# Beam Control Eval

> Evaluates real-time reinforcement learning for particle beam steering on edge SoCs. It probes the ability to maximize control reward while adhering to strict millisecond latency and cycle-rate constraints. Use when the user wants to benchmark on Fermilab Booster Synchrotron Dataset, or asks about evaluating this task. Reports Reward (R).

- Skill: `qhjqhj00/beam-control-eval` (Agent Skill)
- Install (CLI): `npx skillmds add qhjqhj00/beam-control-eval`
- Raw SKILL.md: https://api.skillmd.com/api/skills/qhjqhj00/beam-control-eval/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: AI & ML
- Author: qhjqhj00 (https://skillmd.com/u/qhjqhj00)
- Updated: 2026-09-08
- Page: https://skillmd.com/skills/qhjqhj00/beam-control-eval

---


# beam-control-eval

> FastML Science Benchmarks: Accelerating Real-Time Scientific Edge Machine Learning — Duarte et al. (2022) (arXiv:2207.07958, 2022)

## What this evaluates

Evaluates real-time reinforcement learning for particle beam steering on edge SoCs. It probes the ability to maximize control reward while adhering to strict millisecond latency and cycle-rate constraints.

## Datasets

- **Fermilab Booster Synchrotron Dataset** — total ?; splits: test (-1); repo https://github.com/fastmachinelearning/fastml-science

## Metrics

- `Reward (R)` **(primary)** — range: other
  - R = -|ΔI_min|, defined as the negative of the minimum error with respect to the reference expected current in the Booster.

## Input / output format

**Input**: 5 expert-selected causal variables (32-bit floating-point) representing synchrotron and downstream accelerator currents/errors at each time step.

**Output**: 7 discrete actions output by a Deep Q-Network (DQN) agent, representing control signals for magnet power supplies.

## Scoring recipe

```python
# Per episode or cycle
delta_I_min = abs(current - reference_current)
reward = -delta_I_min
# Maximize cumulative reward over the episode
# Report reward convergence alongside latency (≤5ms) and pipeline interval (5ms)
```

## Common pitfalls

- The environment is a surrogate LSTM model, not the physical accelerator; results may not transfer directly.
- Latency must include data movement overhead; the algorithm itself must run within 5 ms.
- Inputs are already pre-selected expert variables, not raw sensor data.

## Evidence (verbatim from paper)

> The primary performance metric in this reference benchmark is the reward, R, defined as the negative of the error with respect to the reference expected current in the Booster, R=−|ΔI_min|.

## Citation

```bibtex
@misc{duarte2022fastml,
  title={FastML Science Benchmarks: Accelerating Real-Time Scientific Edge Machine Learning},
  author={Duarte et al. (2022)},
  year={2022},
  note={arXiv:2207.07958}
}
```

- arXiv: 2207.07958