Results 1  10
of
1,151,615
Inverse Optimal Controller Design For
"... For a class of nonlinear stochastic systems in strictfeedback form, where the diffusion coefficients depend on the state, we obtain risksensitive statefeedback controllers which are both globally inverse optimal and locally suboptimal. These controllers also lead to closedloop system traject ..."
Abstract
 Add to MetaCart
For a class of nonlinear stochastic systems in strictfeedback form, where the diffusion coefficients depend on the state, we obtain risksensitive statefeedback controllers which are both globally inverse optimal and locally suboptimal. These controllers also lead to closedloop system
Inverse optimal control of hyperchaotic finance system∗
, 2014
"... Abstract. This paper aims to control a new 4D hyperchaotic finance system by means of inverse optimal control scheme. For this purpose, the inverse optimal controller is designed and added to the new hyperchaotic finance system. Based on Lyapunov stability theory, the stability of the hyperchaotic f ..."
Abstract
 Add to MetaCart
Abstract. This paper aims to control a new 4D hyperchaotic finance system by means of inverse optimal control scheme. For this purpose, the inverse optimal controller is designed and added to the new hyperchaotic finance system. Based on Lyapunov stability theory, the stability of the hyperchaotic
Inverse Optimal Control for Humanoid Locomotion
"... Abstract—In this paper, we present a method for learning the reward function for humanoid locomotion from motioncaptured demonstrations of human running. We show how an approximate, local inverse optimal control algorithm can be used to learn the reward function for this high dimensional domain, an ..."
Abstract

Cited by 1 (0 self)
 Add to MetaCart
Abstract—In this paper, we present a method for learning the reward function for humanoid locomotion from motioncaptured demonstrations of human running. We show how an approximate, local inverse optimal control algorithm can be used to learn the reward function for this high dimensional domain
Inverse Optimal Control Oleg Arenz
"... In Reinforcement Learning, an agent learns a policy that maximizes a given reward function. However, providing a reward function for a given learning task is often non trivial. Inverse Reinforcement Learning, which is sometimes also called Inverse Optimal Control, addresses this problem by learning ..."
Abstract
 Add to MetaCart
In Reinforcement Learning, an agent learns a policy that maximizes a given reward function. However, providing a reward function for a given learning task is often non trivial. Inverse Reinforcement Learning, which is sometimes also called Inverse Optimal Control, addresses this problem by learning
Continuous inverse optimal control with locally optimal examples
 In ICML
, 2012
"... Inverse optimal control, also known as inverse reinforcement learning, is the problem of recovering an unknown reward function in a Markov decision process from expert demonstrations of the optimal policy. We introduce a probabilistic inverse optimal control algorithm that scales gracefully with tas ..."
Abstract

Cited by 11 (1 self)
 Add to MetaCart
Inverse optimal control, also known as inverse reinforcement learning, is the problem of recovering an unknown reward function in a Markov decision process from expert demonstrations of the optimal policy. We introduce a probabilistic inverse optimal control algorithm that scales gracefully
Inverse optimal control with polynomial optimization
, 2014
"... In the context of optimal control, we consider the inverse problem of Lagrangian identification given system dynamics and optimal trajectories. Many of its theoretical and practical aspects are still open. Potential applications are very broad as a reliable solution to the problem would provide a p ..."
Abstract

Cited by 1 (1 self)
 Add to MetaCart
In the context of optimal control, we consider the inverse problem of Lagrangian identification given system dynamics and optimal trajectories. Many of its theoretical and practical aspects are still open. Potential applications are very broad as a reliable solution to the problem would provide a
Inverse Optimal Control with LinearlySolvable MDPs
"... We present new algorithms for inverse optimal control (or inverse reinforcement learning, IRL) within the framework of linearlysolvable MDPs (LMDPs). Unlike most prior IRL algorithms which recover only the control policy of the expert, we recover the policy, the value function and the cost function. ..."
Abstract

Cited by 25 (4 self)
 Add to MetaCart
We present new algorithms for inverse optimal control (or inverse reinforcement learning, IRL) within the framework of linearlysolvable MDPs (LMDPs). Unlike most prior IRL algorithms which recover only the control policy of the expert, we recover the policy, the value function and the cost function
Inverse Optimal Control of Linear Distributed Parameter Systems
, 2014
"... Abstract A constructive method is developed to design inverse optimal controllers for a class of linear distributed parameter systems (DPSs). Inverse optimality guarantees that the cost functional to be minimized is meaningful in the sense that the symmetric and positive definite weighting kernel m ..."
Abstract
 Add to MetaCart
Abstract A constructive method is developed to design inverse optimal controllers for a class of linear distributed parameter systems (DPSs). Inverse optimality guarantees that the cost functional to be minimized is meaningful in the sense that the symmetric and positive definite weighting kernel
Robust inverse optimal control laws for nonlinear systems
, 2003
"... SUMMARY This work proposes a robust inverse optimal controller design for a class of nonlinear systems with bounded, timevarying uncertain variables. The basic idea is that of reshaping the scalar nonlinear gain of an L g V controller, based on Sontag's formula, so as to guarantee certain un ..."
Abstract
 Add to MetaCart
SUMMARY This work proposes a robust inverse optimal controller design for a class of nonlinear systems with bounded, timevarying uncertain variables. The basic idea is that of reshaping the scalar nonlinear gain of an L g V controller, based on Sontag's formula, so as to guarantee certain
Inverse Optimal Control with Linearlysolvable MDPs
"... We present new algorithms for inverse optimal control (or inverse reinforcement learning, IRL) within the framework of linearlysolvable MDPs. Unlike most prior IRL algorithms which recover only the control policy of the expert, we recover both the policy, the value function and the cost function. T ..."
Abstract
 Add to MetaCart
We present new algorithms for inverse optimal control (or inverse reinforcement learning, IRL) within the framework of linearlysolvable MDPs. Unlike most prior IRL algorithms which recover only the control policy of the expert, we recover both the policy, the value function and the cost function
Results 1  10
of
1,151,615