Re:Training a local model to play browser games on the fly
by serkan-ozal on Thursday October 15, 2026 @01:16PM
(#50106922)
IronBee Gamer author here.
An LLM writes each game's rules as code. The rules play the game and label every state with the move they would make. The model (322M, mmBERT-base) is fine-tuned on those labels. Then the model plays its own games, the rules label the states it ended up in and it's fine-tuned again.
Re:Training a local model to play browser games on the fly
by ehalici on Thursday October 15, 2026 @02:16PM
(#50107860)
Thank you . How do you prevent the model from overfitting to the rule-based labels, and can it eventually discover strategies that outperform the original rules?
Re:Training a local model to play browser games on the fly
by berkay on Thursday October 15, 2026 @09:35AM
(#50103498)
An interesting approach where a frontier model (Claude) is used to train the local model (Laya)to play browser games and learn as it fails. Both Jev and Laya were tried, and Laya was preferred due to need for low latency.
An LLM writes each game's rules as code. The rules play the game and label every state with the move they would make. The model (322M, mmBERT-base) is fine-tuned on those labels. Then the model plays its own games, the rules label the states it ended up in and it's fine-tuned again.