5 papers
Heterogeneous Policy Networks for Composite Robot Team Communication and Coordination
Esmaeil Seraj, Rohan Paleja, Luis Pimentel +7
High-performing human-human teams learn intelligent and efficient communication and coordination strategies to maximize their joint utility. These teams implicitly understand the d…
Interactive Distillation for Cooperative Multi-Agent Reinforcement Learning
Minwoo Cho, Batuhan Altundas, Matthew Gombolay
Knowledge distillation (KD) has the potential to accelerate MARL by employing a centralized teacher for decentralized students but faces key bottlenecks. Specifically, there are (1…
Towards Automated Semantic Interpretability in Reinforcement Learning via Vision-Language Models
Zhaoxin Li, Zhang Xi-Jia, Batuhan Altundas +3
Semantic interpretability in Reinforcement Learning (RL) enables transparency and verifiability of decision-making. Achieving semantic interpretability in reinforcement learning re…
Model-Agnostic Policy Explanations with Large Language Models
Zhang Xi-Jia, Yue Guo, Shufei Chen +4
Intelligent agents, such as robots, are increasingly deployed in real-world, human-centric environments. To foster appropriate human trust and meet legal and ethical standards, the…
Asynchronous Training of Mixed-Role Human Actors in a Partially-Observable Environment
Kimberlee Chestnut Chang, Reed Jensen, Rohan Paleja +7
In cooperative training, humans within a team coordinate on complex tasks, building mental models of their teammates and learning to adapt to teammates' actions in real-time. To re…