223 citations · 267 across the 16 of their papers we have counts for
8 papers · 1 filter
Bayesian Anytime Pareto Set Identification for Multi-Objective Multi-Armed Bandits
Lennert Saerens, Bram Silue, Eleni Litsa +2
Identifying Pareto optimal solutions is critical to support multi-objective decision-making. In this work, we present Top-Two Pareto Front Thompson Sampling (TTPFTS), the first any…
Bellman: A Toolbox for Model-Based Reinforcement Learning in TensorFlow
John McLeod, Hrvoje Stojic, Vincent Adam +4
In the past decade, model-free reinforcement learning (RL) has provided solutions to challenging domains such as robotics. Model-based RL shows the prospect of being more sample-ef…
Compatible features for Monotonic Policy Improvement
Marcin B. Tomczak, Sergio Valcarcel Macua, Enrique Munoz de Cote +1
Recent policy optimization approaches have achieved substantial empirical success by constructing surrogate optimization objectives. The Approximate Policy Iteration objective (Sch…
Policy Optimization Through Approximate Importance Sampling
Marcin B. Tomczak, Dongho Kim, Peter Vrancx +1
Recent policy optimization approaches (Schulman et al., 2015a; 2017) have achieved substantial empirical successes by constructing new proxy optimization objectives. These proxy ob…
Disentangled Skill Embeddings for Reinforcement Learning
Janith C. Petangoda, Sergio Pascual-Diaz, Vincent Adam +2
We propose a novel framework for multi-task reinforcement learning (MTRL). Using a variational inference formulation, we learn policies that generalize across both changing dynamic…
Model-Based Regularization for Deep Reinforcement Learning with Transcoder Networks
Felix Leibfried, Peter Vrancx
This paper proposes a new optimization objective for value-based deep reinforcement learning. We extend conventional Deep Q-Networks (DQNs) by adding a model-learning component yie…
Direct Load Control of Thermostatically Controlled Loads Based on Sparse Observations Using Deep Reinforcement Learning
Frederik Ruelens, Bert J. Claessens, Peter Vrancx +2
This paper considers a demand response agent that must find a near-optimal sequence of decisions based on sparse observations of its environment. Extracting a relevant set of featu…
Convolutional Neural Networks For Automatic State-Time Feature Extraction in Reinforcement Learning Applied to Residential Load Control
Bert J. Claessens, Peter Vrancx, Frederik Ruelens
Direct load control of a heterogeneous cluster of residential demand flexibility sources is a high-dimensional control problem with partial observability. This work proposes a nove…