clay-borg/games/ground/examples/attack-value.rs

//! F17's reproduction: what is ATTACK worth, in each scoring mode?
//!
//! The maintainer reported *"there is no incentive to play attacks as long
//! as I have positive cards"*. F17 sat as a note because nothing
//! demonstrated it. This is the artifact.
//!
//! **`GreedyPolicy` plays ATTACK zero times, and that measures our bot.**
//! `bot.rs` ranks `Action::Attack => 10`, below everything else. Reporting
//! "the game gives no incentive" from a policy programmed to rank attack
//! last would be CB-WP-0025's C4 error again — one policy's behaviour
//! presented as the game's.
//!
//! So this varies **exactly one number**: ATTACK's rank in an otherwise
//! identical policy. 10 is greedy's. 75 puts it above SUPPORT and below
//! INVESTIGATE — *attack when convenient*. 95 puts it above SOLVE —
//! *attack whenever legal*.
//!
//! And it asks the question in **all three scoring modes**, because Blame
//! costs *personal* score: ATTACK may be worthless in the co-op mode and
//! earn its place in GR-E03 or GR-E04.

use cb_game_runtime::{ScenarioGame, Setup};
use cb_kernel::PlayerId;
use games_ground::bot::{play, Choice, GreedyPolicy, Policy};
use games_ground::{Action, GroundCommand, GroundState, ScoringMode};

/// Greedy's ordering with ATTACK's rank as a parameter.
///
/// A copy of the ranking rather than a call into it: `GreedyPolicy::rank`
/// is private, and the point is to vary one number while holding every
/// other preference identical.
struct Attacker(i32);

impl Policy for Attacker {
    fn name(&self) -> &'static str {
        "attacker"
    }
    fn choose(
        &mut self,
        state: &GroundState,
        seat: PlayerId,
        legal: &[GroundCommand],
        _may_pass: bool,
    ) -> Choice {
        let gated = state
            .players
            .get(&seat)
            .is_some_and(|p| p.stress >= 4 && !p.freedom_gate_lifted);
        let rank = |c: &GroundCommand| -> i32 {
            match c {
                GroundCommand::SelectAction {
                    action, problem, ..
                } => match action {
                    Action::Ground if gated => 100,
                    Action::Attack => self.0, // the one varying number
                    Action::Solve
                        if problem
                            .and_then(|p| state.problems.get(&p))
                            .is_some_and(|p| p.claimed_by.is_some()) =>
                    {
                        5
                    }
                    Action::Solve => 90,
                    Action::Investigate => 80,
                    Action::Support => 70,
                    Action::Ground => 60,
                },
                GroundCommand::SpendFreedom => {
                    if gated {
                        96
                    } else {
                        0
                    }
                }
                GroundCommand::Reveal | GroundCommand::Resolve | GroundCommand::EndRound => -1,
                _ => 50,
            }
        };
        let mut best = 0usize;
        for (i, c) in legal.iter().enumerate() {
            if rank(c) > rank(&legal[best]) {
                best = i;
            }
        }
        Choice::Command(best)
    }
}

/// `(games, good outcomes, attacks, DARVO armings)` over 200 seeds.
///
/// **`games` is reported, not assumed to be 200.** A rules variant can
/// make the engine refuse a position, and a harness that skips those
/// silently reports "nobody won" for a run in which nobody played.
fn sweep(
    mode: ScoringMode,
    variant: games_ground::Variant,
    players: u8,
    mk: &dyn Fn(u8) -> Vec<Box<dyn Policy>>,
) -> (u32, u32, u32, u32) {
    let (mut games, mut won, mut atk, mut darvo) = (0, 0, 0, 0);
    let mut errs: Vec<String> = Vec::new();
    let mut setup_fails = 0u32;
    for seed in 0..200u64 {
        let Ok(mut st) = GroundState::setup(
            &Setup {
                players,
                preset: format!("standard-{players}p"),
                patch: Default::default(),
            },
            seed,
        ) else {
            setup_fails += 1;
            continue;
        };
        st.mode = mode;
        // CB-WP-0038 T03: the SAME instrument measures both rule sets in
        // the same run. Two harnesses would compare harnesses.
        st.variant = variant;
        let mut ps = mk(players);
        // CB-WP-0038 T03: a game the engine REFUSES is not a game the
        // table lost, and `else { continue }` made the two identical.
        // H1's first run showed won/atk/darvo all exactly 0 at 3+ seats,
        // which is the signature of every game being discarded rather
        // than played -- so the count is now reported, not swallowed.
        let g = match play(st, &mut ps) {
            Ok(g) => g,
            Err(e) => {
                errs.push(format!("{e:?}"));
                continue;
            }
        };
        games += 1;

