Probabilistic Differential Dynamic Programming

By Yunpeng Pan, Evangelos A. Theodorou. 2014

109 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): “These ideas have been successfully applied to RL problems in control and robotics by Atkeson & Schaal (1997), Bagnell & Schneider (2001), Deisenroth & Rasmussen (2011) and Pan & Theodorou (2014), for instance.”
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”
One-shot learning of manipulation skills with online dynamics adaptation and neural network priors (2015, background): “closely reflects a range of recent Gaussian process modelbased reinforcement learning algorithms [7], [22].”
Data-Efficient Reinforcement Learning with Probabilistic Model Predictive Control (2017, methodology): “This approximation has been shown to work well in practice in RL contexts [10, 9, 7, 2, 3, 33, 34] and can be computed in closed form when using the Gaussian kernel (3).”
Stability of Controllers for Gaussian Process Forward Models (2016, unknown): “Many successful applications impressively demonstrate the efficiency of this approach (Deisenroth et al., 2015; Engel et al., 2006; Pan & Theodorou, 2014; Kocijan et al., 2004; Klenske et al., 2013; Maciejowski & Yang, 2013; Nguyen-Tuong & Peters, 2011).”
Combining Model-Based and Model-Free Updates for Trajectory-Centric Reinforcement Learning (2017, methodology): “…policies can be categorized as model-free methods (Theodorou et al., 2010; Peters et al., 2010), methods that use global models (Deisenroth et al., 2014; Pan & Theodorou, 2014), and methods that use local models (Levine & Abbeel, 2014; Lioutikov et al., 2014; Akrour et al., 2016).”
Predictor-Corrector Policy Optimization (2018, methodology): “A classical example of pure model-based methods is optimal control [5, 6, 7, 8], which has recently been extended to model abstract latent dynamics with structured neural networks [9, 10].”
Synthesizing Neural Network Controllers with Probabilistic Model-Based Reinforcement Learning (2018, methodology): “Locally linear controllers can be learned in this fashion, for example by extending the classical Differential Dynamic Programming (DDP) [19] method or Iterative LQG [20] to use GP models.”
Model Predictive Path Integral Control using Covariance Variable Importance Sampling (2015, background): “There have been several applications of DDP to autonomous systems that demonstrate its broad applicability [9, 10, 11, 12].”
Neural networks and differential dynamic programming for reinforcement learning problems (2016, unknown): “We consider some assumptions to simplify (A).”
Data-Efficient Learning of Feedback Policies from Image Pixels using Deep Dynamical Models (2015, background): “However, they often rely on heuristics, demonstrations or engineered low-dimensional features, and do not easily scale to data-efﬁcient RL using pixel information only.”
Robust Locally-Linear Controllable Embedding (2017, background): “Algorithms from this class such as differential dynamic programming (DDP) [3], iterative linear quadratic regulator (iLQR) [8], and iterative linear quadratic Gaussian (iLQG) [14] have been successfully applied to a variety of complex control problems [1, 13, 7, 9].”