The goal of reinforcement learning is to enable an agent to learn by using rewards. However, some robotic tasks naturally specify with sparse rewards, and manually shaping reward functions is a difficult project. In this article, we propose a general and model-free approach for reinforcement learning to learn robotic tasks with sparse rewards. First, a variant of Hindsight Experience Replay, Curious and Aggressive Hindsight Experience Replay, is proposed to improve the sample efficiency of reinforcement learning methods and avoid the need for complicated reward engineering. Second, based on Twin Delayed Deep Deterministic policy gradient algorithm, demonstrations are leveraged to overcome the exploration problem and speed up the policy training process. Finally, the action loss is added into the loss function in order to minimize the vibration of output action while maximizing the value of the action. The experiments on simulated robotic tasks are performed with different hyperparameters to verify the effectiveness of our method. Results show that our method can effectively solve the sparse reward problem and obtain a high learning speed.
Previous research has demonstrated that duration of implied motion (IM) was dilated, whereas hMT+ activity related to perceptual processes on IM stimuli could be modulated by their motion coherence. Based on these findings, the present study aimed to examine whether subjective time perception of IM stimuli would be influenced by varying coherence levels. A temporal bisection task was used to measure the subjective experience of time, in which photographic stimuli showing a human moving in four directions (left, right, toward, or away from the viewer) were presented as probe stimuli. The varying coherence of these IM stimuli was manipulated by changing the percentage of pictures implying movement in one direction. Participants were required to judge whether the duration of probe stimulus was more similar to the long or short pre-presented standard duration. As predicted, the point of subjective equality was significantly modulated by the varying coherence of the IM stimuli, but not for no-IM stimuli. This finding suggests that coherence level might be a key mediating factor for perceived duration of IM images, and top-down perceptual stream from inferred motion could influence subjective experience of time perception.
Background
Diagnostic codes can retrospectively identify samples of febrile infants, but sensitivity is low, resulting in many febrile infants eluding detection. To ensure study samples are representative, an improved approach is needed.
Objective
To derive and internally validate a natural language processing algorithm to identify febrile infants and compare its performance to diagnostic codes.
Methods
This cross‐sectional study consisted of infants aged 0–90 days brought to one pediatric emergency department from January 2016 to December 2017. We aimed to identify infants with fever, defined as a documented temperature ≥38°C. We used 2017 clinical notes to develop two rule‐based algorithms to identify infants with fever and tested them on data from 2016. Using manual abstraction as the gold standard, we compared performance of the two rule‐based algorithms (Models 1, 2) to four previously published diagnostic code groups (Models 5–8) using area under the receiver‐operating characteristics curve (AUC), sensitivity, and specificity.
Results
For the test set (n = 1190 infants), 184 infants were febrile (15.5%). The AUCs (0.92–0.95) and sensitivities (86%–92%) of Models 1 and 2 were significantly greater than Models 5–8 (0.67–0.74; 20%–74%) with similar specificities (93%–99%). In contrast to Models 5–8, samples from Models 1 and 2 demonstrated similar characteristics to the gold standard, including fever prevalence, median age, and rates of bacterial infections, hospitalizations, and severe outcomes.
Conclusions
Findings suggest rule‐based algorithms can accurately identify febrile infants with greater sensitivity while preserving specificity compared to diagnostic codes. If externally validated, rule‐based algorithms may be important tools to create representative study samples, thereby improving generalizability of findings.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.