# Oasis Action World Model Integration

ADAM treats Oasis as a first-class trainer named `Oasis Action World Model`.
It uses the existing `Oasis-Game-Trainer/roblox_action_flow_app.py` worker and
keeps training and playable inference in separate processes.

## Dataset Layout

Use one or more recorder folders. Multiple folders can be supplied with
semicolon separators.

```text
My_Oasis_Dataset/
  dataset_info.json
  actions.jsonl
  frames/
    frame_00000000.png
    frame_00000001.png
```

Each `actions.jsonl` row must identify the frame and its labels:

```json
{"session_id":"run1","frame_index":1,"filename":"frame_00000001.png","w":1,"a":0,"s":0,"d":0,"jump":0,"mouse_dx":0.0,"mouse_dy":0.0,"zoom":0.0}
```

Rows describe the action for the transition into that frame. ADAM validates
missing frames, invalid labels, duplicate or gapped frame indexes, broken
images, inconsistent resolutions, empty sequences, and missing action columns.
It does not guess missing labels.

## Minecraft Beta-Style Recording Notes

Record your own gameplay. Start with `256x144` at 8-12 FPS for a first pipeline
test, then increase data before long runs. Keep every clip as its own session or
recording folder so training never learns fake transitions between worlds.

Capture a mix of walking forward, strafing, turning, jumping, climbing, terrain
changes, interiors, caves, water, sky, and short idle moments. Avoid long
standing-still stretches; idle is useful, but a dataset dominated by idle frames
will make the model ignore controls.

A good smoke dataset is 300-1,000 labelled frames. A more meaningful first
Minecraft experiment is 5,000-20,000 labelled frames with clean W/A/S/D/Space
coverage and synchronized frame/action timestamps.

## RTX 3060 12 GB Starting Point

Use `256x144`, batch size `2`, mixed precision `fp32`, gradient accumulation
`1`, prediction horizon `3`, loader workers `2`, save every `5` epochs, preview
every `5` epochs, and 5-10 epochs for a pipeline test. Try `fp16` only after
FP32 is stable.