A Deep Reinforcement Learning Trader without Offline Training
This is an incremental improvement for algorithmic traders seeking online methods without pre-training.
The paper tackled the problem of developing a fully online trading algorithm without offline training, using Double Deep Q-learning with Fast Learning Networks and a mechanism to conserve money in unfavorable market conditions, and found that it performed better than random trading on Cardano price data across different market trends.
In this paper we pursue the question of a fully online trading algorithm (i.e. one that does not need offline training on previously gathered data). For this task we use Double Deep $Q$-learning in the episodic setting with Fast Learning Networks approximating the expected reward $Q$. Additionally, we define the possible terminal states of an episode in such a way as to introduce a mechanism to conserve some of the money in the trading pool when market conditions are seen as unfavourable. Some of these money are taken as profit and some are reused at a later time according to certain criteria. After describing the algorithm, we test it using the 1-minute-tick data for Cardano's price on Binance. We see that the agent performs better than trading with randomly chosen actions on each timestep. And it does so when tested on the whole dataset as well as on different subsets, capturing different market trends.