49 citations · 95 across the 13 of their papers we have counts for
3 papers · 1 filter
Sparse Markov Decision Processes with Causal Sparse Tsallis Entropy Regularization for Reinforcement Learning
Kyungjae Lee, Sungjoon Choi, Songhwai Oh
In this paper, a sparse Markov decision process (MDP) with novel causal sparse Tsallis entropy regularization is proposed.The proposed policy regularization induces a sparse and mu…
A Nonparametric Motion Flow Model for Human Robot Cooperation
Sungjoon Choi, Kyungjae Lee, H. Andy Park +1
In this paper, we present a novel nonparametric motion flow model that effectively describes a motion trajectory of a human and its application to human robot cooperation. To this…
Uncertainty-Aware Learning from Demonstration using Mixture Density Networks with Sampling-Free Variance Modeling
Sungjoon Choi, Kyungjae Lee, Sungbin Lim +1
In this paper, we propose an uncertainty-aware learning from demonstration method by presenting a novel uncertainty estimation method utilizing a mixture density network appropriat…