55 citations · 68 across the 4 of their papers we have counts for
5 papers
Memory-based Deep Reinforcement Learning for POMDPs
Lingheng Meng, Rob Gorbet, Dana Kulić
A promising characteristic of Deep Reinforcement Learning (DRL) is its capability to learn optimal policy in an end-to-end manner without relying on feature engineering. However, m…
Fast Approximate Multi-output Gaussian Processes
Vladimir Joukov, Dana Kulić
Gaussian processes regression models are an appealing machine learning method as they learn expressive non-linear models from exemplar data with minimal parameter tuning and estima…
The Effect of Multi-step Methods on Overestimation in Deep Reinforcement Learning
Lingheng Meng, Rob Gorbet, Dana Kulić
Multi-step (also called n-step) methods in reinforcement learning (RL) have been shown to be more efficient than the 1-step method due to faster propagation of the reward signal, b…
Supportive Actions for Manipulation in Human-Robot Coworker Teams
Shray Bansal, Rhys Newbury, Wesley Chan +5
The increasing presence of robots alongside humans, such as in human-robot teams in manufacturing, gives rise to research questions about the kind of behaviors people prefer in the…
Inverse Optimal Control from Incomplete Trajectory Observations
Wanxin Jin, Dana Kulić, Shaoshuai Mou +1
This article develops a methodology that enables learning an objective function of an optimal control system from incomplete trajectory observations. The objective function is assu…