Add to ORKGpeer reviewedWe propose new methods for guiding the generation of informative trajectories when solving discrete-time optimal control problems. These methods exploit recently published results that provide ways for computing bounds on the return of control policies from a set of trajectories
In this paper, we study the optimal stopping problem in the so-called exploratory framework, in whic...
International audienceWe consider the problem of finding a near-optimal policy using value-function ...
We consider deterministic optimal control problems with continuous state spaces where the informatio...
Abstract We propose new methods for guiding the generation of informative trajectories when solving ...
peer reviewedWe propose an approach for inferring bounds on the finite-horizon return of a control p...
Many Stochastic Optimal Control (SOC) approaches rely on samples to either obtain an estimate of th...
peer reviewedWe study the minmax optimization problem introduced in [Fonteneau et al. (2011), ``Towa...
This dissertation presents various research contributions published during these four years of PhD i...
Trajectory-Centric Reinforcement Learning and Trajectory Optimization methods optimize a sequence of...
proaches rely on samples to either obtain an estimate of the value function or a linearisation of th...
International audiencePolicy search is a method for approximately solving an optimal control problem...
Reinforcement learning describes how an agent can learn to act in an unknown environment in order to...
peer reviewedWe propose a strategy for experiment selection - in the context of reinforcement learni...
peer reviewedWe introduce the Optimal Sample Selection (OSS) meta-algorithm for solving discrete-tim...
Stochastic Optimal Control (SOC) is typically used to plan a movement for a specific situation. Whil...
In this paper, we study the optimal stopping problem in the so-called exploratory framework, in whic...
International audienceWe consider the problem of finding a near-optimal policy using value-function ...
We consider deterministic optimal control problems with continuous state spaces where the informatio...
Abstract We propose new methods for guiding the generation of informative trajectories when solving ...
peer reviewedWe propose an approach for inferring bounds on the finite-horizon return of a control p...
Many Stochastic Optimal Control (SOC) approaches rely on samples to either obtain an estimate of th...
peer reviewedWe study the minmax optimization problem introduced in [Fonteneau et al. (2011), ``Towa...
This dissertation presents various research contributions published during these four years of PhD i...
Trajectory-Centric Reinforcement Learning and Trajectory Optimization methods optimize a sequence of...
proaches rely on samples to either obtain an estimate of the value function or a linearisation of th...
International audiencePolicy search is a method for approximately solving an optimal control problem...
Reinforcement learning describes how an agent can learn to act in an unknown environment in order to...
peer reviewedWe propose a strategy for experiment selection - in the context of reinforcement learni...
peer reviewedWe introduce the Optimal Sample Selection (OSS) meta-algorithm for solving discrete-tim...
Stochastic Optimal Control (SOC) is typically used to plan a movement for a specific situation. Whil...
In this paper, we study the optimal stopping problem in the so-called exploratory framework, in whic...
International audienceWe consider the problem of finding a near-optimal policy using value-function ...
We consider deterministic optimal control problems with continuous state spaces where the informatio...