Search results for "Reinforcement"
showing 10 items of 230 documents
Realizing Undelayed N-step TD prediction with neural networks
2010
There exist various techniques to extend reinforcement learning algorithms, e.g., eligibility traces and planning. In this paper, an approach is proposed, which combines several extension techniques, such as using eligibility-like traces, using approximators as value functions and exploiting the model of the environment. The obtained method, ‘Undelayed n-step TD prediction’ (TD-P), has produced competitive results when put in conditions of not fully observable environment.
Seismic behavior of exterior RC beam-column joints without code-specified ties in the joint core
2021
Abstract Beam-column joint design for reinforced concrete (RC) buildings is a critical issue for modern earthquake engineering, because for these structural elements, the current codes provide several geometrical constraints and reinforcement provisions, which may be very complex to implement during the construction phase. To investigate how a construction error might influence the joint behavior, two identical full-scale exterior beam-column joints specimens are built, according to Italian Building Code specifications for the high ductility class, but without the required horizontal ties inside the joint panel. This construction error could be plausible because, according to the design dra…
Learning competitive pricing strategies by multi-agent reinforcement learning
2003
Abstract In electronic marketplaces automated and dynamic pricing is becoming increasingly popular. Agents that perform this task can improve themselves by learning from past observations, possibly using reinforcement learning techniques. Co-learning of several adaptive agents against each other may lead to unforeseen results and increasingly dynamic behavior of the market. In this article we shed some light on price developments arising from a simple price adaptation strategy. Furthermore, we examine several adaptive pricing strategies and their learning behavior in a co-learning scenario with different levels of competition. Q-learning manages to learn best-reply strategies well, but is e…
Validation of a Shear Model for RC and Hybrid Beams with Two Different Inclinations of Transversal Reinforcement
2016
The validation of an analytical model recently proposed for evaluation of the shear capacity in Reinforced Concrete (RC) beams containing multiple inclination of transverse stirrups is presented. The model is a suitable extension of that currently proposed in Eurocode 2 for the evaluation of the shear resistance, and it is derived by means of the the variable-inclination stress-field theory based on Nielsen’s plastic approach. Experimental and numerical data available in the literature on Hybrid Steel-Trussed Concrete Beams (HSTCBs) are used for model validation and result discussion. Finally, also the comparison with a different analytical approach for the assessment of the shear resistanc…
MARL-Ped: A multi-agent reinforcement learning based framework to simulate pedestrian groups
2014
Abstract Pedestrian simulation is complex because there are different levels of behavior modeling. At the lowest level, local interactions between agents occur; at the middle level, strategic and tactical behaviors appear like overtakings or route choices; and at the highest level path-planning is necessary. The agent-based pedestrian simulators either focus on a specific level (mainly in the lower one) or define strategies like the layered architectures to independently manage the different behavioral levels. In our Multi-Agent Reinforcement-Learning-based Pedestrian simulation framework (MARL-Ped) the situation is addressed as a whole. Each embodied agent uses a model-free Reinforcement L…
Analysis of the accuracy of fiber-optic strain transducers installed by using composite smart patches
2015
The aim of this work is to investigate the accuracy of fiber-optic strain transducer related to the incomplete load transmission that can occur on composite smart patches used as base support for the installation of such transducer, commonly used for structural monitoring of concrete elements. In detail, since the dimensions of the transducer are generally very small compared to those of the structural element being monitored, attention is given not to the global reinforcement effect, which occurs when the transducer alters the entire strain field of the transversal section of the monitored element, but rather to the so-called local reinforcement effect, which is due to an incomplete load …
Interaction between Longitudinal Shear and Transverse Bending in Prestressed Concrete Box Girders
2017
In box girder bridges, the quantity and distribution of reinforcement to be put in concrete elements of sections can be evaluated only by considering the deformation of the cross section in addition to the longitudinal analysis of the static scheme, establishing the entire state of stress of box sections. This leads to a need to evaluate the interaction between internal forces obtained by the global analysis and the ones obtained by the local analysis of the cross sections. The frame effect implies the elastic deformation of slabs and webs, whereas eccentrically applied loads lead to cross-section distortion with the loss of the box shape. Hence, the reinforcement is strongly influenced by …
Timber anti-seismic devices in historical architecture in the Mediterranean area
2017
Questo lavoro esamina l’uso di un dispositivo strutturale in legno storico utilizzato come rinforzo della muratura per i sistemi di prevenzione sismica nell'area mediterranea. Tale tecnologia viene realizzata mediante un telaio tridimensionale tridimensionale di legno incorporato nella muratura di pietra per legare insieme le varie parti strutturali e contribuire alla resistenza sismica complessiva. Molto spesso, questo principio costruttivo fu esteso non solo per le parti più deboli, ma per l'intero edificio, creando nuove configurazioni strutturali che erano in grado di assorbire gli effetti delle azioni sismiche. Dalle esperienze costruttive di epoca romana (opus craticium), questo siste…
Load-carrying capacity of axially-loaded RC members with circular openings
2012
Abstract Core drilling is today one of the most used technique among the group of partially destructive testing methods in reinforced concrete (RC) members. Even if the engineering practice provided to extract cores only in beams, taking samples from columns could be often necessary. In this case, the presence of the hole introduced a geometrical discontinuity in the member, creating a disturbed region. Consequently, compressive stresses will disperse in lateral direction as they have to avoid the drilled area. A bursting tensile force will develop, in orthogonal direction to the column axis, and if no sufficient reinforcement was arranged, a vertical crack will form, leading to the concret…
Minimum bond length and size effects in FRP–substrate bonded joints
2009
Abstract The load transfer mechanism between the fibre-reinforced polymer (FRP) materials and the substrate plays a crucial role in the overall response of retrofitted structural members. The FRP–support material interface can be studied by using pull tests in which a reinforcement plate is bonded to a prism and subjected to a tensile force. The experimental results obtained regard the assembly (FRP strip-support block), then a central problem is how to carry out the interface constitutive laws and the related parameters. The principal objective of the present paper is to contrive a procedure which, for a fixed interface constitutive law, permits to derive the interface mechanical parameter…