        // In the co-op mode the table wins together. In the other two the
        // question is whether SEAT 0 is among the winners — because that
        // is what an individual player's incentive turns on, and ATTACK is
        // an individual's choice.
        let good = match mode {
            ScoringMode::SharedGround => g.state.outcome.as_ref().is_some_and(|o| o.group_success),
            _ => g
                .state
                .outcome
                .as_ref()
                .is_some_and(|o| o.winners.contains(&PlayerId(0))),
        };
        if good {
            won += 1;
        }
        for (_, c) in &g.steps {
            if let GroundCommand::SelectAction {
                action: Action::Attack,
                ..
            } = c
            {
                atk += 1;
            }
        }
        for e in &g.events {
            if matches!(e, games_ground::GroundEvent::DarvoTriggered { .. }) {
                darvo += 1;
            }
        }
    }
    if setup_fails > 0 {
        eprintln!("  !! {setup_fails} of 200 SETUPS failed ({players}p)");
    }
    if games != 200 {
        eprintln!("  !! only {games} of 200 games ran ({players}p, {mode:?})");
    }
    if !errs.is_empty() {
        eprintln!(
            "  !! {} of 200 games did not run ({}p): first = {}",
            errs.len(),
            players,
            errs[0]
        );
    }
    (games, won, atk, darvo)
}

fn main() {
    println!("F17 — what is ATTACK worth, in each scoring mode?\n");
    println!("CB-WP-0038 T03: run for BOTH rule sets. ground-game's H1 asks");
    println!("whether problem pressure plus a high-Stress self-soothe make");
    println!("ATTACK and DARVO relevant without making always-ATTACK optimal.\n");
    println!("`won` is group success in SHARED GROUND, and \"seat 0 is among the");
    println!("winners\" in the other two, because ATTACK is an individual's choice");
    println!("and that is what an individual's incentive turns on.\n");

    for (vlabel, variant) in [
        ("BASELINE ground-darvo-r0", games_ground::Variant::Baseline),
        (
            "H1 h1-problem-stress",
            games_ground::Variant::H1ProblemStress,
        ),
    ] {
        println!("================ {vlabel} ================\n");
        for (label, mode) in [
            ("SHARED GROUND (GR-E02, co-op)", ScoringMode::SharedGround),
            (
                "COMMON PROBLEM (GR-E03, semi-co-op)",
                ScoringMode::CommonProblem,
            ),
            ("BONDED COALITIONS (GR-E04)", ScoringMode::BondedCoalitions),
        ] {
            println!("{label}");
            println!("       rank=10 (greedy)    rank=75 (sometimes)  rank=95 (always)");
            println!("seats   won  atk darvo      won  atk darvo       won  atk darvo");
            for players in [2u8, 3, 4, 6] {
                let (_, gw, ga, gd) = sweep(mode, variant, players, &|n| {
                    (0..n)
                        .map(|_| Box::new(GreedyPolicy) as Box<dyn Policy>)
                        .collect()
                });
                let cell = |r: i32| {
                    sweep(mode, variant, players, &move |n| {
                        (0..n)
                            .map(|_| Box::new(Attacker(r)) as Box<dyn Policy>)
                            .collect()
                    })
                };
                let (_, mw, ma, md) = cell(75);
                let (_, aw, aa, ad) = cell(95);
                println!(
                    "  {players}p   {gw:>4} {ga:>4} {gd:>5}     {mw:>4} {ma:>4} {md:>5}      \
                 {aw:>4} {aa:>4} {ad:>5}"
                );
            }
            println!();
        }
    }
    println!("(200 games per cell)");
}