A DeepMind research team proposes Collect and Infer, a novel paradigm that explicitly models Reinforcement Learning (RL) as data collection and knowledge inference to dramatically boost RL data efficiency.

Here is a quick read: DeepMind’s Collect & Infer: A Fresh Look at Data-Efficient Reinforcement Learning.

The paper Collect & Infer — A Fresh Look at Data-Efficient Reinforcement Learning is on arXiv.



Source link