agentfoundationmodel.github.io - An Interactive Agent Foundation Model

home > domains > agentfoundationmodel.github.io

Description: An Interactive Agent Foundation Model

website (31167) homepage (16658) ai (8878) research (8581)

Example domain paragraphs

An Interactive Agent Foundation Model

The development of artificial intelligence systems is transitioning from creating static, task-specific models to dynamic, agent-based systems capable of performing well in a wide range of applications. We propose an Interactive Agent Foundation Model that uses a novel multi-task agent training paradigm for training AI agents across a wide range of domains, datasets, and tasks. Our training paradigm unifies diverse pre-training strategies, including visual masked auto-encoders, language modeling, and next-a

We pre-train our model on the CALVIN and Language Table Datasets. Below we show example successful rollouts of our policy in randomized initial conditions in both environments.

Links to agentfoundationmodel.github.io (1)

• bsarkar321.github.io Bidipta Sarkar