180 citations · 601 across the 46 of their papers we have counts for
6 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…
Asynchronous Actor-Critic for Multi-Agent Reinforcement Learning
Yuchen Xiao, Weihao Tan, Christopher Amato
Synchronizing decisions across multiple agents in realistic settings is problematic since it requires agents to wait for other agents to terminate and communicate about termination…
Deep Transformer Q-Networks for Partially Observable Reinforcement Learning
Kevin Esslinger, Robert Platt, Christopher Amato
Real-world reinforcement learning tasks often involve some form of partial observability where the observations only give a partial or noisy view of the true state of the world. Su…
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…
BADDr: Bayes-Adaptive Deep Dropout RL for POMDPs
Sammie Katt, Hai Nguyen, Frans A. Oliehoek +1
While reinforcement learning (RL) has made great advances in scalability, exploration and partial observability are still active research topics. In contrast, Bayesian RL (BRL) pro…
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…