2 citations · 8 across the 12 of their papers we have counts for
3 papers · 1 filter
Leveraging Fully Observable Policies for Learning under Partial Observability
Hai Nguyen, Andrea Baisero, Dian Wang +2
Reinforcement learning in partially observable domains is challenging due to the lack of observable state information. Thankfully, learning offline in a simulator with such state i…
Hierarchical Reinforcement Learning under Mixed Observability
Hai Nguyen, Zhihan Yang, Andrea Baisero +3
The framework of mixed observable Markov decision processes (MOMDP) models many robotic domains in which some state variables are fully observable while others are not. In this wor…
A Deeper Understanding of State-Based Critics in Multi-Agent Reinforcement Learning
Xueguang Lyu, Andrea Baisero, Yuchen Xiao +1
Centralized Training for Decentralized Execution, where training is done in a centralized offline fashion, has become a popular solution paradigm in Multi-Agent Reinforcement Learn…