Structured Exploration via Hierarchical Variational Policy Networks

By Stephan Zheng, Yisong Yue. 2018

6 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

1. Tabish Rashid
2. Wendelin Böhmer
3. Shimon Whiteson
4. Christian Schröder de Witt
5. Anuj Mahajan
6. Mikayel Samvelyan
7. Tonghan Wang
8. Filippos Christianos

Citations in the corpus

• MAVEN: Multi-Agent Variational Exploration (2019, background): “[52] allow each agent to condition their policies on a shared continuous latent variable.”
• Exploration with Unreliable Intrinsic Reward in Multi-Agent Reinforcement Learning (2019, background): “First, estimating (2) is infeasible for MARL, as we would have to estimate one correlation matrix for each joint action u.”