Zobrazeno 1 - 10
of 532
pro vyhledávání: '"Zavlanos A"'
Autor:
Konti, Xenia, Riess, Hans, Giannopoulos, Manos, Shen, Yi, Pencina, Michael J., Economou-Zavlanos, Nicoleta J., Zavlanos, Michael M.
In this paper, we address the challenge of heterogeneous data distributions in cross-silo federated learning by introducing a novel algorithm, which we term Cross-silo Robust Clustered Federated Learning (CS-RCFL). Our approach leverages the Wasserst
Externí odkaz:
http://arxiv.org/abs/2410.07039
In this paper, we consider a transfer reinforcement learning problem involving agents with different action spaces. Specifically, for any new unseen task, the goal is to use a successful demonstration of this task by an expert agent in its action spa
Externí odkaz:
http://arxiv.org/abs/2410.14484
Autor:
Sivakumar, Kavinayan P., Shen, Yi, Bell, Zachary, Nivison, Scott, Chen, Boyuan, Zavlanos, Michael M.
In this paper, we study an inverse reinforcement learning problem that involves learning the reward function of a learning agent using trajectory data collected while this agent is learning its optimal policy. To address this problem, we propose an i
Externí odkaz:
http://arxiv.org/abs/2410.14135
Vision-based imitation learning has shown promising capabilities of endowing robots with various motion skills given visual observation. However, current visuomotor policies fail to adapt to drastic changes in their visual observations. We present Pe
Externí odkaz:
http://arxiv.org/abs/2406.19971
Autor:
Wang, Siyi, Wang, Zifan, Yi, Xinlei, Zavlanos, Michael M., Johansson, Karl H., Hirche, Sandra
Considering non-stationary environments in online optimization enables decision-maker to effectively adapt to changes and improve its performance over time. In such cases, it is favorable to adopt a strategy that minimizes the negative impact of chan
Externí odkaz:
http://arxiv.org/abs/2404.02988
This paper considers risk-averse learning in convex games involving multiple agents that aim to minimize their individual risk of incurring significantly high costs. Specifically, the agents adopt the conditional value at risk (CVaR) as a risk measur
Externí odkaz:
http://arxiv.org/abs/2403.10399
The path signature, having enjoyed recent success in the machine learning community, is a theoretically-driven method for engineering features from irregular paths. On the other hand, graph neural networks (GNN), neural architectures for processing d
Externí odkaz:
http://arxiv.org/abs/2402.03558
Autor:
Wang, Zifan, Gao, Yulong, Wang, Siyi, Zavlanos, Michael M., Abate, Alessandro, Johansson, Karl H.
Distributional reinforcement learning (DRL) enhances the understanding of the effects of the randomness in the environment by letting agents learn the distribution of a random return, rather than its expected value as in standard reinforcement learni
Externí odkaz:
http://arxiv.org/abs/2401.10240
In this paper we deal with stochastic optimization problems where the data distributions change in response to the decision variables. Traditionally, the study of optimization problems with decision-dependent distributions has assumed either the abse
Externí odkaz:
http://arxiv.org/abs/2310.02384
Autor:
Riess, Hans, Henselman-Petrusek, Gregory, Munger, Michael C., Ghrist, Robert, Bell, Zachary I., Zavlanos, Michael M.
Preferences, fundamental in all forms of strategic behavior and collective decision-making, in their raw form, are an abstract ordering on a set of alternatives. Agents, we assume, revise their preferences as they gain more information about other ag
Externí odkaz:
http://arxiv.org/abs/2310.00179