3 papers
cs.RO2024
Optimizing Sensor Redundancy in Sequential Decision-Making Problems
Jonas Nüßlein, Maximilian Zorn, Fabian Ritz +5
Reinforcement Learning (RL) policies are designed to predict actions based on current observations to maximize cumulative future rewards. In real-world applications (i.e., non-simu…
cs.NE2024
Finding Strong Lottery Ticket Networks with Genetic Algorithms
Philipp Altmann, Julian Schönberger, Maximilian Zorn +1
According to the Strong Lottery Ticket Hypothesis, every sufficiently large neural network with randomly initialized weights contains a sub-network which - still with its random we…
cs.MA2024
Emergence in Multi-Agent Systems: A Safety Perspective
Philipp Altmann, Julian Schönberger, Steffen Illium +5
Emergent effects can arise in multi-agent systems (MAS) where execution is decentralized and reliant on local information. These effects may range from minor deviations in behavior…