RL$^3$: Boosting Meta Reinforcement Learning via RL inside RL$^2$

arXiv:2306.15909v4 Announce Type: replace
Abstract: Meta reinforcement learning (meta-RL) methods such as RL$^2$ have emerged as promising approaches for learning data-efficient RL algorithms tailored to a given task distribution. However, they show poor asymptotic performance and struggle with out-of-distribution tasks because they rely on sequence models, such as recurrent neural networks or transformers, to process experiences rather than summarize them using general-purpose RL components such as value functions. In contrast, traditional RL algorithms are data-inefficient as they do not use …

abstract algorithms arxiv boosting cs.ai cs.lg data distribution however inside meta networks neural networks performance recurrent neural networks reinforcement reinforcement learning show struggle tasks type via