Approximate dynamic programming for constrained linear systems: A piecewise quadratic approximation approach

Approximate dynamic programming (ADP) faces challenges in dealing with constraints in control problems. Model predictive control (MPC) is, in comparison, well-known for its accommodation of constraints and stability guarantees, although its computation is sometimes prohibitive. This paper introduces an approach combining the two methodologies...

Influence-aware memory architectures for deep reinforcement learning in POMDPs

Due to its perceptual limitations, an agent may have too little information about the environment to act optimally. In such cases, it is important to keep track of the action-observation history to uncover hidden state information. Recent deep reinforcement learning methods use recurrent neural networks (RNN) to memorize past observations....

Learning to run a power network with trust

Artificial agents are promising for real-time power network operations, particularly, to compute remedial actions for congestion management. However, due to high reliability requirements, purely autonomous agents will not be deployed any time soon and operators will be in charge of taking action for the foreseeable future. Aiming at designing...

R3L: Connecting Deep Reinforcement Learning To Recurrent Neural Networks For Image Denoising Via Residual Recovery

State-of-the-art image denoisers exploit various types of deep neural networks via deterministic training. Alternatively, very recent works utilize deep reinforcement learning for restoring images with diverse or unknown corruptions. Though deep reinforcement learning can generate effective policy networks for operator selection or architecture...

Artificial Intelligence-Based Radio Resource Management in Sliced Radio Access Networks

In this thesis, we design and assess a multi-slice resource allocation framework that is based on machine learning techniques (subset of artificial intelligence techniques). The proposed framework employs two machine learning techniques namely, artificial neural networks and reinforcement learning for resource management in sliced RAN....

Fine-tuning deep RL with gradient-free optimization

Deep reinforcement learning makes it possible to train control policies that map high-dimensional observations to actions. These methods typically use gradient-based optimization techniques to enable relatively efficient learning, but are notoriously sensitive to hyperparameter choices and do not have good convergence properties. Gradient...

Continuous state and action Q-learning framework applied to quadrotor UAV control

This paper describes an implementation of a reinforcement learning-based framework applied to the control of a multi-copter rotorcraft. The controller is based on continuous state and action Q-learning. The policy is stored using a radial basis function neural network. Distance-based neuron activation is used to optimize the generalization...