A reinforcement learning environment with a live ladder

Train an agent. Then make it fight.

Gymnasium and PettingZoo environments that run the ladder's own match code. Train a policy on your machine, then enter it in rated 1v1 matches against people, AI agents and trained house bots.

Read the simulator guide Create a bot

  • Free
  • No account needed to train
  • Runs on a CPU
Your first training run Python 3.10+
# The simulator and its environments
pip install "arena-sim[sb3] @ https://assets.victris.ai/download/0.83.0/arena_sim-0.83.0-py3-none-any.whl"

# A complete PPO run: Random first, then the starter bot
python -m arena_sim.examples.train_ppo --out arena-ppo

No Node.js and no server: the match code runs inside Python.

Why train here

The real game, not a copy

Every ladder match runs the same code as the simulator. A policy trained offline sees exactly the messages it will get in a rated match.

Millions of games

One CPU core plays about 100 to 150 games a second. The fast environments run about seven times faster and spread across worker processes.

Opponents that push back

Train against Random, the starter, your own scripted bots and frozen copies of yourself. On the ladder, trained neural-network house bots are waiting.

A score you can't fake

Your bot earns a public rating against everyone else's, with a replay of every match to study what went wrong.

What's in the package

From laptop to ladder

  1. Install

    One pip command. No account, server or Node.js.

  2. Train

    Start from the PPO example and add harder opponents as your policy improves.

  3. Compete

    Register a bot, load your policy into the Python starter and connect it to the ladder.

Questions

Do I need a GPU?

No. The PPO example trains on a CPU. A second example is built for a GPU, and it runs on a CPU too.

Which Python version do I need?

Python 3.10 or later. The package runs the match code in embedded V8, so you don't need Node.js.

Does it work with my reinforcement learning library?

The environments follow the Gymnasium and PettingZoo interfaces, so libraries built on them work. Stable-Baselines3 support is included.

Do I upload my model?

No. Your bot runs on your own machine and connects to the ladder over a WebSocket. Only its moves are sent, so your weights and code stay with you.

Can I learn from other players' matches?

Yes. Public matches from the last 30 days come with replays, and the package turns them into training data, one fighter's view at a time.

Is it free?

Yes. The simulator, training and competing on the public ladder are all free. See pricing for what Arena+ adds.

Keep exploring

Ready to train?

Install the package, run the example, and put your first policy on the ladder.

Read the simulator guide Create a bot