Zobrazeno 1 - 10
of 60
pro vyhledávání: '"Waytowich, Nicholas R."'
The recent rapid advancement of machine learning has been driven by increasingly powerful models with the growing availability of training data and computational resources. However, real-time decision-making tasks with limited time and sparse learnin
Externí odkaz:
http://arxiv.org/abs/2410.15181
Recent advancements in large language models (LLMs) have expanded their capabilities beyond traditional text-based tasks to multimodal domains, integrating visual, auditory, and textual data. While multimodal LLMs have been extensively explored for h
Externí odkaz:
http://arxiv.org/abs/2408.15950
Publikováno v:
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2023
Spatial reasoning tasks in multi-agent environments such as event prediction, agent type identification, or missing data imputation are important for multiple applications (e.g., autonomous surveillance over sensor networks and subtasks for reinforce
Externí odkaz:
http://arxiv.org/abs/2401.04290
The development of plans of action in disaster response scenarios is a time-consuming process. Large Language Models (LLMs) offer a powerful solution to expedite this process through in-context learning. This study presents DisasterResponseGPT, an al
Externí odkaz:
http://arxiv.org/abs/2306.17271
Autor:
Ganesh, Prashant, Ramos, J. Humberto, Goecks, Vinicius G., Paquet, Jared, Longmire, Matthew, Waytowich, Nicholas R., Brink, Kevin
This paper describes a methodology for learning flight control systems from human demonstrations and interventions while considering the estimated uncertainty in the learned models. The proposed approach uses human demonstrations to train an initial
Externí odkaz:
http://arxiv.org/abs/2305.00929
Autor:
Thakur, Ravi Kumar, Sunbeam, MD-Nazmus Samin, Goecks, Vinicius G., Novoseller, Ellen, Bera, Ritwik, Lawhern, Vernon J., Gremillion, Gregory M., Valasek, John, Waytowich, Nicholas R.
Approaches for teaching learning agents via human demonstrations have been widely studied and successfully applied to multiple domains. However, the majority of imitation learning work utilizes only behavioral information from the demonstrator, i.e.
Externí odkaz:
http://arxiv.org/abs/2102.13008
Autor:
Bera, Ritwik, Goecks, Vinicius G., Gremillion, Gregory M., Valasek, John, Waytowich, Nicholas R.
Learning from demonstration has been widely studied in machine learning but becomes challenging when the demonstrated trajectories are unstructured and follow different objectives. This short-paper proposes PODNet, Plannable Option Discovery Network,
Externí odkaz:
http://arxiv.org/abs/1911.00171
Autor:
Goecks, Vinicius G., Gremillion, Gregory M., Lawhern, Vernon J., Valasek, John, Waytowich, Nicholas R.
This paper investigates how to efficiently transition and update policies, trained initially with demonstrations, using off-policy actor-critic reinforcement learning. It is well-known that techniques based on Learning from Demonstrations, for exampl
Externí odkaz:
http://arxiv.org/abs/1910.04281
Multi-agent reinforcement learning (MARL) extends (single-agent) reinforcement learning (RL) by introducing additional agents and (potentially) partial observability of the environment. Consequently, algorithms for solving MARL problems incorporate v
Externí odkaz:
http://arxiv.org/abs/1909.05232
Autor:
Prakash, Bharat, Horton, Mark, Waytowich, Nicholas R., Hairston, William David, Oates, Tim, Mohsenin, Tinoosh
In autonomous embedded systems, it is often vital to reduce the amount of actions taken in the real world and energy required to learn a policy. Training reinforcement learning agents from high dimensional image representations can be very expensive
Externí odkaz:
http://arxiv.org/abs/1903.10404