Environment for Communicated-based AI

October 2016 Facebook Research

CommAI-env is an open-source virtual environment for learning AI systems to communicate. We want to develop machines that can learn to perform novel tasks for us through natural language communication.

The Learner is in a communication-based setup, where it interacts via interface with an Environment. The Environment asks the Learner to solve a number of communication-based Tasks, and assigns it a Reward for each task instance it successfully completes.

The Learner is presented with multiple instances of all tasks, and it has to solve as many of them as possible in order to maximize the reward. Examples of tasks include counting problems, tasks where the Learners must memorize lists of items and answer questions about them, or follow navigation instructions through a text-based navigation scheme.

Two examples of basic communication tasks:

  • Task 1
    Teacher: repeat after me: AABBB
    Learner: AAB
    Teacher: wrong, the correct answer is: AABBB
  • Task 2
    Teacher: repeat after me: BBAA
    Learner: BBAA
    Teacher: good! [reward +1]

The ultimate goal of CommAI-env is to provide an environment in which Learners can be trained, from ground up, to be able to genuinely interact with humans through language. While the tasks might appear almost trivial, we believe that most of them are beyond the grasp of current machine learning-based algorithms, and that a Learner able to solve them all would have already made great strides towards the level of communicative intelligence required to interact with, and learn further from human teachers.

CommAI-env Page