强化学习的动作为序列的 token,比如"BEG"、"5"、"$vol"等。强化学习的奖励函数则比较特殊,输出一个 alpha 因子之后(一个 episode),我们通过算法 1的得到了新的组合因子,该新因子的 IC 值就是强化学习在这个 episode 的 return。通过选择折现因子\gamma = 1,确保了强化学习算法不会因为 longer episode 而受到...
In practice, a set of formulaic alphas is often used together for better modeling precision, so we need to find synergistic formulaic alpha sets that work well together. However, most traditional alpha generators mine alphas one by one separately, overlooking the fact that the alphas would be ...
Automatic formulaic alpha generation with reinforcement learning. PaperGenerating Synergistic Formulaic Alpha Collections via Reinforcement Learningaccepted byKDD 2023, Applied Data Science (ADS) track. Paper available onACM DLorarXiv. How to reproduce? Note that you can either use our builtin alpha cal...
Yu, Shuo, et al. "Generating Synergistic Formulaic Alpha Collections via Reinforcement Learning." Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. 2023. Malkin, Nikolay, et al. "Trajectory balance: Improved credit assignment in GFlowNets." Advances in Neural In...
AlphaGen Automatic formulaic alpha generation with reinforcement learning. Paper Generating Synergistic Formulaic Alpha Collections via Reinforcement Learning accepted by KDD 2023, Applied Data Science (ADS) track. Paper available on ACM DL or arXiv. How to reproduce? Note that you can either use our...
AlphaGen Automatic formulaic alpha generation with reinforcement learning. This repository contains the code for our paperGenerating Synergistic Formulaic Alpha Collections via Reinforcement Learningaccepted byKDD 2023, Applied Data Science (ADS) track, publically available onACM DL. Some extensions upon this...
This branch is4 commits behindRL-MLDM/alphagen:master. README AlphaGen Automatic formulaic alpha generation with reinforcement learning. PaperGenerating Synergistic Formulaic Alpha Collections via Reinforcement Learningaccepted byKDD 2023, Applied Data Science (ADS) track. ...
Paper Generating Synergistic Formulaic Alpha Collections via Reinforcement Learning accepted by KDD 2023, Applied Data Science (ADS) track. Paper available on ACM DL or arXiv. How to reproduce? Note that you can either use our builtin alpha calculation pipeline(see Choice 1), or implement an ad...
AlphaGen Automatic formulaic alpha generation with reinforcement learning. Paper Generating Synergistic Formulaic Alpha Collections via Reinforcement Learning accepted by KDD 2023, Applied Data Science (ADS) track. Paper available on ACM DL or arXiv. How to reproduce? Note that you can either use our...
AlphaGenAutomatic formulaic alpha generation with reinforcement learning.This repository contains the code for our paper Generating Synergistic Formulaic Alpha Collections via Reinforcement Learning accepted by KDD 2023, Applied Data Science (ADS) track, publically available on ACM DL. Some extensions upon ...