A Mathematical Introduction to Property Theory: The Fundamental Theorem and Duality Theory for Penalties

2004 ◽  
Author(s):  
David Ellerman
Keyword(s):  
Fundamental Theorem ◽  
Duality Theory ◽  
Property Theory

General Property Theory

2013 ◽  
Author(s):  
Gennady Innokentievich Cherkasov
Keyword(s):  
General Property ◽  
Property Theory

The property theory and de se attitudes

2017 ◽  
Author(s):  
Wayne A. Davis
Keyword(s):  
Propositional Attitude ◽  
Property Theory ◽  
De Se ◽  
Propositional Theory ◽  
Independent Property

The property theory of de se belief denies that believing is a propositional attitude, maintaining instead that for Lingens to believe that he himself is lost is for him to self-attribute the property of being lost. For Lingens to believe that Lingens is lost is for him to self-attribute the independent property of being such that Lingens is lost. The chapter argues that this theory postulates differences where we expect uniformity, introduces unnecessary theoretical complexity, is false to a variety of linguistic and phenomenological facts, and fails to explain many psychological and linguistic facts. If “self-attribute a property” means “believing oneself to have the property,” then the theory provides no explanation of de se belief. The author sketches a propositional theory on which the objects of the attitudes are complexes of concepts (thoughts), de se attitudes involving one type of indexical concept.

Property Rights: A Re-Examination

2020 ◽  
Author(s):  
J. E Penner
Keyword(s):  
Property Rights ◽  
Property Theory ◽  
Natural Right ◽  
Kantian Theory ◽  
Bundle Of Rights ◽  
Vexed Question ◽  
The Right ◽  
Jural Relations

Ranging over a host of issues, Property Rights: A Re-Examination pinpoints and addresses a number of theoretical problems at the heart of property theory. Part 1 reconsiders and refutes the bundle of rights picture of property and the related nominalist theories of property, showing that ownership reflects a tripartite structure of title, the right to immediate, exclusive, possession, and the power to licence what would otherwise be a trespass, and to transfer ownership. Part 2 explores in detail the Hohfeldian theory of jural relations, in particular liberties and powers and Hohfeld’s concept of ‘multital’ jural relations, and shows that this theory fails to illuminate the nature of property rights, and indeed obscures much that it is vital to understand about them. Part 3 considers the form and justification of property rights, beginning with the relation an owner’s liberty to use her property and her ‘right to exclude’, with particular reference to the tort of nuisance. Next up for consideration is the Kantian theory of property rights, the deficiencies of which lead us to understand that the only natural right to things is a form of use- or usufructory-right. Part 3 concludes by addressing the ever-vexed question of property rights in land.

scholarly journals Fully distributed actor-critic architecture for multitask deep reinforcement learning

2021 ◽  
Vol 36 ◽  
Author(s):  
Sergio Valcarcel Macua ◽  
Ian Davies ◽  
Aleksi Tukiainen ◽  
Enrique Munoz de Cote
Keyword(s):  
Neural Network ◽  
Reinforcement Learning ◽  
Duality Theory ◽  
Deep Neural Network ◽  
Original Problem ◽  
Almost Sure Convergence ◽  
Continuous Control ◽  
Access Data ◽  
Central Station ◽  
Common Policy

Abstract We propose a fully distributed actor-critic architecture, named diffusion-distributed-actor-critic Diff-DAC, with application to multitask reinforcement learning (MRL). During the learning process, agents communicate their value and policy parameters to their neighbours, diffusing the information across a network of agents with no need for a central station. Each agent can only access data from its local task, but aims to learn a common policy that performs well for the whole set of tasks. The architecture is scalable, since the computational and communication cost per agent depends on the number of neighbours rather than the overall number of agents. We derive Diff-DAC from duality theory and provide novel insights into the actor-critic framework, showing that it is actually an instance of the dual-ascent method. We prove almost sure convergence of Diff-DAC to a common policy under general assumptions that hold even for deep neural network approximations. For more restrictive assumptions, we also prove that this common policy is a stationary point of an approximation of the original problem. Numerical results on multitask extensions of common continuous control benchmarks demonstrate that Diff-DAC stabilises learning and has a regularising effect that induces higher performance and better generalisation properties than previous architectures.

Sign in / Sign up

Export Citation Format

Share Document