Lifelong learning applied to artificial intelligence in new Defense Advanced Research Projects Agency opportunity
Lifelong Learning is a relatively new area of machine learning research, in which artificial intelligence agents continually learn as they encounter varying conditions and tasks while deployed in the field, acquiring experience and knowledge and improving performance on tasks.
The Defense Advanced Research Projects Agency issued an Artificial Intelligence Exploration Opportunity for submissions of innovative basic or applied research concepts in the area of lifelong learning by agents.
The total award value for this phae of the project is limited to $1 million per proposal. Responses are due by July 27.
Lifelong learning differs from the train-then-deploy process for typical machine learning systems, which often results in:
- unpredictable outcomes when input conditions not representative of training experiences are encountered,
- catastrophic forgetting of previously learned knowledge useful for new instances of previously learned tasks, and
- the inability to execute new tasks effectively, if at all.
Current lifelong learning research assumes a single, independent agent that learns from its own actions and surroundings; it has not considered populations of agents that benefit from each other’s experiences. Furthermore, the algorithms used for lifelong learning typically require large amounts of computing resources, including server farms, GPUs, and other resource-consuming hardware, and typically do not have to address communication resource limitations.
To learn more about the project and to submit a proposal visit the DARPA announcement HERE.
