Sample Efficient Reinforcement Learning With Domain Randomization for Automated Demand Response in Low-Voltage Grids

Sample Efficient Reinforcement Learning with Gaussian Processes

This paper derives sample complexity results for using Gaussian Processes (GPs) in both modelbased and model-free reinforcement learning (RL). We show that GPs are KWIK learnable, proving for the first time that a model-based RL approach using GPs, GP-Rmax, is sample efficient (PAC-MDP). However, we then show that previous approaches to model-free RL using GPs take an exponential number of step...

Integration in Low - Voltage Feeders with Demand Response

The rapid growth of photovoltaics (PV) over the last few years has introduced many new challenges for power system operators. Most PV is integrated into the low-voltage network, where they can cause voltage and line constraint violations if generation exceeds local demand. This thesis explores the capabilities of using demand response to aid the integration of photovoltaic capacity into low vol...

Sample-Efficient Evolutionary Function Approximation for Reinforcement Learning

Reinforcement learning problems are commonly tackled with temporal difference methods, which attempt to estimate the agent’s optimal value function. In most real-world problems, learning this value function requires a function approximator, which maps state-action pairs to values via a concise, parameterized function. In practice, the success of function approximators depends on the ability of ...

Sample-efficient Deep Reinforcement Learning for Dialog Control

Representing a dialog policy as a recurrent neural network (RNN) is attractive because it handles partial observability, infers a latent representation of state, and can be optimized with supervised learning (SL) or reinforcement learning (RL). For RL, a policy gradient approach is natural, but is sample inefficient. In this paper, we present 3 methods for reducing the number of dialogs require...

Active Low Voltage Grids