dp-solver

Name: dp-solver
Author: anubhavg-icpl

Solve a small tabular MDP exactly via policy iteration or value iteration. Report convergence behavior. Use when you need help with dp solver.

by anubhavg-icpl(0) 0 installs

Free

Free account. Installing gives you the manifest plus copy-paste snippets.

See reviews

About

Imported from anubhavg-icpl/vibe (skills/dp-solver/SKILL.md). Install upstream with npx skills add anubhavg-icpl/vibe --skill dp-solver. Copyright stays with the author (CC-BY-NC-SA-4.0).

Given an MDP with a known model, output:

Choice. Policy iteration vs value iteration. Reason tied to |S|, |A|, γ.
Initialization. V_0, starting policy. Convergence sensitivity.
Stopping. Sup-norm tolerance ε. Expected number of sweeps.
Verification. V*(s_0) computed exactly. Greedy policy extracted.
Use. How this baseline will be used to debug/evaluate sampling-based methods.

Refuse to run DP on state spaces > 10⁷. Refuse to claim convergence without a sup-norm check. Flag any γ ≥ 1 on an infinite-horizon task as a guarantee violation.

Use it

Copy one of these into your project. Installing also returns the manifest and these snippets.

# after Install: the listing is in your workspace's routing pool - a plan picks it for its slot
curl -s -X POST https://api.opensmartroute.ai/api/v1/route -H 'Authorization: Bearer $OSR_API_KEY' -H 'Content-Type: application/json' -d '{"text": "...", "plan": true}'

Manifest

An Open Capability Manifest: the router reads it to know what this does, what it costs and when to pick it.

anubhavg-icpl-vibe-dp-solver.ocm.jsonjson

{
  "ocm": "1",
  "id": "anubhavg-icpl-vibe-dp-solver",
  "kind": "skill",
  "name": "dp-solver",
  "description": "Solve a small tabular MDP exactly via policy iteration or value iteration. Report convergence behavior. Use when you need help with dp solver.",
  "publisher": "anubhavg-icpl",
  "version": "1.0.0",
  "capabilities": {
    "domains": [
      "general"
    ],
    "tags": [
      "skill-md",
      "rl",
      "dynamic-programming",
      "bellman",
      "github"
    ],
    "languages": [
      "en"
    ]
  },
  "quality_prior": 0.6,
  "examples": [
    "Solve a small tabular MDP exactly via policy iteration or value iteration. Report convergence behavior. Use when you need help with dp solver."
  ],
  "primary": false,
  "metadata": {
    "source": {
      "provider": "github",
      "repository": "https://github.com/anubhavg-icpl/vibe",
      "path": "skills/dp-solver/SKILL.md",
      "ref": "d51e7ac9a34111cd2e63daed83c2198f91570050",
      "url": "https://github.com/anubhavg-icpl/vibe/blob/d51e7ac9a34111cd2e63daed83c2198f91570050/skills/dp-solver/SKILL.md",
      "key": "anubhavg-icpl/vibe/skills/dp-solver/SKILL.md"
    },
    "license": "CC-BY-NC-SA-4.0"
  },
  "instructions": "Given an MDP with a known model, output:\n\n1. Choice. Policy iteration vs value iteration. Reason tied to |S|, |A|, γ.\n2. Initialization. V_0, starting policy. Convergence sensitivity.\n3. Stopping. Sup-norm tolerance ε. Expected number of sweeps.\n4. Verification. V*(s_0) computed exactly. Greedy policy extracted.\n5. Use. How this baseline will be used to debug/evaluate sampling-based methods.\n\nRefuse to run DP on state spaces > 10⁷. Refuse to claim convergence without a sup-norm check. Flag any γ ≥ 1 on an infinite-horizon task as a guarantee violation.",
  "cost": {
    "context_tokens": 139
  }
}

Fetch it by URL: GET /api/v1/registry/anubhavg-icpl-vibe-dp-solver/manifest?version=1.0.0

About

Use it

Manifest

Reviews