Autonomous transfer for reinforcement learning
- Computer Science, PsychologyAAMAS
This paper introduces Modeling Approximate State Transitions by Exploiting Regression (MASTER), a method for automatically learning a mapping from one task to another through an agent's experience and demonstrates that such learned relationships can significantly improve the speed of a reinforcement learning algorithm in a series of Mountain Car tasks.
Autonomous Formation of Concepts and Communication
- Computer Science
Automating Construction Operations using Discrete Event Simulation Models
The level of automation in the construction industry stands in stark contrast to other engineering industries such as automobile manufacturing wherein most of the tasks are done by machines with…
Neural-Adaptive Control of Waste-to-Energy Steam Generators
- EngineeringIEEE Transactions on Control Systems Technology
This work considers a boiler heated by waste-gas incineration, modeled as a standard utility boiler using one known and one unknown fuel input, and proposes a nonlinear adaptive control design that can obtain accurate performance and stability in a situation where PI control performs poorly.
Microassembly path planning using reinforcement learning for improving positioning accuracy of a 1 cm3 omni-directional mobile microrobot
- Computer ScienceApplied Intelligence
The path planning of a 1 cm3 mobile microrobot that is designed for microassembly in a microfactory is introduced and the SL-RL method achieves higher positioning accuracy and learning efficiency than the single RL method.
LOCAL SPARSE CODING CONTROL OF CVPSTS.
This paper discusses simulations of a control scheme based on locally sparse coded networks (CMACs) for a novel previously proposed continuously variable transmission (CVT), a hybrid continuously…
The Control Of A Manipulator Using Cerebellar Model Articulation Controllers
- Computer Science
In this thesis, CMAC neural networks are analyzed in detail and the relationship between CMAC network parameters and training techniques are presented.
Artificial Immune Systems and Their Applications
- Computer ScienceSpringer Berlin Heidelberg
This book provides an overview of artificial immune systems, explaining its applications in areas such as immunological memory, anomaly detection algorithms, and modeling the effects of prior infection on vaccine efficacy.
Adaptive Encoding Strongly Improves Function Approximation with CMAC
- Computer ScienceNeural Computation
Based on the already far better function approximation capability on continuous functions with a fixed topologically distributed encoding scheme in CMAC, the better results in learning a two-valued function with discontinuity are presented.
SHOWING 1-10 OF 22 REFERENCES
An Introduction to Hear¬
Design for Manufacturability: Design of Parts for Ease of Handling.
- NSF Grant APR77-10197. Amherst, MA: Univ. of Massachusetts,
A Structure for Plans and Behavior
- Computer Science
Progress to date in the ability of a computer system to understand and reason about actions is described, and the structure of a plan of actions is as important for problem solving and execution monitoring as the nature of the actions themselves.
Acquisition of Linguistic Skills by a Chimpanzee
- Reading, MA: Addison-Wesley,
The Dragons of Eden: Speculations on the Evolution of Human Intelligence
“A history of the human brain from the big bang, fifteen billion years ago, to the day before yesterday . . . It's a delight.”—The New York Times Dr. Carl Sagan takes us on a great reading adventure,…
Worldwide Com¬ puter-Aided Manufacturing Survey.
- ICAM Program, A.F. Materials Lab, Wright-Patterson AFB,