Welcome to DDQL Optimal Execution’s documentation!

Contents:

• Installation
• Quickstart Guide

Main Objects

Preprocessor(n_periods[, QV, ...])	This class is used to preprocess the data before it is fed into the environment.
ExperienceReplay([capacity])	The ExperienceReplay class is a memory buffer that stores and retrieves experiences for reinforcement learning agents.
State	The class State is a subclass of the built-in dict class.
StateArray(*args)	A class to represent a list of states
DDQL([state_dict, greedy_decay_rate, ...])	The DDQL class inherits from the Agent class.
TWAP(initial_budget[, horizon])	The TWAP class inherits from the Agent class.
Trainer(agent, env, **kwargs)	This class is used to train a DDQL agent in a given environment.
MarketEnvironnement([initial_inventory, ...])	This class represents the environment in which the agent is operating.