Bot for KalshiPajamajoker / reinforcement-learning-for-kalshi-trading
Repository metadata checked 2026-09-23. GitHub was accessible; latest repository push: 2025-12-23. This does not verify current trading compatibility, security, or returns.
What it does
DQN agent for hourly BTC threshold markets. Gymnasium-compatible RL environment; multi-day backtesting with policy comparison (random vs. baseline vs. DQN); Streamlit GUI.
What we learned from it
the RL framing for prediction markets is interesting but reward-shaping is hard. The author's policy comparison framework (always benchmark against a random baseline) is a useful discipline that many ML approaches skip.
Find the author
- Repository: github.com/Pajamajoker/reinforcement-learning-for-kalshi-trading
- GitHub profile: @Pajamajoker
- Website / blog: jpratham.info/
- Author bio: MS AI @ Katz, Yeshiva University | Ex Sr. SWE @ Intangles.ai | Ex SWE @ UBS
Get the free weekly Kalshi flow report
One email every Monday with the past week's Kalshi activity: the largest fills, where size kept accumulating, the biggest movers, and the most traded markets. Numbers and tickers — no picks, no predictions.
You're on the list. The next report goes out Monday.
Bring a strategy. Watch it become a bot.
Join the free live build on September 29 at 6:00 PM Pacific. Bring a market and a rule, or just watch. We’ll build a draft, review the workflow, demonstrate paper mode, and answer your questions.
We'll email the calendar invite and reminders for this webinar. Registering does not create an account. See our Privacy Policy.
Don't want to maintain your own bot?
Bot for Kalshi is the no-code platform for automated prediction-market trading — visual builder, signals, encrypted credentials, kill switch. The infrastructure these open-source projects build, ready to use.
One plan includes the visual builder, paper and live modes, hosted execution, and risk controls. Cancel anytime.