Reinforcement learning algorithms typically consider discrete-time dynamics, even though
the underlying systems are often continuous in time. In this paper, we introduce a model …

A natural approach for reinforcement learning is to predict future rewards by unrolling a
neural network world model, and to backpropagate through the resulting computational …

Reinforcement learning has traditionally focused on learning state-dependent policies to
solve optimal control problems in a closed-loop fashion. In this work, we introduce the …

Progress in sequence modeling with deep learning has been driven by the advances in
temporal credit assignment coming from better gradient propagation in neural network …