Deep Reinforcement Learning with Task-Adaptive Retrieval via Hypernetwork

arXiv:2306.10698v5 Announce Type: replace
Abstract: Deep reinforcement learning algorithms are usually impeded by sampling inefficiency, heavily depending on multiple interactions with the environment to acquire accurate decision-making capabilities. In contrast, humans rely on their hippocampus to retrieve relevant information from past experiences of relevant tasks, which guides their decision-making when learning a new task, rather than exclusively depending on environmental interactions. Nevertheless, designing a hippocampus-like module for an agent to incorporate past experiences into established reinforcement learning algorithms presents two …

abstract algorithms arxiv capabilities contrast cs.ai cs.lg decision environment guides humans information interactions making multiple reinforcement reinforcement learning retrieval sampling tasks the environment type via