Gaussian Processes in Reinforcement Learning

By Carl E. Rasmussen, Malte Kuss. 2003

301 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Modelling transition dynamics in MDPs with RKHS embeddings (2012, background): “Other related approaches include Rasmussen & Kuss (2003), Deisenroth et al. (2009), Ormoneit & Sen (1999) and Kroemer & Peters (2011).”
Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Models (2018, background): “However, such models typically induce additional assumptions on the system, such as the smoothness assumption inherent in GPs with squared-exponential kernels [20].”
Model-Ensemble Trust-Region Policy Optimization (2018, methodology): “An alternative is to use nonparametric models such as Gaussian Processes (GPs) (Rasmussen et al., 2003; Ko et al., 2007; Deisenroth & Rasmussen, 2011).”
Learning and Policy Search in Stochastic Dynamical Systems with Bayesian Neural Networks (2016, neutral): “When the state space is continuous, popular modes for transition functions include Gaussian processes [16, 12, 3], fixed bases such as Laguerre functions [21], and adaptive basis/neural networks [5].”
Learning to Control a Low-Cost Manipulator using Data-Efficient Reinforcement Learning (2011, methodology): “Although the approaches in [20, 8] do long-term planning for finding a policy, they cannot directly deal with constraints in the state space (e.”
Reducing hardware experiments for model learning and policy optimization (2015, background): “Gaussian Process (GP) [19] is a stochastic model that represents the relationship between r inputs x̃ ∈ <r and a scalar output y.”
Learning and Using Models (2012, background): “There are other approaches that perform as well or better without such theoretical guarantees, such as Gaussian Process RL (Deisenroth and Rasmussen, 2011; Rasmussen and Kuss, 2004) or TEXPLORE (Hester and Stone, 2010).”
Reinforcement learning with Gaussian processes (2005, background): “In Rasmussen and Kuss (2004) an alternative approach to employing GPs in RL is proposed.”
Gaussian process dynamic programming (2009, methodology): “[13,14], for model-based control by Rasmussen and Kuss [47], Murray-Smith and Sbarbaro [35], Rasmussen and Deisenroth [45], and modelbased value iteration by Deisenroth et al.”
Model learning for robot control: a survey (2011, methodology): “In contrast to previous applications, the forward models incorporate a probabilistic description of the system dynamics in this case (Rasmussen and Kuss 2003; Rottmann and Burgard 2009).”
Graph kernels and Gaussian processes for relational reinforcement learning (2006, methodology): “In (Rasmussen and Kuss, 2004), a method for policy iteration using Gaussian processes is described.”
Convex Optimization: Algorithms and Complexity (2015, unknown): “Another approach to employ GPs in RL was proposed by Rasmussen and Kuss [2004]. The approach taken in this work is notably different from the generative approach of the GPTD framework.”
A Clustering-Based Graph Laplacian Framework for Value Function Approximation in Reinforcement Learning (2014, background): “In recent years, there are some papers on applying Gaussian processes (GPs) or SVMs to RL problems, such as GPs in TD(0) learning [32], SVMs for RL [33], and policy iteration based on GPs [34].”
Proto-value Functions: A Laplacian Framework for Learning Representation and Control in Markov Decision Processes (2007, background): “support vector machines (Dietterich and Wang, 2002) and Gaussian processes (Engel et al., 2003; Rasmussen and Kuss, 2004).”
Approximate real-time optimal control based on sparse Gaussian process models (2014, methodology): “the transition function of the dynamical system: Kuss and Rasmussen [26] use a GP dynamics model in combination with a GP based value function approximation for reinforcement learning.”
Gaussian Processes for Regression and Optimisation (2007, methodology): “Interesting machine learning applications include Gaussian processes for reinforcement learning [60], the incorporation of derivative observations into Gaussian process models [73], Gaussian processes to speed up the evaluation of Bayesian integrals [58], and Gaussian process models of dynamical sys”