Bound and Optimality},
booktitle = {Tenth International Conference on Learning Representations(ICLR)},
year = {2022},
month = {April},
abstract = {Deployment efficiency is an important criterion for many real-world applications of reinforcement learning (RL). Despite the community's increasing interest, there lacks a formal theoretical formulation for the problem. In this paper, we propose such a formulation for deployment-efficient RL (DE-RL) from an ''optimization with constraints'' perspective: we are interested in exploring an MDP and obtaining a near-optimal policy within minimal \emph[deployment complexity], whereas in each deployment the policy can sample a large batch of data. Using finite-horizon linear MDPs as a concrete structural model, we reveal the fundamental limit in achieving deployment efficiency by establishing information-theoretic lower bounds, and provide algorithms that achieve the optimal deployment efficiency. Moreover, our formulation for DE-RL is flexible and can serve as a building block for other practically relevant settings; we give ''Safe DE-RL'' and ''Sample-Efficient DE-RL'' as two examples, which may be worth future investigation.},
url = {http://approjects.co.za/?big=en-us/research/publication/towards-deployment-efficient-reinforcement-learning-lower-bound-and-optimality/},
}