TD-Gammon is a neural network that is able to teach itself to play backgammon solely by playing against itself and learning from the results, based on the TD(X) reinforcement learning algorithm (Sutton 1988). Despite starting from random initial weights (and hence random initial strategy), TD-Gammon achieves a surprisingly strong level of play. With zero knowledge built in at the start of learn...

Reinforcement learning has been applied to many interesting problems such as the famous TD-gammon [1] and the inverted helicopter flight [2]. However little effort has been put into developing methods to learn policies for complex persistent tasks and tasks that are time-sensitive. In this paper we take a step towards solving this problem by using signal temporal logic (STL) as task specificati...

The expanding therapeutic uses of thalidomide (TD) are limited by its teratogenic side effects. Although the therapeutic and teratogenic effects may be stereoselectively separable, rapid in vivo racemization of the TD isomers confounds the corroboration of this distinction. Herein we evaluated the potential of fluorothalidomide (FTD), the closest structural analog of TD with stable, nonracemizi...

Tourette's disorder (TD) frequently co-occurs with attention-deficit/hyperactivity disorder (ADHD) and obsessive compulsive disorder (OCD). While the relationship between TD and OCD suggests that they share etiological factors, the exact relationship between TD and ADHD is less clear. The goal of the current analyses was to understand better the familial relationship between DSM-IV ADHD and TD....

OBJECTIVE Tardive dyskinesia (TD) is a long-term adverse effect of antipsychotic. Dopaminergic activity in the nigrostriatal system have been proposed to be involved in development of TD and dopamine D2 receptors (DRD2) has been regarded as a candidate gene for TD because the antipsychotics have potent antagonism DRD2. This study was aimed to find the relationship between DRD2 gene and antipsyc...

INTRODUCTION TomoTherapy (Accuray, Sunnyvale, CA) has recently introduced a static form of tomotherapy: TomoDirect™ (TD). This study aimed to evaluate TD against a contemporary intensity modulated radiation therapy (IMRT) alternative through comparison of target and organ at risk (OAR) doses in breast cancer cases. A secondary objective was to evaluate planning efficiency by measuring optimisat...

Temporal-difference (TD) networks have been introduced as a formalism for expressing and learning grounded world knowledge in a predictive form (Sutton & Tanner, 2005). Like conventional TD(0) methods, the learning algorithm for TD networks uses 1-step backups to train prediction units about future events. In conventional TD learning, the TD(λ) algorithm is often used to do more general multi-s...

A method to detect and to adjust or exclude abnormally low or high milk, fat, and protein yields on test-day (TD) was developed. Predicted TD yield is calculated based on preceding and subsequent (if available) TD yields. Observed TD yields that are < 60% or > 150% of predicted TD yield are defined as abnormal. Most abnormal yields are adjusted to this floor or ceiling, but some are excluded. Y...