The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
In this paper, reinforcement learning approach to motion control of 2-link planer underactuated manipulator is described. This manipulator has one passive joint and is difficult to control. The experiments of learning to control this manipulator by RL and human are executed. Using the experimental results, the associations between RL and human learning are considered.
On reinforcement learning researches, even though environments have continuous state space, many RL algorithms are assumed to be on a discrete state space. Typically, most approaches which treat continuous state and action spaces, just discretise these spaces. In this paper, to treat the continuous state space, we propose a RL algorithm which based on the locally weighted regression.
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.