Q-learning with neural network function approximation (neural Q-learning for short) is
among the most prevalent deep reinforcement learning algorithms. Despite its empirical …

In this work, we identify a novel set of conditions that ensure convergence with probability 1
of Q-learning with linear function approximation, by proposing a two time-scale variation …

Despite the great empirical success of deep reinforcement learning, its theoretical
foundation is less well understood. In this work, we make the first attempt to theoretically …

Q-learning with function approximation is one of the most popular methods in reinforcement
learning. Though the idea of using function approximation was proposed at least 60 years …

Q-learning methods are a common class of algorithms used in reinforcement learning (RL).
However, their behavior with function approximation, especially with neural networks, is …

In this paper, we consider the model-free reinforcement learning problem and study the
popular Q-learning algorithm with linear function approximation for finding the optimal …

Although Q-learning is one of the most successful algorithms for finding the best action-
value function (and thus the optimal policy) in reinforcement learning, its implementation …

Q-learning is arguably one of the most applied representative reinforcement learning
approaches and one of the off-policy strategies. Since the emergence of Q-learning, many …

We present a novel definition of the reinforcement learning state, actions and reward
function that allows a deep Q-network (DQN) to learn to control an optimization …

The use of target networks has been a popular and key component of recent deep Q-
learning algorithms for reinforcement learning, yet little is known from the theory side. In this …