Zobrazeno 1 - 10
of 30
pro vyhledávání: '"Aljalbout, Elie"'
Most recent successes in robot reinforcement learning involve learning a specialized single-task agent. However, robots capable of performing multiple tasks can be much more valuable in real-world applications. Multi-task reinforcement learning can b
Externí odkaz:
http://arxiv.org/abs/2407.13466
Robotic manipulation requires accurate motion and physical interaction control. However, current robot learning approaches focus on motion-centric action spaces that do not explicitly give the policy control over the interaction. In this paper, we di
Externí odkaz:
http://arxiv.org/abs/2407.02904
Autor:
Chen, Nutan, Cseke, Botond, Aljalbout, Elie, Paraschos, Alexandros, Alles, Marvin, van der Smagt, Patrick
We present a novel motion generation approach for robot arms, with high degrees of freedom, in complex settings that can adapt online to obstacles or new via points. Learning from Demonstration facilitates rapid adaptation to new tasks and optimizes
Externí odkaz:
http://arxiv.org/abs/2403.15239
We study the choice of action space in robot manipulation learning and sim-to-real transfer. We define metrics that assess the performance, and examine the emerging properties in the different action spaces. We train over 250 reinforcement learning~(
Externí odkaz:
http://arxiv.org/abs/2312.03673
Multi-robot manipulation tasks involve various control entities that can be separated into dynamically independent parts. A typical example of such real-world tasks is dual-arm manipulation. Learning to naively solve such tasks with reinforcement lea
Externí odkaz:
http://arxiv.org/abs/2211.15824
Intelligent agents must be able to think fast and slow to perform elaborate manipulation tasks. Reinforcement Learning (RL) has led to many promising results on a range of challenging decision-making tasks. However, in real-world robotics, these meth
Externí odkaz:
http://arxiv.org/abs/2110.09904
Autor:
Aljalbout, Elie
Robot learning is a very promising topic for the future of automation and machine intelligence. Future robots should be able to autonomously acquire skills, learn to represent their environment, and interact with it. While these topics have been expl
Externí odkaz:
http://arxiv.org/abs/2110.08066
Autor:
Alles, Marvin, Aljalbout, Elie
Robotic manipulators are widely used in modern manufacturing processes. However, their deployment in unstructured environments remains an open problem. To deal with the variety, complexity, and uncertainty of real-world manipulation tasks, it is esse
Externí odkaz:
http://arxiv.org/abs/2110.04003
Vision-based reinforcement learning (RL) is a promising approach to solve control tasks involving images as the main observation. State-of-the-art RL algorithms still struggle in terms of sample efficiency, especially when using image observations. T
Externí odkaz:
http://arxiv.org/abs/2110.00784
Vision-based reinforcement learning (RL) is a promising technique to solve control tasks involving images as the main observation. State-of-the-art RL algorithms still struggle in terms of sample efficiency, especially when using image observations.
Externí odkaz:
http://arxiv.org/abs/2109.13588