On the Practical Consistency of Meta-Reinforcement Learning Algorithms
This addresses the practical relevance of theoretical guarantees in meta-RL for researchers and practitioners, showing incremental improvements in algorithm design.
The paper investigates whether theoretically consistent meta-reinforcement learning algorithms adapt better to out-of-distribution tasks than inconsistent ones, finding that consistent algorithms usually succeed while inconsistent ones can be made consistent by updating all agent components, achieving similar or better adaptation.
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.