About WareMax
A Rust-core discrete-event simulator and Gymnasium environment for warehouse-robotics dispatching — built so that (seed, action sequence) ⇒ trajectory is a property, not a hope.
What it is
WareMax is an open-source project from
Skelf Research. It is a Cargo workspace with
two surfaces: a Rust CLI (waremax) for deterministic simulations, parameter
sweeps, A/B tests with Welch’s t, and benchmarking with regression detection; and a
Python extension built with maturin that exposes a Gymnasium environment
(WaremaxAllocEnv) usable from stable-baselines3 and
sb3-contrib.
What it simulates
WareMax models Robotic Mobile Fulfillment Systems — pod-to-person warehouses in the style of Kiva / Amazon Robotics. Robots are AMRs on a graph topology; stations are pick stations with concurrency and lognormal service times; orders arrive by a Poisson process with negative-binomial line counts and a Zipf SKU popularity model. The primary lever it studies is task allocation: which robot handles which pick task.
It does not simulate AS/RS cranes, conveyor sortation, fork-AGV tugger trains, or human pickers walking aisles, and it does not import warehouse CAD or DWG files. Scenarios are YAML files describing a graph topology, station list, robot count, traffic capacities, and policy stack.
Determinism
Reproducibility is enforced, not asserted. The core is single-threaded per scenario,
uses a ChaCha8 RNG seeded from a u64, and applies canonical (id-based)
tie-breaking throughout. The RL control loop wraps the simulator with a strict crossbeam
ping-pong handshake so exactly one side runs at a time. Tests live in
waremax-rl/tests/determinism.rs. As part of getting there, the project fixed
several latent HashMap-iteration-order bugs that had made prior “seeded”
results silently irreproducible. See
verifying determinism for the full mechanism.
A finding, not a sales pitch
On the built-in presets, the trained RL dispatchers match the nearest-robot and round-robin heuristics but do not surpass them. The system is capacity- and destination-contention-bound; state-blind round-robin is near-optimal. WareMax exposes this as one of its findings, and provides the tunable structure — load, congestion, replicas, inventory SKU count — to let you find the regimes where dispatching choice does have leverage.
License and source
MIT-licensed. Source of truth: github.com/Skelf-Research/waremax. Authoritative docs: docs.skelfresearch.com/waremax/.
Who built it
Skelf Research is a research group that publishes practical, narrowly-scoped tooling. WareMax backs an ongoing research effort on warehouse dispatching and reward design under controllability constraints. Issues and pull requests on the GitHub repository are the canonical channel.