Risk-Sensitive Reinforcement Learning

By Oliver Mihatsch, Ralph Neuneier. 1998

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

1. Victoria Krakovna
2. Medhi Bennis
3. Merouane Debbah
4. Tom Everitt
5. Miljan Martic
6. Shane Legg
7. Jun Morimoto
8. Laurent Orseau

Citations in the corpus

• Measuring and avoiding side effects using relative reachability (2018, background): “, 2016), penalizing risk (Chow et al., 2015; Mihatsch and Neuneier, 2002), preserving ergodicity (Moldovan and Abbeel, 2012; Eysenbach et al.”
• Ultra-Reliable Communication in 5G mmWave Networks: A Risk-Sensitive Approach (2018, methodology): “ble communication (URC). The prime motivation behind using RSL stems from the fact that the risk-sensitive utility function to be optimized is a function of not only the average but also the variance [6], and thus it captures the tail of rate distribution to enable URC. While our proposed algorithm ”
• Nonparametric Representation of Policies and Value Functions: A Trajectory-Based Approach (2002, background): “This is closely related to robust nonlinear controller design techniques based on the idea of control [11, 12] and risk sensitive control [13, 14].”