Rl Reward Agent Skill

RL Algorithm + Task type?
│
├── GRPO / REINFORCE — Verifiable task (math, code, structured output)
│   └── → POINTWISE  ✅  (FunctionGrader, exact score, zero LLM cost)
│
├── GRPO / REINFORCE — Subjective task (instruction following, dialogue, summarization)
│   └── → PAIRWISE TOURNAMENT  ✅  (compare each rollout vs all others in group,
│                                    reward = net win rate within group)
│
├── DPO / IPO / SLiC — need (chosen, rejected) pairs
│   └── → PAIRWISE  ✅  (two-way comparison, return winner/loser)
│
└── Best-of-N / reranking — rank N candidates
    └── → LISTWISE  ✅  (single call ranks all N at once)

Cost constraint?
├── Low budget
│   └── FunctionGrader (free) → pointwise; or pairwise with small judge model
│
├── Medium budget
│   └── Pointwise: 2–3 LLM graders + WeightedSumAggregator
│   └── Pairwise tournament: 1 LLM judge, N*(N-1)/2 comparisons per group
│
└── High quality / no cost limit
    └── Pointwise voting (3–5 calls) or pairwise with strong judge + debiasing

pip install py-openjudge

def normalize(score: float, min_score: float, max_score: float) -> float:
    """Map [min_score, max_score] → [0.0, 1.0]."""
    if max_score == min_score:
        return 0.0
    return (score - min_score) / (max_score - min_score)

# LLM graders (common/*) return 1–5 → normalize to 0–1
reward = normalize(result.score, min_score=1, max_score=5)

# FunctionGrader / text graders already return 0–1 → no normalization needed

Grader type?
│
├── Deterministic (FunctionGrader, StringMatch, CodeExecution, etc.)
│   └── → Direct  (zero variance, no need for aggregation)
│
├── LLM grader — Pointwise scoring
│   │
│   ├── Budget limited / speed critical
│   │   └── → Direct  (accept variance, 1× cost)
│   │
│   ├── Discrete scores (1–5 integer, pass/fail, binary)
│   │   └── → Voting  (majority vote, robust to outliers, N× cost)
│   │
│   └── Continuous / fine-grained scores (need precise ranking)
│       └── → Average  (mean, preserves signal, N× cost)
│
└── LLM grader — Pairwise GRPO tournament
    └── → GRPOTournament  (all-pairs comparison, net win rate)

from openjudge.evaluation_strategy import VotingEvaluationStrategy

grader = CorrectnessGrader(
    model=model,
    strategy=VotingEvaluationStrategy(num_votes=3, tie_breaker="closest_to_mean"),
)
# Now each call internally runs 3 LLM evaluations and returns the most common score

from openjudge.evaluation_strategy import GRPOTournamentEvaluationStrategy

strategy = GRPOTournamentEvaluationStrategy(debiased=False)
results = await strategy.execute(
    pairwise_grader.aevaluate,
    query="Write a haiku about the ocean.",
    responses=["rollout_1", "rollout_2", "rollout_3", "rollout_4"],
)
rewards = [r.score for r in results]  # net win rates in [-1.0, 1.0]