HAVEN combines a transformer-based high-level subgoal selector with a low-level controller to improve safe navigation by exploiting visibility and cover in uncertain environments.
Deep transformer q-networks for partially observable reinforcement learning
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
A survey of Transformer-enhanced reinforcement learning fundamentals and applications in communication networks covering resource allocation, computation offloading, routing, trajectory control, and security.
citing papers explorer
-
HAVEN: Hierarchical Adversary-aware Visibility-Enabled Navigation with Cover Utilization using Deep Transformer Q-Networks
HAVEN combines a transformer-based high-level subgoal selector with a low-level controller to improve safe navigation by exploiting visibility and cover in uncertain environments.
-
Transformer-Enhanced Reinforcement Learning: Fundamentals and Applications in Communication Networks
A survey of Transformer-enhanced reinforcement learning fundamentals and applications in communication networks covering resource allocation, computation offloading, routing, trajectory control, and security.