Approximate real-time optimal control based on sparse Gaussian process models

By Joschka Boedecker, Jost Tobias Springenberg, Jan Wülfing, Martin A. Riedmiller. 2014

70 citations recorded by the source corpus.

Subfields: Reinforcement Learning, Probabilistic & Bayesian Methods

How researchers see this paper

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

In Reinforcement Learning

In Probabilistic & Bayesian Methods

Citations in the corpus

From Pixels to Torques: Policy Learning with Deep Dynamical Models (2015, methodology): “Along these lines, (Deisenroth et al., 2009; Abramova et al., 2012; Boedecker et al., 2014; Pan & Theodorou, 2014; Levine et al., 2015) suggested to first learn a transition model and then use optimal control methods to solve RL problems.”
Embed to Control: A Locally Linear Latent Dynamics Model for Control from Raw Images (2015, methodology): “When combined with receding horizon control [3], and machine learning methods for learning approximate system models, such algorithms are a powerful tool for solving complicated control problems [3, 4, 5, 6]; however, they either rely on a known system model or require the design of relatively low-d”
Model-based reinforcement learning with parametrized physical models and optimism-driven exploration (2015, neutral): “[9], which uses Gaussian processes with MPC.”
Neural Network Dynamics for Model-Based Deep Reinforcement Learning with Model-Free Fine-Tuning (2017, methodology): “However, the most efficient model-based algorithms have used relatively simple function approximators, such as Gaussian processes [6], [21], [22], time-varying linear models [5], [23], [24], and mixtures of Gaussians [25].”
Transfer from Simulation to Real World through Learning Deep Inverse Dynamics Model (2016, background): “A number of options are available for representation of learned dynamics functions, from linear functions [28] [43], to Gaussian processes [2] [19] [7], to deep neural networks [32] [11].”
One-shot learning of manipulation skills with online dynamics adaptation and neural network priors (2015, background): “Typically, in order to learn the model from a small amount of interaction, they make various assumptions, such as smoothness [7], [8] or access to prior knowledge about the system [3], [4], since the general problem of learning a complex, nonlinear”
Data-Efficient Reinforcement Learning with Probabilistic Model Predictive Control (2017, methodology): “In [5, 28], the authors considered MPC problems with GP models, where only the GP’s posterior mean was used while ignoring the variance for planning.”
Prediction and Control with Temporal Segment Models (2017, unknown): “, 2016; Yip & Camarillo, 2014), Gaussian processes (Boedecker et al., 2014; Ko & Fox, 2009; Deisenroth & Rasmussen, 2011), predictive state representations (PSRs) (Littman et al.”
Differentiable MPC for End-to-end Planning and Control (2018, methodology): “These methods generally rely on learning a dynamics model directly from interactions with the real system and then integrate the learned model into the control policy [Schneider, 1997, Abbeel et al., 2006, Deisenroth and Rasmussen, 2011, Heess et al., 2015, Boedecker et al., 2014].”