Deployment-Efficient Reinforcement Learning via Model-Based Offline Optimization

Abstract

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. Codes and pre-trained models are available at https://github.com/matsuolab/BREMEN .

References in corpus (11)

• Rainbow: Combining Improvements in Deep Reinforcement Learning
• Massively Parallel Methods for Deep Reinforcement Learning
• Behavior Regularized Offline Reinforcement Learning
• Benchmarking Model-Based Reinforcement Learning
• Benchmarking Batch Deep Reinforcement Learning Algorithms
• Lyapunov-based Safe Policy Optimization for Continuous Control
• Way Off-Policy Batch Deep Reinforcement Learning of Implicit Human Preferences in Dialog
• Risk-Sensitive and Robust Decision-Making: a CVaR Optimization Approach
• Generalization in Deep Networks: The Role of Distance from Initialization
• Off-Policy Policy Gradient with State Distribution Correction
• SEED RL: Scalable and Efficient Deep-RL with Accelerated Central Inference