In recent years, deep artificial neural networks (including recurrent ones) have won
numerous contests in pattern recognition and machine learning. This historical survey …

Learning, planning, and representing knowledge at multiple levels of temporal abstraction
are key, longstanding challenges for AI. In this paper we consider how these challenges can …

The simple, but general formal theory of fun and intrinsic motivation and creativity (1990-
2010) is based on the concept of maximizing intrinsic reward for the active creation or …

Previous neural network learning algorithms for sequence processing are computationally
expensive and perform poorly when it comes to long time lags. This paper first introduces a …

Continual learning is the constant development of complex behaviors with no final end in
mind. It is the process of learning ever more complicated skills by building on those skills …

I present a general taxonomy of neural net architectures for processing time-varying
patterns. This taxonomy subsumes many existing architectures in the literature, and points to …

This paper addresses the general problem of reinforcement learning (RL) in partially
observable environments. In 2013, our large RL recurrent neural networks (RNNs) learned …

Temporal-difference (TD) learning can be used not just to predict rewards, as is commonly
done in reinforcement learning, but also to predict states, ie, to learn a model of the world's …

To be maximally effective, autonomous agents such as robots must be able both to react
appropriately in dynamic environments and to plan new courses of action in novel situations …

Learning, planning, and representing knowledge at multiple levels of temporal abstraction
are key challenges for AI. In this paper we develop an approach to these problems based on …