One bot, two-player match
You manage one farm. Every scored episode pairs your bot with another bot managing a separate farm.
Episodeyour bot vs opponent bot
Kaggriculture
Build the winning farm.
Finish 720 turns with more coins in the bank.
30in-game days
24turns per day
3,000starting coins
10 × 10farm grid
Essentials
How scoring works
Compare bank at turn 720
Higher bank wins. Equal bank ties. Lower bank loses. Unsold inventory is worth zero.
Outcomefinal bank comparison
Outcomes build rating
Kaggle adjusts skill rating across many episodes. The size of the coin lead does not affect that rating.
Leaderboardskill rating
Setup
Ready to run
Live snapshot · Aug 14
Top agents
One public replay sampled per agent. Observed behavior—not private implementation.
013267.4rating
カワシギ
Balanced tempo- D11
12 melons · 8 cows · 4 sheep
- D21
13 strawberries · staged third quadrant
- End
102,222 bank · near-empty inventory
Pattern: balanced production, staged expansion, disciplined exit.
023127.6rating
researchstudio.site
Expansion rush- D11
3 quadrants · 36 sprouts · 8 cows
- D21
20 strawberries · 10 cows
- End
126,350 bank · inventory cleared
Pattern: early land, dense crops, aggressive capital deployment.
033108.8rating
Ueddy
Livestock compound- D11
12 melons · 6 cows · 6 sheep
- D21
4 quadrants · 18 pastures · 12 sheep
- End
80,832 bank · decisive sampled win
Pattern: full-grid expansion, sheep-heavy compounding, wheat support.
Approach A · v0
Balanced tempo
First local benchmark complete.
- D00–12
Melon cash loop
Ten melons, five wheat plots, six temporary hands.
- D11–13
Stage the compound
Build four pastures and unlock the second quadrant.
- D13–26
Cattle + strawberries
Feed and care for cattle while recurring crops mature.
- D27–29
Intended exit · not implemented
v0 still hires and buys seeds; a hard liquidation gate is the next change.
Episodes 2010 seeds · both seats
Finished ahead 20 / 20against the starter bot
Average final bank 31,337
Runtime failures 0
| Seat | Episodes | Finished ahead | Average final bank |
|---|---|---|---|
| First | 10 | 10 / 10 | 31,622 |
| Second | 10 | 10 / 10 | 31,052 |
Local benchmark: Balanced Tempo v0 versus Kaggle's starter bot. This is matchup evidence, not a Kaggle leaderboard rating.
Best run · seed 3 · second seat
30-day timeloop
Episode outcome rule
Day 00 · behind by 830
Our bot must finish turn 720 with more banked coins than the opponent bot.
A tie is only possible when both bots finish with exactly the same bank. Cattle, strawberries, and clean exit are internal strategy checkpoints—not official win conditions.
Current bank comparison 2,130 vs 2,960
Cattle engine 0 / 4
Strawberry field 0 / 15
Clean exit Not due
MelonStrawberryWheatCowWorker
Daily trace
What changed and why
| Day | Phase | Bank | Change | What happened | Why |
|---|
- Signal 01
The phase mix works against the starter
Balanced Tempo finished ahead in all 20 head-to-head episodes.
- Signal 02
Seat order is not driving the result
Average bank differed by only 570 coins between first and second seat.
- Signal 03
Execution is still inconsistent
Final bank varied by 14,352 coins across seeds.
- Signal 04
The target build is often incomplete
Three runs ended with three cows; only eight reached ten strawberry plots.
Saved in this browser
Approach B
Expansion rush
Trade early liquidity for productive surface area.
- 01 · Buffer
Fund the rush
Preserve cash for land and seeds.
- 02 · Unlock
Buy three quadrants
Expand before day 11.
- 03 · Fill
Dense strawberry cycle
Convert surface area into peak production.
- 04 · Convert
Stop reinvestment
Harvest and sell before turn 720.
Approach C
Livestock compound
Build recurring yield around feed reliability.
- 01 · Feed
Secure wheat
Hold a daily safety reserve.
- 02 · Build
Pasture network
Expand only with labor capacity.
- 03 · Compound
Sheep + cattle
Collect products and fertilizer on route.
- 04 · Clear
Final collection
Empty shed and inventories.
Reference
Game mechanics
Objective
What we are optimizing
Official targetFinish with more bank than the opponent bot
Every episode is head-to-head. Unsold crops, animals, and shed inventory do not count.
OfficialSkill rating
Built from head-to-head episode outcomes.
DiagnosticFinal bank
Shows whether the farm economy is improving.
ReliabilityRuntime failures
Errors, timeouts, and invalid actions.
Environment
Fixed variables
The agent observes these rules; it cannot change them.
Match2 players · 720 turns
30 days with 24 turns each.
Starting state3,000 coins · 1 quadrant
Northwest 5 × 5 begins unlocked.
Board10 × 10 tiles
Three more quadrants cost 1,000 / 2,000 / 4,000.
Storage100 shed items
Overflow at day-end is discarded.
Market limit10 orders per turn
Both players affect shared prices.
Basic needs2 missed days
Unwatered plants become weeds; unfed animals escape.
Labor cost1, 1, 2, 3, 5…
Daily hires follow Fibonacci pricing and reset each day.
World noise0.5% weed chance
Shops unlock every 3 days and consume stock every 4 turns.
Policy
Current decision tree
Lower number wins when tasks compete.
- 01Is value ready?HARVEST
Harvest crops or animal output before it decays or caps.
- 02Is daily survival work due?WATER · PICKUP · FEED
Water plants, collect feed, and feed cattle.
- 03Can an animal earn a bonus?CARE
Care after feeding to increase the next production event.
- 04Has the cattle phase started?BUILD · PLACE
Build four pastures and place purchased cows.
- 05Is a planned crop tile empty?PLANT
Plant wheat plus melons before day 13; strawberries after.
- 06No local task?MOVE · DROP · PASS
Move toward the next target; after hour 20, return carried output to the shed.
Market and phase gates
Always
Sell completed output already in the shed.
Hour 00
Hire six temporary hands for the day.
Days 00–12
Target 10 melons + 5 wheat plots.
Day 11+
Target 4 cows and keep at least 8 wheat feed in reserve.
Day 13+
Target 15 strawberries; buy the first expansion when bank ≥ 2,200.
Days 27–29
No gate yet. The agent continues reinvesting—this is the known exit defect.
Agent chooses
Portfolio, worker count, routing, crop timing, land purchases, market orders, and when to stop reinvesting.
Agent observes
Both farms, shared prices, town demand, current day/hour, its private seeds, shed, and carried inventory.
Agent cannot control
Episode seed, opponent actions, shop unlock sequence, weed rolls, rule constants, and the 720-turn deadline.
Board
10 × 10 farm
Economy
Production
| Asset | Buy-in | Base price | First yield | Cadence / life | Daily obligation |
|---|
Prices move with supply and town demand.
Invariants
Never miss
2 daysmissed watering or feed loses the asset
100 itemsshed capacity
Turn 720everything must be sold
Submission
Bot contract
def agent(obs):
return {
"farmer": ["PASS"],
"hands": [],
"market": []
}Entry point
main.py at archive root with agent(obs)Runtime1.6 vCPU · 6.5 GiB RAM · 8 GiB disk
NetworkNo ingress or egress during evaluation
ValidationFirst match is your agent versus itself
Evidence
Experiment log
One change. Enough head-to-head episodes. Clear decision.
Trend
Outcome rate
Log a matchup to start.
History
Runs
No experiments yet
Start with a baseline.
Priorities
Next move
Impact × confidence ÷ effort.
Backlog