On the Practical Consistency of Meta-Reinforcement Learning Algorithms

Abstract

Consistency is the theoretical property of a meta learning algorithm that ensures that, under certain assumptions, it can adapt to any task at test time. An open question is whether and how theoretical consistency translates into practice, in comparison to inconsistent algorithms. In this paper, we empirically investigate this question on a set of representative meta-RL algorithms. We find that theoretically consistent algorithms can indeed usually adapt to out-of-distribution (OOD) tasks, while inconsistent ones cannot, although they can still fail in practice for reasons like poor exploration. We further find that theoretically inconsistent algorithms can be made consistent by continuing to update all agent components on the OOD tasks, and adapt as well or better than originally consistent ones. We conclude that theoretical consistency is indeed a desirable property, and inconsistent meta-RL algorithms can easily be made consistent to enjoy the same benefits.

References in corpus (9)

• Auto-Encoding Variational Bayes
• Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
• Learning to reinforcement learn
• Meta-Gradient Reinforcement Learning
• Fast Context Adaptation via Meta-Learning
• Evolved Policy Gradients
• Some Considerations on Learning to Explore via Meta-Reinforcement Learning
• Unsupervised Meta-Learning for Reinforcement Learning
• Meta-Reinforcement Learning Robust to Distributional Shift via Model Identification and Experience Relabeling