About this document

Hierarchical Deep Reinforcement Learning by udayreddy.kaipa is a document available to read on EtoBox.

The document presents a framework called hierarchical-DQN (h-DQN) that integrates hierarchical value functions with intrinsically motivated deep reinforcement learning to address the challenge of learning goal-directed behavior in environments with sparse feedback. It proposes a two-level hierarchy where a meta-controller selects intrinsic goals and a controller executes actions to achieve those goals, enhancing exploration efficiency. The effectiveness of h-DQN is demonstrated through applications in compl

Author

udayreddy.kaipa

Language

EN