I’m new to the machine learning field, so I apologize if this is a basic question.
Is it possible to feed pre-existing data into a reinforcement learning model to speed up its learning process? Or perhaps combine it with supervised or unsupervised learning techniques so that the reinforcement model doesn’t start from scratch, making random guesses during training?
For example, if you have a reinforcement learning model learning to walk, could you provide it with walking data beforehand to help it learn faster, rather than having it start from zero and figuring everything out on its own?
Correct me if I’m wrong, but you’re saying that you can provide the model with the same type of data it would receive during training, before the training actually begins?
I think we can pre-train (in phase 1) a robot (i.e. model) with some (offline) walking data, and then further train that robot as it walks (in phase 2) and receives more (online) walking data.
Certainly, the robot’s behavior (at least at the beginning of phase 2) will be affected by the walking data in phase 1, and that behavior will affect what data the robot will receive in phase 2.
For example, if your pre-training data is all about walking on a flat terrain, but the actual enviornment is very bumpy, then the robot will probably falls a lot and that is the kind of data you will receive.
Perhaps you might share if there is any reason for you to be wondering if pre-training data might not be helpful?
Providing pre-training data might risk steering the AI in the wrong direction. However, if you want a model to learn walking on bumpy terrain, wouldn’t pre-training it on walking on flat surfaces speed up the process? Instead of learning to walk from scratch, it would only need to adapt to the bumpy terrain.