Abstract. This paper proposes a novel approach to discover options in the form of conditionally terminating sequences, and shows how they can be integrated into reinforcement learn...
We consider the task of driving a remote control car at high speeds through unstructured outdoor environments. We present an approach in which supervised learning is first used to...
— Traditional approaches to integrating knowledge into neural network are concerned mainly about supervised learning. This paper presents how a family of self-organizing neural m...
Both genetic algorithms (GAs) and temporal difference (TD) methods have proven effective at solving reinforcement learning (RL) problems. However, since few rigorous empirical com...