This paper presents a Double Deep Q-Network algorithm for trading single assets, namely the E-mini S&P 500 continuous futures contract. We use a proven setup as the foundation for our environment with multiple extensions. The features of our trading agent are constantly being expanded to include additional assets such as commodities, resulting in four models. We also respond to environmental conditions, including costs and crises. Our trading agent is first trained for a specific time period and tested on new data and compared with the long-and-hold strategy as a benchmark (market). We analyze the differences between the various models and the in-sample/out-of-sample performance with respect to the environment. The experimental results show that the trading agent follows an appropriate behavior. It can adjust its policy to different circumstances, such as more extensive use of the neutral position when trading costs are present. Furthermore, the net asset value exceeded that of the benchmark, and the agent outperformed the market in the test set. We provide initial insights into the behavior of an agent in a financial domain using a DDQN algorithm. The results of this study can be used for further development.

Background Sleep apnea (SA) is a prevalent disorder characterized by recurrent events of nocturnal apnea originating from obstructive and/or central mechanisms. SA disrupts normal sleep and can lead to a series of complications when left untreated. SA results in intermittent hypoxia which has an impact on the cardio- and cerebrovascular system. Hospitalized patients with SA typically have a greater burden of comorbidity, a longer length of hospital stay, but may show an improvement of in-hospital mortality compared to patients without diagnosed SA. The reason for this survival benefit is controversial and we aimed to clarify this protective effect in the light of predictive factors including SA-associated comorbidities using a nation-wide hospitalization database. Methods and findings Data were extracted from a nation-wide hospitalization database provided by the Swiss Federal Office for Statistics. Hospitalized patients with a SA co-diagnosis were extracted from the database together with a 1:1-matched control population without SA. Overall, 212’581 patients with SA were hospitalized in Switzerland between 2002 and 2018. Compared to the controls, SA cases had a longer median length of hospital stay (7 days; 95% CI: 3 to 15 vs. 4 days; 95% CI: 2 to 10) (p < 0.001) and a higher median number of comorbidities (8 comorbidities; IQR: 5 to 11 vs. 3 comorbidities; IQR: 1 to 6) (p < 0.001). The risk of in-hospital mortality was lower in the SA cases compared to the controls (OR: 0.73; 95% CI: 0.7 to 0.76; p < 0.001). SA was associated with a survival benefit in hospitalizations related to 28 of 47 conditions with the highest rate of in-hospital death. Sixty-three comorbidities were significantly over-represented in SA cases among which obesity, hypertension and anatomic nasal deviations were associated with a significant decrease of in-hospital mortality. Conclusions Compared to matched controls, SA was associated with significant and relevant inpatient survival benefit in a number of most deadly conditions. Within SA-patients, associated comorbidities mostly correlated with a poorer prognosis, whereas obesity and hypertension were associated with an improved in-hospital mortality.

No abstract