Machine LearningPower
At the start of your turn, draw additional cards.
Is Machine Learning good in Slay the Spire 2?
Machine Learning is a rare Defect power in Slay the Spire 2. In combat it resolves as: At the start of your turn, draw additional cards. It ranks among the strongest cards its class can draft right now, earning a spot at S tier in our Slay the Spire 2 card tier list.
Across 47 recorded runs, decks running it win 50.0% of the time, comfortably clear of the 18.9% average, by 31.1%. It’s a more selective pick, turning up in just 1.2% of decks that could run it. Silent players keep it in 0.2% of their runs, so it’s a familiar sight in those decks. On average it shows up 1.1 times in the decks that take it.
It performs best next to Iteration — together they post a +15.0% swing in win rate. It also has strong chemistry with the relic Bag of Marbles, which moves its win rate by +20.6%. At 1 energy, it’s upgraded in 28.3% of runs and usually joins the deck around floor 17.
That’s 20 wins, 20 deaths, and 7 abandoned runs with it in the deck. The encounter that most often ends a run carrying it is Kaiser Crab Boss, which closes out 6.4% of its appearances. Read on for Machine Learning’s complete synergy, class, and threat breakdown to decide whether it earns a slot in your Defect run.
Machine Learning Win Rate & Pick Rate
Machine Learning’s 50.0% win rate clears the 18.9% all-deck average by 31.1%, the gap charted below.
Run Outcomes with Machine Learning
Machine Learning has 20 wins and 27 losses over 47 tracked runs (42.6% won); abandoned runs count as losses.
- Wins 42.6%
- Losses 57.4%
Best Cards to Pair with Machine Learning
Ranked by win-rate lift, Machine Learning performs best alongside Iteration (+15.0%), Reboot (+13.2%), and Shadow Shield (+12.5%).
Based on small co-occurring samples — treat these as early signals, not final verdicts.
Best Relics for Machine Learning
Machine Learning pairs best with the relics Bag of Marbles (+20.6%), Meal Ticket (+18.8%), and Letter Opener (+16.7%), ranked by win-rate lift.
Bag of Marbles7 runs
Meal Ticket6 runs
Letter Opener5 runs
Red Mask10 runs
Juzu Bracelet8 runs
Ornamental Fan4 runsBased on small co-occurring samples — treat these as early signals, not final verdicts.
Machine Learning Card Details
Machine Learning is a rare power costing 1 energy; it’s upgraded in 28.3% of runs and usually picked up by floor 17.
At the start of your turn, draw additional cards.
What Ends Runs with Machine Learning
Machine Learning’s most common run-enders are Kaiser Crab Boss (6.4%), Queen Boss (4.3%), and Test Subject Boss (4.3%).
- Kaiser Crab Boss6.4% of runs
- Queen Boss4.3% of runs
- Test Subject Boss4.3% of runs
- Infested Prisms Elite4.3% of runs
- Decimillipede Elite4.3% of runs
Get the Winning Edge
Real-time overlays, automatic match tracking, and exclusive tools — everything you need to climb, free on your PC.
- In-game overlays
- Automatic match tracking
- Desktop-exclusive tools
Help us maintain accuracy! If you notice incorrect stats, missing data, or any issues, your feedback directly improves the quality of our data for the entire community.
Machine Learning – Frequently Asked Questions
Is Machine Learning good in Slay the Spire 2?
Across 47 tracked runs, Machine Learning has a 50.0% win rate — +31.1% above the average deck. Win rate reflects how often runs that include the card end in victory.
What does Machine Learning do in Slay the Spire 2?
Machine Learning costs 1 energy. At the start of your turn, draw additional cards.
What class is Machine Learning in Slay the Spire 2?
Machine Learning is a Rare Defect Power.
Is Machine Learning worth upgrading in Slay the Spire 2?
Machine Learning can be upgraded at a rest site to improve its effect.
What is the best relic for Machine Learning?
In tracked runs, Machine Learning has performed best alongside Bag of Marbles, which lifts its win rate by +20.6% over 7 runs together.
See Also
Compare Machine Learning with the rest of the best Slay the Spire 2 cards, relics, and classes below.