Environmentally Adaptive Control Policies for Expensive Systems
نویسندگان
چکیده
Running experiments on physical robotic systems typically requires significant resources (personnel, time, and money), restricting the number that can be run during training. Additionally, these systems typically operate over a range of external conditions and can be highly non-linear. We focus on the problem of learning a globally optimal policy to adapt controllers for such systems based on the value of these external conditions in order to maximize expected performance. We propose two novel myopic search methods for this problem, and present results comparing these algorithms with various other approaches. Finally, we use these methods to train both simulated and physical snake robots to automatically adapt to changing terrain.
منابع مشابه
Adaptive Policies for Reducing Inequalities in the Social Determinants of Health
Inequalities in the social determinants of health (SDH), which drive avoidable health disparities between different individuals or groups, is a major concern for a number of international organisations, including the World Health Organization (WHO). Despite this, the pathways to changing inequalities in the SDH remain elusive. The methodologies and concepts within system science are now viewed ...
متن کاملADAPTIVE FUZZY TRACKING CONTROL FOR A CLASS OF NONLINEAR SYSTEMS WITH UNKNOWN DISTRIBUTED TIME-VARYING DELAYS AND UNKNOWN CONTROL DIRECTIONS
In this paper, an adaptive fuzzy control scheme is proposed for a class of perturbed strict-feedback nonlinear systems with unknown discrete and distributed time-varying delays, and the proposed design method does not require a priori knowledge of the signs of the control gains.Based on the backstepping technique, the adaptive fuzzy controller is constructed. The main contributions of the paper...
متن کاملADAPTIVE FUZZY OUTPUT FEEDBACK TRACKING CONTROL FOR A CLASS OF NONLINEAR TIME-VARYING DELAY SYSTEMS WITH UNKNOWN BACKLASH-LIKE HYSTERESIS
This paper considers the problem of adaptive output feedback tracking control for a class of nonstrict-feedback nonlinear systems with unknown time-varying delays and unknown backlash-like hysteresis. Fuzzy logic systems are used to estimate the unknown nonlinear functions. Based on the Lyapunov–Krasovskii method, the control scheme is constructed by using the backstepping and adaptive techniqu...
متن کاملAn economic-statistical model for production and maintenance planning under adaptive non-central chi-square control chart
Most of the inventory control models assume that quality defect never happens, which means production process is perfect. However, in real manufacturing processes, the production process starts its operation in the in-control state; but after a period of time, shifts to the out-of-control state because of occurrence of some disturbances. In this paper, in order to approach the model to real man...
متن کاملVehicle Stabilization via a Self-Tuning Optimal Controller
Nowadays, using advanced vehicle control and safety systems in vehicles is growing rapidly. In this regard, in recent years new control systems, called VDC, have been introduced. These systems stabilize vehicle yaw motion, by yaw moment resulted from tire controlling forces. In this paper, an adaptive optimal controller applied to a vehicle to obtain a satisfactory lateral and yaw stability. To...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2012