output
20092025
most citedActive Learning of Inverse Models with Intrinsically Motivated Goal Exploration in Robots

451 citations

Showing 2012Show all

7 papers · 1 filter

math.PR2012★ 5 cited

Infinite dimensional weak Dirichlet processes, stochastic PDEs and optimal control

Giorgio Fabbri, Francesco Russo

The present paper continues the study of infinite dimensional calculus via regularization, started by C. Di Girolami and the second named author, introducing the notion of "weak Di…

math.PR2012★ 18 cited

GKW representation theorem and linear BSDEs under restricted information. An application to risk-minimization

Claudia Ceci, Alessandra Cretarola, Francesco Russo

In this paper we provide Galtchouk-Kunita-Watanabe representation results in the case where there are restrictions on the available information. This allows to prove existence and…

cs.LG2012★ 53 cited

Off-Policy Actor-Critic

Thomas Degris, Martha White, Richard S. Sutton

This paper presents the first actor-critic algorithm for off-policy reinforcement learning. Our algorithm is online and incremental, and its per-time-step complexity scales linearl…

math.OC2012★ 4 cited

A Stochastic Dynamic Principle for Hybrid Systems with Execution Delay and Decision Lags

K. Aouchiche, J. Frederic Bonnans, Giovanni Granato +1

This work presents a stochastic dynamic programming (SDP) algorithm that aims at minimizing an economic criteria based on the total energy consumption of a range extender electric…

physics.flu-dyn2012★ 2 cited

Do finite size neutrally buoyant particles cluster?

Lionel Fiabane, Romain Volk, Jean-Francois Pinton +3

We investigate the preferential concentration of particles which are neutrally buoyant but with a diameter significantly larger than the dissipation scale of the carrier flow. Such…

cond-mat.mtrl-sci2012★ 28 cited

Impact of microstructure, temperature and strain ratio on energy-based low- cycle fatigue life prediction models for TiAl alloys

Anne-Lise Gloanec, Thomas Milani, Gilbert Henaff

In this paper, two fatigue lifetime prediction models are tested on TiAl intermetallic using results from uniaxial low-cycle fatigue tests. Both assessments are based on dissipated…