DeepAI AI Chat
Log In Sign Up

Deployment-Efficient Reinforcement Learning via Model-Based Offline Optimization

by   Tatsuya Matsushima, et al.
The University of Tokyo

Most reinforcement learning (RL) algorithms assume online access to the environment, in which one may readily interleave updates to the policy with experience collection using that policy. However, in many real-world applications such as health, education, dialogue agents, and robotics, the cost or potential risk of deploying a new data-collection policy is high, to the point that it can become prohibitive to update the data-collection policy more than a few times during learning. With this view, we propose a novel concept of deployment efficiency, measuring the number of distinct data-collection policies that are used during policy learning. We observe that naïvely applying existing model-free offline RL algorithms recursively does not lead to a practical deployment-efficient and sample-efficient algorithm. We propose a novel model-based algorithm, Behavior-Regularized Model-ENsemble (BREMEN) that can effectively optimize a policy offline using 10-20 times fewer data than prior works. Furthermore, the recursive application of BREMEN is able to achieve impressive deployment efficiency while maintaining the same or better sample efficiency, learning successful policies from scratch on simulated robotic environments with only 5-10 deployments, compared to typical values of hundreds to millions in standard RL baselines.


page 13

page 18


MOORe: Model-based Offline-to-Online Reinforcement Learning

With the success of offline reinforcement learning (RL), offline trained...

Launchpad: Learning to Schedule Using Offline and Online RL Methods

Deep reinforcement learning algorithms have succeeded in several challen...

Marginalized Importance Sampling for Off-Environment Policy Evaluation

Reinforcement Learning (RL) methods are typically sample-inefficient, ma...

Hierarchical Reinforcement Learning with Optimal Level Synchronization based on a Deep Generative Model

The high-dimensional or sparse reward task of a reinforcement learning (...

Policy Resilience to Environment Poisoning Attacks on Reinforcement Learning

This paper investigates policy resilience to training-environment poison...

Robust On-Policy Data Collection for Data-Efficient Policy Evaluation

This paper considers how to complement offline reinforcement learning (R...