Tag Info

Hot answers tagged


I'm not sure I fully understand your design; perhaps you can clarify what you want your network to learn, why TD-learning "isn't cutting it", and what you mean by 'reinforcement' and 'prediction' learning. In particular, TD-learning is a reinforcement learning model, and it does reward based on predicted (and not just observed) outcomes. However, you seem ...


The term I was looking for is "concurrent activities". Some research in the domain of hierarchical learning has been done in this domain by Rohanimanesh and Mahadevan. According to this literature review on hierarchical learning, basically what they did was determine how multiple tasks can be managed without interfering with one another and how they should ...

Only top voted, non community-wiki answers of a minimum length are eligible