gflownet
Bengio's GFlowNets: Generative Flow Networks that sample proportionally to reward. Diversity over maximization for causal discovery and molecule design.
npx skills add majiayu000/claude-skill-registry --skill gflownet --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# GFlowNet Skill > *"Sample x with probability proportional to R(x), not just maximize R(x)."* > — Yoshua Bengio ## Overview **GFlowNets** (Generative Flow Networks) are a new paradigm: - **RL**: Maximize expected reward → single optimal solution - **MCMC**: Sample from distribution → slow mixing - **GFlowNet**: Learn to sample P(x) ∝ R(x) → fast, diverse sampling ## Core Concept ```latex GFlowNet Objective: ∀ terminal state x: P_θ(x) = R(x) / Z Where: P_θ(x) = probability of generating x via forward policy R(x) = unnormalized reward function Z = partition function (normalizing constant) Key Insight: We DON'T need to know Z to train! ``` ## Architecture ``` ┌─────────────────────────────────────────────────────┐ │ GFlowNet │ ├─────────────────────────────────────────────────────┤ │ Initial State s₀ │ │ │ │ │ ▼ │ │ ┌─────────────┐ │ │ │ Forward │ P_F(s' | s) = learned policy │ │ │ Policy │ │ │ └──────┬──────┘ │ │ │ sample action │ │ ▼ │ │ ┌─────────────┐ │ │ │ Transition │ s → s' │ │ └──────┬──────┘ │ │ │ │ │ ▼ │ │ ┌─────────────┐ │ │ │ Terminal? │───No──▶ continue │ │ └──────┬──────┘ │ │ │ Yes │ │ ▼ │ │ ┌─────────────┐ │ │ │ R(x) │ Evaluate reward │ │ └─────────────┘ │ └───────────
- Overview
- Core Concept
- Architecture
- Training Objectives
- 1. Trajectory Balance (TB)
- 2. Detailed Balance (DB)
- Applications
- 1. Molecule Design
- 2. Causal Discovery
- 3. Combinatorial Optimization
- GF(3) Triads
- Integration with Interaction Entropy
- Key Properties
- References
What does the gflownet skill do?
Bengio's GFlowNets: Generative Flow Networks that sample proportionally to reward. Diversity over maximization for causal discovery and molecule design.
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill gflownet --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.