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 (21)

• Trust Region Policy Optimization
• Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems
• Rainbow: Combining Improvements in Deep Reinforcement Learning
• Massively Parallel Methods for Deep Reinforcement Learning
• Continuous Deep Q-Learning with Model-based Acceleration
• Data-Efficient Hierarchical Reinforcement Learning
• Behavior Regularized Offline Reinforcement Learning
• MOPO: Model-based Offline Policy Optimization
• Benchmarking Model-Based Reinforcement Learning
• Benchmarking Batch Deep Reinforcement Learning Algorithms
• MOReL : Model-Based Offline Reinforcement Learning
• Lyapunov-based Safe Policy Optimization for Continuous Control
• Way Off-Policy Batch Deep Reinforcement Learning of Implicit Human Preferences in Dialog
• Model-Based Reinforcement Learning via Meta-Policy Optimization
• Risk-Sensitive and Robust Decision-Making: a CVaR Optimization Approach
• Evaluating Reinforcement Learning Algorithms in Observational Health Settings
• A Game Theoretic Framework for Model Based Reinforcement Learning
• 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
• Multi-Agent Manipulation via Locomotion using Hierarchical Sim2Real

Cited by in corpus (24)

• A Minimalist Approach to Offline Reinforcement Learning
• COMBO: Conservative Offline Model-Based Policy Optimization
• Online and Offline Reinforcement Learning by Planning with a Learned Model
• Offline Reinforcement Learning with Fisher Divergence Critic Regularization
• Representation Matters: Offline Pretraining for Sequential Decision Making
• Offline Reinforcement Learning with Reverse Model-based Imagination
• Model-Based Offline Planning
• Offline Reinforcement Learning from Images with Latent Space Models
• Policy Finetuning: Bridging Sample-Efficient Offline and Online Reinforcement Learning
• OPAL: Offline Primitive Discovery for Accelerating Offline Reinforcement Learning
• A Survey of Reinforcement Learning for Optimization in Automation
• Offline-to-Online Reinforcement Learning via Balanced Replay and Pessimistic Q-Ensemble
• Behavioral Priors and Dynamics Models: Improving Performance and Domain Transfer in Offline RL
• Autoregressive Dynamics Models for Offline Policy Evaluation and Optimization
• ACL-QL: Adaptive Conservative Level in Q-Learning for Offline Reinforcement Learning
• EMaQ: Expected-Max Q-Learning Operator for Simple Yet Effective Offline and Online RL
• Mitigating Covariate Shift in Imitation Learning via Offline Data Without Great Coverage
• Pessimistic Model-based Offline Reinforcement Learning under Partial Coverage
• MUSBO: Model-based Uncertainty Regularized and Sample Efficient Batch Optimization for Deployment Constrained Reinforcement Learning
• Conservative Data Sharing for Multi-Task Offline Reinforcement Learning
• Detecting Rewards Deterioration in Episodic Reinforcement Learning
• Discovering an Aid Policy to Minimize Student Evasion Using Offline Reinforcement Learning
• Learning Off-Policy with Online Planning
• The Difficulty of Passive Learning in Deep Reinforcement Learning