Ctc Executioner Save

Master Thesis: Limit order placement with Reinforcement Learning

Project README

Order placement with Reinforcement Learning

CTC-Executioner is a tool that provides an on-demand execution/placement strategy for limit orders on crypto currency markets using Reinforcement Learning techniques. The underlying framework provides functionalities which allow to analyse order book data and derive features thereof. Those findings can then be used in order to dynamically update the decision making process of the execution strategy.

The methods being used are based on a research project (master thesis) currently proceeding at TU Delft.

Documentation

Comprehensive documentation and concepts explained in the academic report

For hands-on documentation and examples see Wiki

Usage

Load orderbooks

orderbook = Orderbook()
orderbook.loadFromEvents('data/example-ob-train.tsv')
orderbook.summary()
orderbook.plot(show_bidask=True)

orderbook_test = Orderbook()
orderbook_test.loadFromEvents('data/example-ob-test.tsv')
orderbook_test.summary()

Create and configure environments

import gym_ctc_executioner
env = gym.make("ctc-executioner-v0")
env.setOrderbook(orderbook)

env_test = gym.make("ctc-executioner-v0")
env_test.setOrderbook(orderbook_test)
Open Source Agenda is not affiliated with "Ctc Executioner" Project. README Source: mjuchli/ctc-executioner

Open Source Agenda Badge

Open Source Agenda Rating