rl
  • My Journey into Reinforcement Learning and Trading
  • ☺️Foundations of RL with Applications in Finance
    • Abstraction,Immutability,'dataclasses',Type Checking
    • Type variables(generics)
  • Functionality
  • Abstracting over Computation
  • Markov Models for Stock Prices: A Trade-Off Between Simplicity and Accuracy
  • Understanding Markov Processes and their Representations
  • Navigating State Transitions and Rewards: PR, P, RT, and R in MRP
  • Value Function Computation in Markov Reward Processes
  • State-Value and Action-Value Functions
  • module 1 synthesis
  • Strategies for Combining and Coordinating Multiple Utility Functions in Algorithmic Trading: A Multi
Powered by GitBook
On this page
  • Why Reinforcement Learning?Well, Why Not?
  • What's the Endgame?
  • The Navigator
  • Facing the Beasts!
  • Sailing Against the Wind
  • Stay Tuned!

My Journey into Reinforcement Learning and Trading

Hello, World! I'm ZHANG NAN, a seasoned trader with 13 years of experience. Through the turbulent markets, I've learned to navigate towards steady returns. While I'm no Scrooge McDuck swimming in gold coins, I've managed to stay afloat in the financial seas while balancing work, family, and my eclectic array of interests. Now, I'm embarking on a new journey to explore the intersection of reinforcement learning (RL) and trading.

Why Reinforcement Learning?Well, Why Not?

In my day-to-day work, the thrill of a challenge has faded like an old photograph. The thrill of a challenge has been replaced by the humdrum of routine. So, why RL? Simply put, I'm yearning for some spicy challenges to my daily mix. Plus, RL has the potential to revolutionize how we play the trading game, and who doesn't love a good game-changer?

What's the Endgame?

The destination of this journey? Well, if I knew that, it wouldn't be much of an adventure, would it? I'm diving headfirst into these uncharted waters, and who knows where the currents will take me. But one thing's for sure – this journey promises to add new colors to the canvas of life.

The aim is to construct a trading contraption that cleverly employs RL. Not so much a dream, but an engaging challenge that promises not only to save some precious time but also add a dash more of wealth to my treasury - something I'd happily spend on other exciting escapades.

The Navigator

My initial compass is the book "Foundations of Reinforcement Learning with Applications in Finance" by Ashwin Rao and Tikhon Jelvis. But let's not kid ourselves – one map does not a journey make. As I explore further, I'll undoubtedly encounter new learning resources and unexpected intellectual challenges that will enrich this expedition.

Facing the Beasts!

Trading might have been a wild beast that I've tamed, but RL and Python are entirely different creatures. The path ahead is lined with cryptic mathematical riddles and strange Pythonic spells. But as they say, what doesn't kill you makes you stronger, right?

Sailing Against the Wind

Between a demanding day job and the challenge of balancing my interests and family life, it's like trying to sail against the wind. But who says an adventure should be rushed? Even if this turns into a moonlit quest with the stars as our guide, we're in for a long but exciting journey.

Stay Tuned!

Expect regular logs of my journey right here. The highs, the lows, the aha moments, and the oh-no moments – you'll find it all here. Who knows, my journey might just inspire you to embark on your own adventure.

NextAbstraction,Immutability,'dataclasses',Type Checking

Last updated 1 year ago