Once Burned, Twice Shy? The Effect of Stock Market Bubbles on Traders that Learn by Experience
2023 Winter Simulation Conference (WSC)(2023)
摘要
We study how experience with asset price bubbles changes the trading
strategies of reinforcement learning (RL) traders and ask whether the change in
trading strategies helps to prevent future bubbles. We train the RL traders in
a multi-agent market simulation platform, ABIDES, and compare the strategies of
traders trained with and without bubble experience. We find that RL traders
without bubble experience behave like short-term momentum traders, whereas
traders with bubble experience behave like value traders. Therefore, RL traders
without bubble experience amplify bubbles, whereas RL traders with bubble
experience tend to suppress and sometimes prevent them. This finding suggests
that learning from experience is a mechanism for a boom and bust cycle where
the experience of a collapsing bubble makes future bubbles less likely for a
period of time until the memory fades and bubbles become more likely to form
again.
更多查看译文
关键词
Asset Pricing,Boom And Bust,Trading Strategies,Price Bubbles,Asset Bubbles,Test Session,Business Environment,Simulation Environment,Market Participants,Market Volatility,Types Of Agents,Multi-agent Systems,Bubble Formation,Fundamental Values,Huge Losses,Shapley Value,Trading Days,Ornstein-Uhlenbeck Process,Reinforcement Learning Agent,Bubble Burst,Order Book,Trained Agent,Large Volatility,Proximal Policy Optimization,Bubble Generation,State Space,Retail Investors,Stock Price,Stock Market
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要