Will any agent perform better on Minecraft (or comparable open world game) after being fine-tuned on a manual by 2027?
One-OffIA2mManifold MarketsSin KYCDatos de resolución verificadosBien calibradoPronóstico comunitario actualSí 79.8%
Pronosticadores
17
Tipo de pregunta
binary
Metodología
Play-money forecasting platform
Tipo de fuente
Pronóstico
Datos de mercado
Actualizado hace 11 horas
Desactualizado11 jul 22, 19:56 UTC1 ene 27, 5:00 UTC
Tendencias
Reglas
To clarify: the experiment is that there are two copies of an agent that runs on Minecraft (or some other open world game environment).
- The agent has the capacity to be fine-tuned with text.
- One version is passed a manual for the game as text (or text + images, but *not* video), the other runs without any finetuning.
- Will the former perform better than the latter (either better sample efficiency or better final reward)?
- The agent can't have been trained on that env before, but it can be trained on other envs/data beforehand (e.g. it's okay if there's a pretrained LLM in the loop).
