How to find an effective trading policy is still an open question mainly due to the nonlinear and non-stationary dynamics in a financial market.Deep reinforcement learning,which has recently been used to develop tradi...How to find an effective trading policy is still an open question mainly due to the nonlinear and non-stationary dynamics in a financial market.Deep reinforcement learning,which has recently been used to develop trading strategies by automatically extracting complex features from a large amount of data,is struggling to deal with fastchanging markets due to sample inefficiency.This paper applies the meta-reinforcement learning method to tackle the trading challenges faced by conventional reinforcement learning(RL)approaches in non-stationary markets for the first time.In our work,the history trading data is divided into multiple task data and for each of these data themarket condition is relatively stationary.Then amodel agnosticmeta-learning(MAML)-based tradingmethod involving a meta-learner and a normal learner is proposed.A trading policy is learned by the meta-learner across multiple task data,which is then fine-tuned by the normal learner through a small amount of data from a new market task before trading in it.To improve the adaptability of the MAML-based method,an ordered multiplestep updating mechanism is also proposed to explore the changing dynamic within a task market.The simulation results demonstrate that the proposed MAML-based trading methods can increase the annualized return rate by approximately 180%,200%,and 160%,increase the Sharpe ratio by 180%,90%,and 170%,and decrease the maximum drawdown by 30%,20%,and 40%,compared to the traditional RL approach in three stock index future markets,respectively.展开更多
To evaluate the anesthetic effect of ultrasound-guided(USG)ilioinguinal/iliohypogastric nerve(Ⅱ/IHN)block combined with genital branch of genitofemoral nerve(GFN)block in the elderly undergoing inguinal hernia repair...To evaluate the anesthetic effect of ultrasound-guided(USG)ilioinguinal/iliohypogastric nerve(Ⅱ/IHN)block combined with genital branch of genitofemoral nerve(GFN)block in the elderly undergoing inguinal hernia repair,54 old patients(aged 60-96years,ASAⅠ-Ⅲ)with indirect hernia were enrolled and scheduled for unilateral tensiofree herniorrhaphy.Patients were grouped randomly to receive either USGⅡ/IHN plus GFN block(Group G)or USGⅡ/IHN block alone(GroupⅠ).The intraoperative visual analogue scale(VAS)scores were recorded at skin incision,at spermatic cord/round ligament traction and at sac ligation.The resting and dynamic VAS scores were recorded postoperatively.The requirements of extra sedatives and analgesics for intra-and postoperative analgesia were assessed.Occurrence of complications of the block,postoperative nausea and vomiting and femoral nerve palsy was also reported.Both groups showed similar sensory block.When stretching spermatic cord/round ligament,the patients in group G had significantly lower VAS scores than in group.And group G used much fewer adjuvant sedatives and analgesics to achieve adequate anaesthesia.In addition,group G was presented with better intraoperative anaesthesia and lower postoperative dynamic VAS scores at all time points tested.No significant difference was found in the postoperative requirement of rescue medication.Both groups showed no complications related to the block and group G reported no femoral nerve palsy.The addition of GFN block toⅡ/IHN block improves the quality of perioperative anesthesia and analgesia in the elderly and reduces the consumption of extra sedatives and analgesics during the surgery.展开更多
文摘How to find an effective trading policy is still an open question mainly due to the nonlinear and non-stationary dynamics in a financial market.Deep reinforcement learning,which has recently been used to develop trading strategies by automatically extracting complex features from a large amount of data,is struggling to deal with fastchanging markets due to sample inefficiency.This paper applies the meta-reinforcement learning method to tackle the trading challenges faced by conventional reinforcement learning(RL)approaches in non-stationary markets for the first time.In our work,the history trading data is divided into multiple task data and for each of these data themarket condition is relatively stationary.Then amodel agnosticmeta-learning(MAML)-based tradingmethod involving a meta-learner and a normal learner is proposed.A trading policy is learned by the meta-learner across multiple task data,which is then fine-tuned by the normal learner through a small amount of data from a new market task before trading in it.To improve the adaptability of the MAML-based method,an ordered multiplestep updating mechanism is also proposed to explore the changing dynamic within a task market.The simulation results demonstrate that the proposed MAML-based trading methods can increase the annualized return rate by approximately 180%,200%,and 160%,increase the Sharpe ratio by 180%,90%,and 170%,and decrease the maximum drawdown by 30%,20%,and 40%,compared to the traditional RL approach in three stock index future markets,respectively.
文摘To evaluate the anesthetic effect of ultrasound-guided(USG)ilioinguinal/iliohypogastric nerve(Ⅱ/IHN)block combined with genital branch of genitofemoral nerve(GFN)block in the elderly undergoing inguinal hernia repair,54 old patients(aged 60-96years,ASAⅠ-Ⅲ)with indirect hernia were enrolled and scheduled for unilateral tensiofree herniorrhaphy.Patients were grouped randomly to receive either USGⅡ/IHN plus GFN block(Group G)or USGⅡ/IHN block alone(GroupⅠ).The intraoperative visual analogue scale(VAS)scores were recorded at skin incision,at spermatic cord/round ligament traction and at sac ligation.The resting and dynamic VAS scores were recorded postoperatively.The requirements of extra sedatives and analgesics for intra-and postoperative analgesia were assessed.Occurrence of complications of the block,postoperative nausea and vomiting and femoral nerve palsy was also reported.Both groups showed similar sensory block.When stretching spermatic cord/round ligament,the patients in group G had significantly lower VAS scores than in group.And group G used much fewer adjuvant sedatives and analgesics to achieve adequate anaesthesia.In addition,group G was presented with better intraoperative anaesthesia and lower postoperative dynamic VAS scores at all time points tested.No significant difference was found in the postoperative requirement of rescue medication.Both groups showed no complications related to the block and group G reported no femoral nerve palsy.The addition of GFN block toⅡ/IHN block improves the quality of perioperative anesthesia and analgesia in the elderly and reduces the consumption of extra sedatives and analgesics during the surgery.