GitPlanet

Cheap and reliable Node.js hosting starts at $3/month, and $1/month static HTML hosting

Created with love in Canada, visit hostnodejs.com today

Feel like to post an Ad? Learn Details
All Projects → yazzaoui → A3C-Crypto-Trader

yazzaoui / A3C-Crypto-Trader

Licence: other
Deep Reinforcement Learning A3C Crypto Trading Bot

Programming Languages

python
139335 projects - #7 most used programming language

Labels

reinforcement-learninga3c

Projects that are alternatives of or similar to A3C-Crypto-Trader

Tensorlayer
Deep Learning and Reinforcement Learning Library for Scientists and Engineers 🔥
Stars: ✭ 6,796 (+19888.24%)
Mutual labels:  a3c
Deep Reinforcement Learning With Pytorch
PyTorch implementation of DQN, AC, ACER, A2C, A3C, PG, DDPG, TRPO, PPO, SAC, TD3 and ....
Stars: ✭ 1,345 (+3855.88%)
Mutual labels:  a3c
Minimalrl
Implementations of basic RL algorithms with minimal lines of codes! (pytorch based)
Stars: ✭ 2,051 (+5932.35%)
Mutual labels:  a3c
Slm Lab
Modular Deep Reinforcement Learning framework in PyTorch. Companion library of the book "Foundations of Deep Reinforcement Learning".
Stars: ✭ 904 (+2558.82%)
Mutual labels:  a3c
Torch Ac
Recurrent and multi-process PyTorch implementation of deep reinforcement Actor-Critic algorithms A2C and PPO
Stars: ✭ 70 (+105.88%)
Mutual labels:  a3c
A3c Pytorch
PyTorch implementation of Advantage async actor-critic Algorithms (A3C) in PyTorch
Stars: ✭ 108 (+217.65%)
Mutual labels:  a3c
Btgym
Scalable, event-driven, deep-learning-friendly backtesting library
Stars: ✭ 765 (+2150%)
Mutual labels:  a3c
A3c continuous
A continuous action space version of A3C LSTM in pytorch plus A3G design
Stars: ✭ 223 (+555.88%)
Mutual labels:  a3c
Reinforcement learning
Reinforcement learning tutorials
Stars: ✭ 82 (+141.18%)
Mutual labels:  a3c
Machin
Reinforcement learning library(framework) designed for PyTorch, implements DQN, DDPG, A2C, PPO, SAC, MADDPG, A3C, APEX, IMPALA ...
Stars: ✭ 145 (+326.47%)
Mutual labels:  a3c
A3c
MXNET + OpenAI Gym implementation of A3C from "Asynchronous Methods for Deep Reinforcement Learning"
Stars: ✭ 9 (-73.53%)
Mutual labels:  a3c
Policy Gradient Methods
Implementation of Algorithms from the Policy Gradient Family. Currently includes: A2C, A3C, DDPG, TD3, SAC
Stars: ✭ 54 (+58.82%)
Mutual labels:  a3c
Reinforcementlearning Atarigame
Pytorch LSTM RNN for reinforcement learning to play Atari games from OpenAI Universe. We also use Google Deep Mind's Asynchronous Advantage Actor-Critic (A3C) Algorithm. This is much superior and efficient than DQN and obsoletes it. Can play on many games
Stars: ✭ 118 (+247.06%)
Mutual labels:  a3c
Bombora
My experimentations with Reinforcement Learning in Pytorch
Stars: ✭ 18 (-47.06%)
Mutual labels:  a3c
Tensorflow Rl
Implementations of deep RL papers and random experimentation
Stars: ✭ 176 (+417.65%)
Mutual labels:  a3c
Super Mario Bros A3c Pytorch
Asynchronous Advantage Actor-Critic (A3C) algorithm for Super Mario Bros
Stars: ✭ 775 (+2179.41%)
Mutual labels:  a3c
Easy Rl
强化学习中文教程，在线阅读地址：https://datawhalechina.github.io/easy-rl/
Stars: ✭ 3,004 (+8735.29%)
Mutual labels:  a3c
Reinforcement Learning
Minimal and Clean Reinforcement Learning Examples
Stars: ✭ 2,863 (+8320.59%)
Mutual labels:  a3c
Rlcycle
A library for ready-made reinforcement learning agents and reusable components for neat prototyping
Stars: ✭ 184 (+441.18%)
Mutual labels:  a3c
Baby A3c
A high-performance Atari A3C agent in 180 lines of PyTorch
Stars: ✭ 144 (+323.53%)
Mutual labels:  a3c
View All Similar Projects ➔

A3C-Crypto-Trader

Deep Reinforcement Learning A3C Crypto Trading Bot

The trading logic is in ai.py. The market data scraper in scrap.py , currently only using bitmex data.

The bot was succesfully working with simple hand created market datawith a 3-layer FNN, learning profitable strategies under 30 min. On real world data, the learning time is way too high.

The RL architecture is based on google deepmind's A3C. The trading rules (BUY/SELL/HOLD) were kept simples for maximum generalization. Activation function is Tanh, ReLu was found not effective at all after much experimentation.

It's currently performing a grid-search to find out the best hyper-parameters, simulations results are VERY sensitive to those values.

TODO :

  • Try out an LSTM network.
  • Implement generative algorithm to find optimal hyperparameters.
  • Try out RAINBOW.

Created by Youssef Azzaoui based on Google Deepmind's work. If any question, please contact me [email protected]

Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].