An Inception Network with Bottleneck Attention Module for Deep Reinforcement Learning Framework in Financial Portfolio Management

Yao, Weiye; Ren, Xiaotian; Su, Jionglong

doi:10.1109/icbda55095.2022.9760343

Cited by 5 publications

(1 citation statement)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Jiang et al [27] proposed the ensemble of identical independent evaluators Yao et al [31] implemented an inception module with a convolution block of different filter sizes and a bottleneck attention module to mitigate challenges associated with uniformly stacked networks, such as overfitting and computational overflow. However, these approaches did not incorporate risk management into their methodologies.…”

Section: Reinforcement Learning For Cryptocurrency Tradingmentioning

confidence: 99%

Multi-agent deep reinforcement learning for cryptocurrency trading

Kumlungmak

View full text Add to dashboard Cite

Reinforcement learning has emerged as a promising approach for enhancing profitability in cryptocurrency trading. However, the inherent volatility of the market, especially during bearish periods, poses significant challenges in this domain. Existing literature addresses this issue through the adoption of single-agent techniques such as deep Q-network (DQN), advantage actor-critic (A2C), and proximal policy optimization (PPO), or their ensembles. Despite these efforts, the mechanisms employed to mitigate losses during bearish market conditions within the cryptocurrency context lack robustness. Consequently, the performance of reinforcement learning methods for cryptocurrency trading remains constrained within the current literature. To overcome this limitation, we present a novel cryptocurrency trading method, leveraging multi-agent proximal policy optimization (MAPPO). Our approach incorporates a collaborative multi-agent scheme and a local-global reward function to optimize both individual and collective agent performance. Employing a multi-objective optimization technique and a multi-scale continuous loss (MSCL) reward, we train the agents using a progressive penalty mechanism to prevent consecutive losses of portfolio value. In evaluating our method, we compare it against multiple baselines, revealing superior cumulative returns compared to baseline methods. Notably, the strength of our method is further exemplified through the results obtained from the bearish test set, where only our approach demonstrates the ability to yield a profit. Specifically, our method achieves an impressive cumulative return of 2.36%, while the baseline methods result in negative cumulative returns. In comparison to FinRL-Ensemble, a reinforcement learning-based method, our approach exhibits a remarkable 46.05% greater cumulative return in the bullish test set.

show abstract

Section: Reinforcement Learning For Cryptocurrency Tradingmentioning

confidence: 99%