OPAL: Offline Primitive Discovery for Accelerating Offline Reinforcement Learning

Abstract

Reinforcement learning (RL) has achieved impressive performance in a variety of online settings in which an agent's ability to query the environment for transitions and rewards is effectively unlimited. However, in many practical applications, the situation is reversed: an agent may have access to large amounts of undirected offline experience data, while access to the online environment is severely limited. In this work, we focus on this offline setting. Our main insight is that, when presented with offline data composed of a variety of behaviors, an effective way to leverage this data is to extract a continuous space of recurring and temporally extended primitive behaviors before using these primitives for downstream task learning. Primitives extracted in this way serve two purposes: they delineate the behaviors that are supported by the data from those that are not, making them useful for avoiding distributional shift in offline RL; and they provide a degree of temporal abstraction, which reduces the effective horizon yielding better learning in theory, and improved offline RL in practice. In addition to benefiting offline policy optimization, we show that performing offline primitive learning in this way can also be leveraged for improving few-shot imitation learning as well as exploration and transfer in online RL on a variety of benchmark domains. Visualizations are available at https://sites.google.com/view/opal-iclr

https://sites.google.com/view/opal-iclr

References in corpus (7)

• Conservative Q-Learning for Offline Reinforcement Learning
• Challenges of Real-World Reinforcement Learning
• Behavior Regularized Offline Reinforcement Learning
• Way Off-Policy Batch Deep Reinforcement Learning of Implicit Human Preferences in Dialog
• Deployment-Efficient Reinforcement Learning via Model-Based Offline Optimization
• Unsupervised Curricula for Visual Meta-Reinforcement Learning
• DDCO: Discovery of Deep Continuous Options for Robot Learning from Demonstrations

Cited by in corpus (8)

• On the Opportunities and Risks of Foundation Models
• Decision Transformer: Reinforcement Learning via Sequence Modeling
• What Matters in Learning from Offline Human Demonstrations for Robot Manipulation
• Representation Matters: Offline Pretraining for Sequential Decision Making
• Demonstration-Guided Reinforcement Learning with Learned Skills
• Provable Representation Learning for Imitation with Contrastive Fourier Features
• TRAIL: Near-Optimal Imitation Learning with Suboptimal Data
• S4RL: Surprisingly Simple Self-Supervision for Offline Reinforcement Learning