DecktraceCard-game simulation and training
More navigation links

Decktrace: OPTCG · fixed Imu mirror

One Piece
Card Game

Decktrace implements a fixed One Piece Card Game matchup for self-play training. Candidate policies are evaluated using paired games, uncertainty estimates, legal-action checks, and comparisons with earlier policies.

The browser demo runs an earlier bundled policy, separate from the training results below.

Play the browser policy Training status Review historical records
Measured training champion

Archive-safe champion

The recorded comparison scored 53.2% against its reference policy. The conservative estimate is 50.3% after accounting for uncertainty.

Paired score
53.2%
Observed point share in the controlled matchup.
Adjusted lower bound
50.3%
Conservative floor after uncertainty.
Paired openings
768
Common openings tested from both seats.
Invalid actions
0
Promotion requires zero.
Evaluation record and behavior checks

Controlled paired evidence cleared promotion and archive gates.

Subject: champion generation-019-candidate-03 · Opponent: generation-018-candidate-02 · 1,536 games

Automatic promotion gateAdjusted lower bound > 50%

Promotion also checks invalid actions and comparisons with archived champions. Qualification in the original client requires separate testing.

  • Archive safety gatePass
  • Native qualificationNot run
Observed behavior
Critical misses
0 forced lethal · 1 immediate survival
Counts; opportunity totals are not recorded.
Event plays
100% effectful · 0% trash-only
5,410 total event plays
Counter spend
95.4% avoided hit · 4.6% still hit
27,648 resolved spend windows
DON attachment actions
9.5% to rested · 9.6% already attacked
15,330 attachment actions

The browser demo packages Generation 11 separately from this training feed. Evidence is scoped to the checked-in Imu mirror and simulator runtime. Play the browser policy · Open the full campaign.

The game itself

Game rules and tested matchup

Two seats

One Piece Card Game is a two-player trading-card game. Players deploy Characters, attach DON!! to raise power, attack the opposing Leader, and answer attacks with counters, blockers, and effects. This project holds both players to the same checked-in Imu leader and deck so policy changes can be measured cleanly.

Players
2
Current profile
Imu mirror
Result
Win / loss
Action families
8
Information
Public board, resources, Leader and Life counts; private hands and hidden cards stay outside the opponent view
Agent boundary
A masked shared-action policy chooses only actions legal in the current player-visible state
Evaluation unit
Two games on one opening, with challenger and incumbent swapping seats

Game boundary: the capability claim is intentionally limited to this checked-in mirror matchup, not arbitrary leaders or decks.

Champion evidence

Evaluation results

Decktrace keeps training, comparison, and runtime evidence connected to the exact game profile and checkpoint that produced it.

Champion selectionAutomatedSelection from game results
Decision path

Automated policy selection

Training, comparison, and checkpoint publication stay automated; no human game, expert label, or manual promotion vote is required.

Training
Self-play
without labels
Comparison
Paired openings
and seats
Play
Packaged
browser actor
Evaluation boundaryExplicitFixed simulator matchup
What the result means

Tested matchup and limitations

The evidence applies to the checked-in Imu mirror. Native execution, other decks, and broad live-game strength require their own evidence.

Rules
Fixed Imu
mirror
Runtime
Python
simulator
Coverage
Scoped
claim
Continue exploringAvailableTraining and engineering context
What is established

Simulator evaluation and browser demo

The browser demo uses a checkpoint evaluated in the simulator. Qualification in the original game client has not been established.

Preserved

Automated campaign execution

Execution
Deterministic headless games, masked legal actions, resumable training, and source-bound checkpoints
Selection
Common openings, paired seats, fresh lower bounds, zero-tolerance invalid actions, and archive opponents
Current result
The latest champion cleared paired-seat promotion and archive confirmation in the checked-in simulator; the browser bundle has a separate version and source record

See how this fits the Decktrace platform tour.

Technical evidence

Original-client execution checks

A historical six-game check showed that the Generation 19 checkpoint could execute in the native runtime. It did not establish rules parity or strength in the original game.

Native execution record

A historical six-game smoke executed the Generation 19 checkpoint against the recorded native runtime and finished with both native inventories matching the exact training deck. This is not per-game deck, card-rule, or Python/native parity evidence. OP13-097 may legally pay its optional 5 DON and then resolve no K.O.

Inspectable artifact
Complete source-bound native execution path
Purpose
Checkpoint execution and observation smoke, not the default training backend
Not established
Exhaustive rules parity, arbitrary-deck strength, or a user-qualified OPTCG champion
Engineering case studyPlatform Atlas