5 papers
Static Is Not Enough: A Comparative Study of VR and SpaceMouse in Static and Dynamic Teleoperation Tasks
Yijun Zhou, Muhan Hou, Kim Baraka
Imitation learning relies on high-quality demonstrations, and teleoperation is a primary way to collect them, making teleoperation interface choice crucial for the data. Prior work…
Can you see how I learn? Human observers' inferences about Reinforcement Learning agents' learning processes
Bernhard Hilpert, Muhan Hou, Kim Baraka +1
Reinforcement Learning (RL) agents often exhibit learning behaviors that are not intuitively interpretable by human observers, which can result in suboptimal feedback in collaborat…
Robot Policy Transfer with Online Demonstrations: An Active Reinforcement Learning Approach
Muhan Hou, Koen Hindriks, A. E. Eiben +1
Transfer Learning (TL) is a powerful tool that enables robots to transfer learned policies across different environments, tasks, or embodiments. To further facilitate this process,…
Active Robot Curriculum Learning from Online Human Demonstrations
Muhan Hou, Koen Hindriks, A. E. Eiben +1
Learning from Demonstrations (LfD) allows robots to learn skills from human users, but its effectiveness can suffer due to sub-optimal teaching, especially from untrained demonstra…
"Give Me an Example Like This": Episodic Active Reinforcement Learning from Demonstrations
Muhan Hou, Koen Hindriks, A. E. Eiben +1
Reinforcement Learning (RL) has achieved great success in sequential decision-making problems, but often at the cost of a large number of agent-environment interactions. To improve…