Recent studies have shown the potential of Reinforcement Learning (RL) algorithms in tuning parameters Model Predictive Controllers (MPC), including weights cost function and unknown MPC model. However, a framework for easy straightforward implementation that allows training just few episodes overcoming need imposing extra constraints as required by state-of-the-art methods, is still missing. I...

Reinforcement learning problems are commonly tackled by estimating the optimal value function. In many real-world problems, learning this value function requires a function approximator, which maps states to values via a parameterized function. In practice, the success of function approximators depends on the ability of the human designer to select an appropriate representation for the value fu...

We propose a novel online learning method for minimizing regret in large extensive-form games. The approach learns a function approximator online to estimate the regret for choosing a particular action. A noregret algorithm uses these estimates in place of the true regrets to define a sequence of policies. We prove the approach sound by providing a bound relating the quality of the function app...

This work introduces a novel approach for solving reinforcement learning problems in multi-agent settings. We propose a state reformulation of multi-agent problems in R that allows the system state to be represented in an image-like fashion. We then apply deep reinforcement learning techniques with a convolution neural network as the Q-value function approximator to learn distributed multi-agen...

In large and continuous state-action spaces reinforcement learning heavily relies on function approximation techniques. Tile coding is a well-known function approximator that has been successfully applied to many reinforcement learning tasks. In this paper we introduce the hyperplane tile coding, in which the usual tiles are replaced by parameterized hyperplanes that approximate the action-valu...

The combination of model predictive control (MPC) and learning methods has been gaining increasing attention as a tool to systems that may be difficult model. Using MPC function approximator in reinforcement (RL) is one approach reduce the reliance on accurate models. RL dependent exploration learn, currently, simple heuristics based random perturbations are most common. This paper considers va...

Approximator-based control, primarily using neural networks and/or fuzzy systems as the main tool for function approximation, had been regarded as non-rigorous, but sold under the fashionable name of intelligent control. To some extent, this view point has some elements of true in it as historically it was indeed the case where we only knew the existence of a stabilizing controller but lacked t...

Abstract System identification as a field has been around since the 1950s with roots from statistical theory. A substantial body of concepts, theory, algorithms and experience developed then. Indeed, there is very extensive literature on subject, many text books, like [5, 8, 12]. Some main points this “classical” are summarized in chapter, just pointing to basic structure problem area. The cent...

Random Vector Functional-link (RVFL) networks, as a class of random learner models, have received careful attention from the neural network research community due to their advantages in obtaining fast learning algorithms and which hidden layer parameters are randomly generated remain fixed during training phase. However, its universal approximation ability may not be guaranteed if properly sele...

Efficient Transformers have been developed for long sequence modeling, due to their subquadratic memory and time complexity. Sparse Transformer is a popular approach improving the efficiency of by restricting self-attention locations specified predefined sparse patterns. However, leveraging sparsity may sacrifice expressiveness compared full-attention, when important token correlations are mult...