# umnilab/rl_pricing architecture

> Architecture diagram of the GitHub repository umnilab/rl_pricing, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2026-10-01). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/umnilab/rl_pricing
- Repository: https://github.com/umnilab/rl_pricing

## Overview

RL_pricing is a research simulator for reinforcement-learning-based ride-hailing prices. The documented workflow trains a model and then tests it; in the sampled code, main.py configures an Environment and Platform, while runner.py performs simulation steps and updates or evaluates the pricing controller. The main runtime stages are demand response, vehicle/passenger simulation, pricing control, and policy learning. The repository also includes static and dynamic small-grid input datasets. Some main.py loading and dispatch sections are omitted, so dataset wiring and several runtime calls are not fully evidenced here.

Main entry points: [`center.py`](https://github.com/umnilab/rl_pricing/blob/main/center.py) (Pricing platform), [`main.py`](https://github.com/umnilab/rl_pricing/blob/main/main.py) (Experiment setup), [`runner.py`](https://github.com/umnilab/rl_pricing/blob/main/runner.py) (Train and test), [`sim.py`](https://github.com/umnilab/rl_pricing/blob/main/sim.py) (Simulation environment)

## Diagram (Mermaid)

```mermaid
flowchart TD

subgraph group_entry["Experiment entry"]
  node_main["Experiment setup<br/>[main.py]"]
  node_runner["Train and test<br/>[runner.py]"]
end

subgraph group_simulation["Ride-hailing simulation"]
  node_environment["Simulation environment<br/>[sim.py]"]
  node_vehicle["Vehicle behavior<br/>[sim.py]"]
end

subgraph group_pricing["Pricing and control"]
  node_platform["Pricing platform<br/>[center.py]"]
  node_matching["Vehicle matching<br/>[center.py]"]
  node_baseline["Baseline pricing<br/>[center.py]"]
end

subgraph group_learning["Reinforcement learning"]
  node_replay["Experience memory<br/>[center.py]"]
  node_pricer["RL pricing algorithms<br/>[pricer.py]"]
  node_networks["Policy networks<br/>[model.py]"]
end

subgraph group_data["Scenario data"]
  node_dynamic_data["Dynamic grid inputs"]
  node_static_data["Static grid inputs"]
end

node_researcher(("Experiment operator"))

node_researcher -->|"starts experiment"| node_main
node_main -->|"initializes environment"| node_environment
node_main -->|"creates controller"| node_platform
node_main -->|"dispatches training"| node_runner
node_runner -->|"steps simulation"| node_environment
node_runner -->|"updates prices"| node_platform
node_runner -->|"trains policy"| node_platform
node_environment -->|"initializes vehicles"| node_vehicle
node_platform -->|"matches vehicles"| node_matching
node_platform -->|"selects prices"| node_pricer
node_platform -->|"provides alternatives"| node_baseline
node_platform -->|"stores experience"| node_replay
node_pricer -->|"uses networks"| node_networks

click node_main "https://github.com/umnilab/rl_pricing/blob/main/main.py"
click node_runner "https://github.com/umnilab/rl_pricing/blob/main/runner.py"
click node_dynamic_data "https://github.com/umnilab/rl_pricing/tree/main/grid_small_dynamic"
click node_static_data "https://github.com/umnilab/rl_pricing/tree/main/grid_small_static"
click node_environment "https://github.com/umnilab/rl_pricing/blob/main/sim.py"
click node_vehicle "https://github.com/umnilab/rl_pricing/blob/main/sim.py"
click node_platform "https://github.com/umnilab/rl_pricing/blob/main/center.py"
click node_matching "https://github.com/umnilab/rl_pricing/blob/main/center.py"
click node_baseline "https://github.com/umnilab/rl_pricing/blob/main/center.py"
click node_replay "https://github.com/umnilab/rl_pricing/blob/main/center.py"
click node_pricer "https://github.com/umnilab/rl_pricing/blob/main/pricer.py"
click node_networks "https://github.com/umnilab/rl_pricing/blob/main/model.py"

classDef toneNeutral fill:#f8fafc,stroke:#334155,stroke-width:1.5px,color:#0f172a
classDef toneBlue fill:#dbeafe,stroke:#2563eb,stroke-width:1.5px,color:#172554
classDef toneAmber fill:#fef3c7,stroke:#d97706,stroke-width:1.5px,color:#78350f
classDef toneMint fill:#dcfce7,stroke:#16a34a,stroke-width:1.5px,color:#14532d
classDef toneRose fill:#ffe4e6,stroke:#e11d48,stroke-width:1.5px,color:#881337
classDef toneIndigo fill:#e0e7ff,stroke:#4f46e5,stroke-width:1.5px,color:#312e81
classDef toneTeal fill:#ccfbf1,stroke:#0f766e,stroke-width:1.5px,color:#134e4a
class node_main,node_runner toneBlue
class node_environment,node_vehicle toneAmber
class node_platform,node_matching,node_baseline toneMint
class node_replay,node_pricer,node_networks toneRose
class node_dynamic_data,node_static_data,node_researcher toneIndigo
```

## Components

### Experiment entry

- [Experiment setup](https://github.com/umnilab/rl_pricing/blob/main/main.py): `main.py`
- [Train and test](https://github.com/umnilab/rl_pricing/blob/main/runner.py): `runner.py`

### Ride-hailing simulation

- [Simulation environment](https://github.com/umnilab/rl_pricing/blob/main/sim.py): `sim.py`
- [Vehicle behavior](https://github.com/umnilab/rl_pricing/blob/main/sim.py): `sim.py`

### Pricing and control

- [Pricing platform](https://github.com/umnilab/rl_pricing/blob/main/center.py): `center.py`
- [Vehicle matching](https://github.com/umnilab/rl_pricing/blob/main/center.py): `center.py`
- [Baseline pricing](https://github.com/umnilab/rl_pricing/blob/main/center.py): `center.py`

### Reinforcement learning

- [Experience memory](https://github.com/umnilab/rl_pricing/blob/main/center.py): `center.py`
- [RL pricing algorithms](https://github.com/umnilab/rl_pricing/blob/main/pricer.py): `pricer.py`
- [Policy networks](https://github.com/umnilab/rl_pricing/blob/main/model.py): `model.py`

### Scenario data

- [Dynamic grid inputs](https://github.com/umnilab/rl_pricing/tree/main/grid_small_dynamic): `grid_small_dynamic`
- [Static grid inputs](https://github.com/umnilab/rl_pricing/tree/main/grid_small_static): `grid_small_static`

### Other components

- **Experiment operator**

## Connections

- Experiment operator → Experiment setup: starts experiment (evidence: `README.md`)
- Experiment setup → Simulation environment: initializes environment (evidence: `main.py`)
- Experiment setup → Pricing platform: creates controller (evidence: `main.py`)
- Experiment setup → Train and test: dispatches training (evidence: `main.py`)
- Train and test → Simulation environment: steps simulation (evidence: `runner.py`)
- Train and test → Pricing platform: updates prices (evidence: `runner.py`)
- Train and test → Pricing platform: trains policy (evidence: `runner.py`)
- Simulation environment → Vehicle behavior: initializes vehicles (evidence: `sim.py`)
- Pricing platform → Vehicle matching: matches vehicles (evidence: `center.py`)
- Pricing platform → RL pricing algorithms: selects prices (evidence: `center.py`)
- Pricing platform → Baseline pricing: provides alternatives (evidence: `center.py`)
- Pricing platform → Experience memory: stores experience (evidence: `center.py`)
- RL pricing algorithms → Policy networks: uses networks (evidence: `pricer.py`)
