markov-regime-features

Community

Debug Markov regime features in RL observations.

Authorsmith6jt-cop
Version1.0.0
Installs0

System Documentation

What problem does it solve?

RL observation plots showed constant Markov regime features due to uniform priors or stale state; this Skill guides you to implement stateful Markov tracking to produce dynamic regime probabilities.

Core Features & Use Cases

  • Use InferenceObservationBuilder for stateful Markov tracking across price history.
  • Build observations so vol_probs and trend_probs evolve with data.
  • Visualize regime evolution and diagnose stationary priors.

Quick Start

Create an InferenceObservationBuilder(window=100, use_gpu_markov=True) and call build(prices=..., high=..., low=...). Access vol_probs and trend_probs to inspect regime probabilities.

Dependency Matrix

Required Modules

None required

Components

Standard package

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: markov-regime-features
Download link: https://github.com/smith6jt-cop/Skills_Registry/archive/main.zip#markov-regime-features

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 223,000+ vetted skills library on demand.