Matches in SemOpenAlex for { <https://semopenalex.org/work/W3088749011> ?p ?o ?g. }
Showing items 1 to 61 of
61
with 100 items per page.
- W3088749011 abstract "Stock trading strategies play a critical role in investment. However, it is challenging to design a profitable strategy in a complex and dynamic stock market. In this paper, we propose an ensemble strategy that employs deep reinforcement schemes to learn a stock trading strategy by maximizing investment return. We train a deep reinforcement learning agent and obtain an ensemble trading strategy using three actor-critic based algorithms: Proximal Policy Optimization (PPO), Advantage Actor Critic (A2C), and Deep Deterministic Policy Gradient (DDPG). The ensemble strategy inherits and integrates the best features of the three algorithms, thereby robustly adjusting to different market situations. In order to avoid the large memory consumption in training networks with continuous action space, we employ a load-on-demand technique for processing very large data. We test our algorithms on the 30 Dow Jones stocks that have adequate liquidity. The performance of the trading agent with different reinforcement learning algorithms is evaluated and compared with both the Dow Jones Industrial Average index and the traditional min-variance portfolio allocation strategy. The proposed deep ensemble strategy is shown to outperform the three individual algorithms and two baselines in terms of the risk-adjusted return measured by the Sharpe ratio." @default.
- W3088749011 created "2020-10-01" @default.
- W3088749011 creator A5054560949 @default.
- W3088749011 creator A5061855742 @default.
- W3088749011 creator A5066875580 @default.
- W3088749011 creator A5073713299 @default.
- W3088749011 date "2020-01-01" @default.
- W3088749011 modified "2023-10-18" @default.
- W3088749011 title "Deep Reinforcement Learning for Automated Stock Trading: An Ensemble Strategy" @default.
- W3088749011 doi "https://doi.org/10.2139/ssrn.3690996" @default.
- W3088749011 hasPublicationYear "2020" @default.
- W3088749011 type Work @default.
- W3088749011 sameAs 3088749011 @default.
- W3088749011 citedByCount "12" @default.
- W3088749011 countsByYear W30887490112021 @default.
- W3088749011 countsByYear W30887490112022 @default.
- W3088749011 countsByYear W30887490112023 @default.
- W3088749011 crossrefType "journal-article" @default.
- W3088749011 hasAuthorship W3088749011A5054560949 @default.
- W3088749011 hasAuthorship W3088749011A5061855742 @default.
- W3088749011 hasAuthorship W3088749011A5066875580 @default.
- W3088749011 hasAuthorship W3088749011A5073713299 @default.
- W3088749011 hasConcept C106159729 @default.
- W3088749011 hasConcept C119857082 @default.
- W3088749011 hasConcept C127413603 @default.
- W3088749011 hasConcept C131562839 @default.
- W3088749011 hasConcept C154945302 @default.
- W3088749011 hasConcept C162324750 @default.
- W3088749011 hasConcept C41008148 @default.
- W3088749011 hasConcept C66938386 @default.
- W3088749011 hasConcept C67203356 @default.
- W3088749011 hasConcept C78508483 @default.
- W3088749011 hasConcept C97541855 @default.
- W3088749011 hasConceptScore W3088749011C106159729 @default.
- W3088749011 hasConceptScore W3088749011C119857082 @default.
- W3088749011 hasConceptScore W3088749011C127413603 @default.
- W3088749011 hasConceptScore W3088749011C131562839 @default.
- W3088749011 hasConceptScore W3088749011C154945302 @default.
- W3088749011 hasConceptScore W3088749011C162324750 @default.
- W3088749011 hasConceptScore W3088749011C41008148 @default.
- W3088749011 hasConceptScore W3088749011C66938386 @default.
- W3088749011 hasConceptScore W3088749011C67203356 @default.
- W3088749011 hasConceptScore W3088749011C78508483 @default.
- W3088749011 hasConceptScore W3088749011C97541855 @default.
- W3088749011 hasLocation W30887490111 @default.
- W3088749011 hasOpenAccess W3088749011 @default.
- W3088749011 hasPrimaryLocation W30887490111 @default.
- W3088749011 hasRelatedWork W3016228233 @default.
- W3088749011 hasRelatedWork W3035574064 @default.
- W3088749011 hasRelatedWork W3122425648 @default.
- W3088749011 hasRelatedWork W3126577088 @default.
- W3088749011 hasRelatedWork W3175255688 @default.
- W3088749011 hasRelatedWork W3176836227 @default.
- W3088749011 hasRelatedWork W4311038708 @default.
- W3088749011 hasRelatedWork W4313641676 @default.
- W3088749011 hasRelatedWork W4319083788 @default.
- W3088749011 hasRelatedWork W4365600551 @default.
- W3088749011 isParatext "false" @default.
- W3088749011 isRetracted "false" @default.
- W3088749011 magId "3088749011" @default.
- W3088749011 workType "article" @default.