We investigate the use of animal videos (observations) to improve Reinforcement Learning (RL) efficiency and performance in navigation tasks with sparse rewards. Motivated by theoretical considerations, we make use of...
详细信息
We investigate the use of animal videos (observations) to improve Reinforcement Learning (RL) efficiency and performance in navigation tasks with sparse rewards. Motivated by theoretical considerations, we make use of weighted policy optimization for off-policy RL and describe the main challenges when learning from animal videos. We propose solutions and test our ideas on a 2D navigation task. We show how the use of animal videos improves performance over RL algorithms that do not leverage such observations.
This paper aims to develop predictive models for the thermal properties of laboratory-prepared hot mix asphalt (HMA) specimens using the Adaptive Neuro-Fuzzy Inference System (ANFIS). The thermal properties investigat...
This paper aims to develop predictive models for the thermal properties of laboratory-prepared hot mix asphalt (HMA) specimens using the Adaptive Neuro-Fuzzy Inference System (ANFIS). The thermal properties investigated include thermal conductivity, thermal diffusivity, and specific heat. Thirty specimens were prepared by varying the mixture’s nominal maximum aggregate size and gradation coarseness, using a single asphalt binder. The transient plane source method was employed to determine the thermal properties, and volumetric parameters such as air void volume and effective binder volume were calculated. Surface characteristics, including friction and texture, were also considered. A total of 150 data points were generated through three aggregate sizes, two gradation levels, five replicates, and five measurement locations to ensure accuracy and repeatability. The model development process was structured in three phases: (1) feature reduction to detect multicollinearity, (2) outlier detection and removal, and (3) application of the ANFIS regression model. Model performance was evaluated using mean squared error (MSE), root mean squared error (RMSE), and coefficient of determination (R2). Results indicated that outliers significantly increased MSE and reduced prediction accuracy, with RMSE improving from 0.4752 to 0.1765 after outlier removal for thermal conductivity. R2 scores for thermal diffusivity and specific heat improved from 0.55 and 0.72 to 0.866 and 0.91, respectively, after addressing multicollinearity and outliers. The study demonstrates that the proposed ANFIS model effectively predicts the thermal properties of HMA specimens and highlights the potential for even greater predictive accuracy by integrating other advanced regression methods.
The Hansen solubility parameters(HSP)are frequently used for solvent selection and characterization of polymers,and are directly related to the suspension behavior of pigments in solvent *** performance of currently a...
详细信息
The Hansen solubility parameters(HSP)are frequently used for solvent selection and characterization of polymers,and are directly related to the suspension behavior of pigments in solvent *** performance of currently available group contribution(GC)methods for HSP were evaluated and found to be insufficient for computer-aided product design(CAPD)of paints and coatings.A revised and,for this purpose,improved GC method is presented for estimating HSP of organic compounds,intended for organic *** to the significant limitations of GC methods,an uncertainty analysis and parameter confidence intervals are provided in order to better quantify the estimation accuracy of the proposed *** to other applicable GC methods,the prediction error is reduced significantly with average absolute errors of 0.45 MPa^(1/2),1.35 MPa^(1/2),and 1.09 MPa^(1/2) for the partial dispersion(δD),polar(δP)and hydrogen-bonding(δH)solubility parameters respectively for a database of 1106 *** performance for organic pigments is comparable to the overall method performance,with higher average errors forδD and lower average errors forδP andδH.
Homo-or heterodimeric compounds that affect dimeric protein function through interaction between monomeric moieties and protein subunits can serve as valuable sources of potent and selective drug ***,we screened an in...
详细信息
Homo-or heterodimeric compounds that affect dimeric protein function through interaction between monomeric moieties and protein subunits can serve as valuable sources of potent and selective drug ***,we screened an in-house dimeric natural product collection,and panepocyclinol A(PecA)emerged as a selective and potent STAT3 inhibitor with profound anti-tumor *** cross-linking C712/C718 residues in separate STAT3 monomers with two distinct Michael receptors,PecA inhibits STAT3 DNA binding affinity and transcription *** dynamics simulation reveals the key conformation changes of STAT3 dimers upon the di-covalent binding with PecA that abolishes its DNA ***,PecA exhibits high efficacy against anaplastic large T cell lymphoma in vitro and in vivo,especially those with constitutively activated STAT3 or STAT3^(Y640F).In summary,our study describes a distinct and effective di-covalent modification for the dimeric compound PecA to disrupt STAT3 function.
Biomedical Named Entity Recognition (NER) is a crucial task in extracting information from biomedical texts. However, the diversity of professional terminology, semantic complexity, and the widespread presence of syno...
详细信息
Accurate and robust segmentation of surgical instrument parts is urgently required by AI enhanced intelligent surgery and automatic surgery skill evaluation. However, it is still a challenging problem due to the multi...
详细信息
Utilizing randomized experiments to evaluate the effect of short-term treatments on the short-term outcomes has been well understood and become the golden standard in industrial practice. However, as service systems b...
详细信息
Cost-effective seafloor mapping at high resolution is yet to be attained. A possible solution consists of using a mobile, wide-aperture, sparse array with subarrays distributed across multiple autonomous surface vesse...
Cost-effective seafloor mapping at high resolution is yet to be attained. A possible solution consists of using a mobile, wide-aperture, sparse array with subarrays distributed across multiple autonomous surface vessels. Such wide-area mapping with multiple dynamic sources and receivers require accurate modeling and processing systems for imaging the seabed. In this paper, we focus on computational schemes and challenges for such high-resolution acoustic imaging or migration. Starting from the imaging condition from the adjoint-state method, we derive a closed-form expression for Gaussian beam migration in stratified media. We employ this technique on simulated data and on real data collected with our novel acoustic array over shipwrecks in the Boston Harbor. We compare Gaussian beam migration with diffraction stack and Kirchhoff migration, and we find that Gaussian beam migration produces the clearest images with the fewest artifacts.
Inelastic neutron scattering (INS) spectra of hydrogen in face-centered cubic palladium have been calculated considering nuclear quantum effects (NQEs) at finite temperatures. The calculations were performed using sem...
详细信息
Randomize-then-optimize (RTO) is widely used for sampling from posterior distributions in Bayesian inverse problems. However, RTO can be computationally intensive forcomplexity problems due to repetitive evaluations o...
详细信息
Randomize-then-optimize (RTO) is widely used for sampling from posterior distributions in Bayesian inverse problems. However, RTO can be computationally intensive forcomplexity problems due to repetitive evaluations of the expensive forward model and itsgradient. In this work, we present a novel goal-oriented deep neural networks (DNN) surrogate approach to substantially reduce the computation burden of RTO. In particular,we propose to drawn the training points for the DNN-surrogate from a local approximatedposterior distribution – yielding a flexible and efficient sampling algorithm that convergesto the direct RTO approach. We present a Bayesian inverse problem governed by ellipticPDEs to demonstrate the computational accuracy and efficiency of our DNN-RTO approach, which shows that DNN-RTO can significantly outperform the traditional RTO.
暂无评论