---
datasets:
- jakegrigsby/metamon-synthetic
- jakegrigsby/metamon-parsed-replays
license: apache-2.0
pipeline_tag: reinforcement-learning
library_name: amago
tags:
- pokemon
- game-ai
- offline-rl
- transformers
---

Checkpoints from Metamon (v1) training runs.

**Metamon** enables reinforcement learning (RL) research on [Pokémon Showdown](https://pokemonshowdown.com/) by providing:

1) A standardized suite of teams and opponents for evaluation.
2) A large dataset of RL trajectories "reconstructed" from real human battles.
3) Starting points for training imitation learning (IL) and RL policies.

Metamon is the codebase behind ["Human-Level Competitive Pokémon via Scalable Offline RL and Transformers"](https://arxiv.org/abs/2504.04395) (RLC, 2025). Please check out our [project website](https://metamon.tech) for an overview of our results. This README documents the dataset, pretrained models, training, and evaluation details to help you get battling!

**Paper:** [Human-Level Competitive Pokémon via Scalable Offline Reinforcement Learning with Transformers](https://huggingface.co/papers/2504.04395)
**Project Website:** https://metamon.tech
**Code:** [GitHub Repository](https://github.com/UT-Austin-RPL/metamon/tree/main)

### Usage

Pretrained models can run without research GPUs, but you will need to install [`amago`](https://github.com/UT-Austin-RPL/amago), which is an RL codebase by the same authors. Follow installation instructions [here](https://ut-austin-rpl.github.io/amago/installation.html).

Load and run pretrained models with `metamon.rl.eval_pretrained`. For example, to run the default checkpoint of the `SyntheticRLV2` model for 100 battles against a set of heuristic baselines:

```bash
python -m metamon.rl.eval_pretrained --agent SyntheticRLV2 --gens 1 --formats ou --n_challenges 100 --eval_type heuristic
```

To battle against other models or humans online (via a local Showdown server):

```bash
python -m metamon.rl.eval_pretrained --agent SyntheticRLV2 --gens 1 --formats ou --n_challenges 50 --eval_type ladder --username <pick unique username> --team_set competitive
```

For more details on models and usage, please refer to the [project's GitHub repository](https://github.com/UT-Austin-RPL/metamon/tree/main).