Closed-Loop Learning of Visual Control Policies
نویسندگان
چکیده
منابع مشابه
Closed-Loop Learning of Visual Control Policies
In this dissertation, I introduce a general, flexible framework for learning direct mappings from images to actions in an agent that interacts with its surrounding environment. This work is motivated by the paradigm of purposive vision. The original contributions consist in the design of reinforcement learning algorithms that are applicable to visual spaces. Inspired by the paradigm of local-ap...
متن کاملLearning open-loop from closed-loop control
This paper explores an evolution from closed-loop control to open-loop control for a planar manipula-tor. A reinforcement learning strategy is used to learn the open-loop commands from the closed-loop control. The goal is to produce a motion using purely open-loop control strategy, thereby eliminating the need for inter-link communication and on-line control computations. Initially closed loop ...
متن کاملHigh-Performance Visual Closed-Loop Robot Control
This thesis addresses the use of monocular eye-in-hand machine vision to control the position of a robot manipulator for dynamically challenging tasks. Such tasks are defined as those where the robot motion required approaches or exceeds the performance limits stated by the manufacturer. Computer vision systems have been used for robot control for over two decades now, but have rarely been used...
متن کاملLearning Parametric Closed-Loop Policies for Markov Potential Games
Multiagent systems where the agents interact among themselves and with an stochastic environment can be formalized as stochastic games. We study a subclass, named Markov potential games (MPGs), that appear often in economic and engineering applications when the agents share some common resource. We consider MPGs with continuous state-action variables, coupled constraints and nonconvex rewards. ...
متن کاملReinforcement Learning for Mixed Open-loop and Closed-loop Control
Closed-loop control relies on sensory feedback that is usually assumed to be free . But if sensing incurs a cost, it may be costeffective to take sequences of actions in open-loop mode. We describe a reinforcement learning algorithm that learns to combine open-loop and closed-loop control when sensing incurs a cost. Although we assume reliable sensors, use of open-loop control means that action...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Journal of Artificial Intelligence Research
سال: 2007
ISSN: 1076-9757
DOI: 10.1613/jair.2110