4 papers
Learning Stable Dynamical Systems for Visual Servoing
Antonio Paolillo, Matteo Saveriano
This work presents the dual benefit of integrating imitation learning techniques, based on the dynamical systems formalism, with the visual servoing paradigm. On the one hand, dyna…
Learning Descriptor of Constrained Task from Demonstration
Xiang Zhang, Matteo Saveriano, Justus Piater
Constrained objects, such as doors and drawers are often complex and share a similar structure in the human environment. A robot needs to interact accurately with constrained objec…
How do Offline Measures for Exploration in Reinforcement Learning behave?
Jakob J. Hollenstein, Sayantan Auddy, Matteo Saveriano +2
Sufficient exploration is paramount for the success of a reinforcement learning agent. Yet, exploration is rarely assessed in an algorithm-independent way. We compare the behavior…
Improving the Exploration of Deep Reinforcement Learning in Continuous Domains using Planning for Policy Search
Jakob J. Hollenstein, Erwan Renaudo, Matteo Saveriano +1
Local policy search is performed by most Deep Reinforcement Learning (D-RL) methods, which increases the risk of getting trapped in a local minimum. Furthermore, the availability o…