A deep reinforcement learning trader without offline training

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 consider 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 1-minute-tick price data for 4 major cryptocurrencies from 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 for a given market as well as on different subsets, representing different market trends.