learned-value-beats-heuristic-augmentation

learned-value-beats-heuristic-augmentation is a skill for Claude Code, Codex from topprismdata/cultivating-ml-agent. It costs 144 tokens per session (1,657 once invoked), scanned A, original, MIT.

A machine-learning approach for improving a strong rule-based game agent by combining a learned value model with deeper search. A value model estimates how good a game position is, while search examines possible future moves.

In plain words
What is it for?
Use it when a hand-crafted game strategy is already strong but basic machine-learning upgrades make decisions worse, especially in turn-based card-game agents.
Why use it?
Simple data augmentation, imitation of winning moves, or shallow search can disrupt a good heuristic instead of improving it.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it when a hand-crafted game strategy is already strong but basic machine-learning upgrades make decisions worse, especially in turn-based card-game agents.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/topprismdata/cultivating-ml-agent/learned-value-beats-heuristic-augmentation
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add topprismdata/cultivating-ml-agent --skill learned-value-beats-heuristic-augmentation
Clone the repo
git clone --depth 1 https://github.com/topprismdata/cultivating-ml-agent

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for learned-value-beats-heuristic-augmentation

README.md
[![agentmods](https://agentmods.dev/badge/skills/topprismdata/cultivating-ml-agent/learned-value-beats-heuristic-augmentation/github.svg)](https://agentmods.dev/skills/topprismdata/cultivating-ml-agent/learned-value-beats-heuristic-augmentation)
Your own site
<a href="https://agentmods.dev/skills/topprismdata/cultivating-ml-agent/learned-value-beats-heuristic-augmentation"><img src="https://agentmods.dev/badge/skills/topprismdata/cultivating-ml-agent/learned-value-beats-heuristic-augmentation/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for learned-value-beats-heuristic-augmentation

Your own site · 80×15
<a href="https://agentmods.dev/skills/topprismdata/cultivating-ml-agent/learned-value-beats-heuristic-augmentation"><img src="https://agentmods.dev/badge/skills/topprismdata/cultivating-ml-agent/learned-value-beats-heuristic-augmentation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 144 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,657 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00144 $0.01657
Opus 5 $0.00072 $0.00829
Sonnet 5 $0.00029 $0.00331
Haiku 4.5 $0.00014 $0.00166

Measured 11d ago against content hash a7f96f94ee07, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

learned-value-beats-heuristic-augmentation scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/examples/learned-value-beats-heuristic-augmentation/SKILL.md · 125 lines

How it starts

The opening of the file, as written. The whole thing — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Learned Value Function + Search Beats Heuristic Augmentation

When a strong hand-crafted heuristic resists every naive ML augmentation (search, behavioral cloning, type-classification), the failure isn't data volume or feature richness — it's the absence of a learned value function. The breakthrough comes from combining (a) a learned value network as a leaf evaluator with (b) sufficient search depth. Neither alone is enough.

This skill captures the hard-won methodology from a multi-week PTCG (Pokémon TCG) AI Battle project where a rank-304 rule-based agent (nursrijan_adv) defeated every naive ML upgrade — until a ReBeL-style value network + 2-ply search finally beat it.

The Anti-Pattern: Strong Baselines Resist Crude Augmentation

A strong heuristic encodes deep domain knowledge (matchup awareness, sequencing, timing). Naive ML augmentation disrupts its internal coherence:

  • Search with a hand-crafted eval overrides good heuristic picks with worse ones (the eval is cruder than the heuristic it's trying to improve).
  • Behavioral cloning on winners picks the wrong move ~45% of the time, and errors compound across a game. 10× more data doesn't fix this — 437K rows still lost 98%.
  • Type-guided policy (predict action TYPE, let heuristic pick within type) breaks the heuristic's coherent sequencing — 6% win rate, worse than random.

Common failure signal: every augmentation approach lands in the same 5-45% range regardless of data volume or feature richness. If you see this, you're not fighting a data problem — you're fighting the coherence problem.

The Breakthrough: V_net + Search Depth, Together

The combination that finally wins:

  1. Train a value network V(state) → P(win). This is a classification problem (who's-ahead), not an imitation problem. Use existing game logs with outcome labels. Targets: >70% accuracy, well-calibrated win-probabilities.
  2. Use V_net as the leaf evaluator inside search (MCTS / minimax / forward-rollout). The search provides depth (sees the opponent's response); V_net provides the learned judgment at the leaf.
  3. Override the heuristic only when V_net is confident (margin ≥ 0.03), so the heuristic's coherence is preserved on uncertain decisions.

Read the full file on GitHub · 125 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 11d ago First seen · 125 lines · 144 tokens per session scan A a7f96f94ee07

Subscribe to this mod's changes

learned-value-beats-heuristic-augmentation is a skill published in the GitHub repository topprismdata/cultivating-ml-agent (5 stars, last pushed 14d ago), licensed MIT. It adds 144 tokens to every session and 1,657 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

huggingface-hub

Hugging Face Hub CLI (hf) — search, download, and upload models and datasets, manage repos, query datasets with SQL, deploy inference endpoints, manage Spaces and buckets.

braxtonROSE4/zorro-agent · 43 tokens

tensorboard

Visualize training metrics, debug models with histograms, compare experiments, visualize model graphs, and profile performance with TensorBoard - Google's ML visualization toolkit.

davila7/claude-code-templates · 32 tokens

mlflow

Track ML experiments, manage model registry with versioning, deploy models to production, and reproduce experiments with MLflow - framework-agnostic ML lifecycle platform.

davila7/claude-code-templates · 33 tokens

datachain-knowledge

Use whenever datasets, cloud storage buckets, or data pipelines are mentioned — creating, saving, querying, listing, exploring, deleting, or processing data in S3, GCS, Azure Blob, or local storage. Also use when running any script that may create datasets as a side effect. Maintains a knowledge base at dc-knowledge/…

datachain-ai/datachain · 104 tokens

install-openviking-memory

Install and configure the OpenViking long-term memory plugin for OpenClaw via natural conversation. Once installed, the plugin automatically captures facts from chats and recalls relevant context before each reply (auto-capture + auto-recall, cross-session). Covers prerequisites, install through OpenClaw's plugin…

volcengine/OpenViking · 191 tokens

pufferlib

Version-aware guidance for PufferLib reinforcement-learning environments, vectorization, policies, PuffeRL training, evaluation, and safe checkpoint review. Use when adapting Gymnasium/PettingZoo environments to published PufferLib 3.0.0 or working with the redesigned native 4.0 source line.

K-Dense-AI/scientific-agent-skills · 65 tokens