A ~13M-parameter Joint Embedding Predictive Architecture (JEPA) that watches 128×128 pixels of PettingZoo Knights-Archers-Zombies (knights_archers_zombies_v10) and predicts a 28-dim game state (archer/knight positions + up to 10 zombies) from a frozen embedding. Pixels in, state out — the model reads no RAM at inference time.

Multi-step rollout sweep, 100 epochs each on 100K frames (kaz_ma_128x128.lance):

Each checkpoint is self-describing: it carries game, state_dim=28, state_names, state_mean/std, num_actions=6, and embed_dim.

Load and drive it with the lepong repo's unified player:

MIT