Browsing by Subject "reinforcement learning"
Now showing items 1-17 of 17
-
(2020-03-30)The game of cops and robbers is a multi-agent adversarial game played on graphs. Previous research on agent strategies for this game has focused on designing heuristics for minimax strategies and often imposes strict ...
-
(2021-12-07)Conventional autonomous navigation framework for mobile robots is highly modularized with various subsystems such as localization, perception, mapping, planning and control. Although these provide easy interpretation, they ...
-
Discretization and Approximation Methods for Reinforcement Learning of Highly Reconfigurable Systems (2010-07-14)There are a number of techniques that are used to solve reinforcement learning problems, but very few that have been developed for and tested on highly reconfigurable systems cast as reinforcement learning problems. ...
-
Enhanced Reinforcement Learning with Attentional Feedback and Temporally Attenuated Distal Rewards (2015-08-09)This thesis presents a new reinforcement learning mechanism suitable to be employed in artificial spiking neural networks of leaky integrate-and-fire (LIF) or Izhikevich neurons. The proposed mechanism is upgraded from, ...
-
(2023-04-19)Federated learning aims to solve a global optimization problem by collectively learning from a group of clients without sharing data they possess. In offline reinforcement learning, an agent aims to learn an optimal policy ...
-
(2016-08-04)Every motion made by a moving object is either planned implicitly, e.g., human natural movement from one point to another, or explicitly, e.g., pre-planned information about where a robot should move in a room to effectively ...
-
(2023-07-23)We study the usage of information-theoretic measures in learning problems. The first problem considered is the algorithm-dependent generalization error bound. Conceptually, the mutual information between the output of ...
-
(2022-09-26)This research studies the network traffic signal control problem. It uses the Lyapunov control function to derive the back pressure method, which is equal to differential queue lengths weighted by intersection lane flows. ...
-
(2018-08-08)Energy and food crisis are two major problems that our human society has to face in the 21st century. With the world’s population reaching 7.62 billion as of May 2018, both electric power and agricultural industries turn ...
-
(2022-08-22)This work examines the application of multi-agent reinforcement learning (MARL) for production scheduling in a real-world two-stage chemical production system found in industry. Improvement and automation of these scheduling ...
-
(2019-10-08)Perception and action have a close functional relationship. While perception provides the means for actions, actions generate more opportunities for perception. This relationship between perception and action, between the ...
-
(2019-01-15)Wireless Internet access has brought legions of heterogeneous applications all sharing the same resources. However, current wireless edge networks that cater to worst or average case performance lack the agility to best ...
-
(2015-09-23)Autonomous travel poses challenges in machine learning navigation. Different approaches have been considered, such as reinforcement learning, dynamic programming methodologies, and other artificial intelligence assisted ...
-
Reinforcement learning (RL) is a state-of-the-art approach to solving sequential decision-making problems in stochastic environments. However, most model-free RL algorithms only produce one action at each timestep. That ...
-
(2009-06-02)Reinforcement learning is a machine learning technique designed to mimic the way animals learn by receiving rewards and punishment. It is designed to train intelligent agents when very little is known about the agent’s ...
-
(2012-12-05)The purpose of this dissertation is to understand how algorithms can efficiently learn to solve new tasks based on previous experience, instead of being explicitly programmed with a solution for each task that we want it ...
-
(2019-04-08)Anytime algorithms are a class of algorithm which are interruptible and whose solution quality improves with time, tending towards an optimal solution. In other words, there is a non-decreasing relationship between time ...