Jürgen T. Hahn

2 accepted papers

2016

Risk-sensitive decision making via constrained expected returns

ICASSP 2016accepted

Decision making based on Markov decision processes (MDPs) is an emerging research area as MDPs provide a convenient formalism to learn an optimal behavior in terms of a given reward. In many applications there are critical states that might harm the agent or the environment and should therefore be a…

Cited by 0 Source ↗Scholar ↗

2015

Inverse Reinforcement Learning using Expectation Maximization in mixture models

Jürgen T. Hahn, Abdelhak M. Zoubir

ICASSP 2015accepted

Reinforcement Learning (RL) is an attractive tool for learning optimal controllers in the sense of a given reward function. In conventional RL, usually an expert is required to design the reward function as the efficiency of RL strongly depends on the latter. An alternative has been presented by the…

Cited by 0 Source ↗Scholar ↗