SplAgger: Split Aggregation for Meta-Reinforcement Learning

arXiv:2403.03020v1 Announce Type: new
Abstract: A core ambition of reinforcement learning (RL) is the creation of agents capable of rapid learning in novel tasks. Meta-RL aims to achieve this by directly learning such agents. One category of meta-RL methods, called black box methods, does so by training off-the-shelf sequence models end-to-end. In contrast, another category of methods have been developed that explicitly infer a posterior distribution over the unknown task. These methods generally have distinct objectives and sequence models designed …

abstract agents aggregation arxiv black box box contrast core cs.ai cs.lg meta novel reinforcement reinforcement learning tasks training type