3 citations · 6 across the 7 of their papers we have counts for
Showing 2022Show all
3 papers · 1 filter
cs.LG2022
Spatial-temporal recurrent reinforcement learning for autonomous ships
Martin Waltz, Ostap Okhrin
This paper proposes a spatial-temporal recurrent neural network architecture for deep -networks that can be used to steer an autonomous ship. The network design makes it possibl…
q-fin.GN2022
Vulnerability-CoVaR: Investigating the Crypto-market
Martin Waltz, Abhay Kumar Singh, Ostap Okhrin
This paper proposes an important extension to Conditional Value-at-Risk (CoVaR), the popular systemic risk measure, and investigates its properties on the cryptocurrency market. Th…
cs.LG2022★ 1 cited
Addressing Maximization Bias in Reinforcement Learning with Two-Sample Testing
Martin Waltz, Ostap Okhrin
Value-based reinforcement-learning algorithms have shown strong results in games, robotics, and other real-world applications. Overestimation bias is a known threat to those algori…