Baldassi C, Gerace F., Kappen H.J., Lucibello C., Saglietti L., Tartaglione E., Zecchina R.
Role of synaptic stochasticity in training low-precision neural netwtorks.
Physical Review Letters,
vol. 120,
no. 26,
pp. 268103-1-6,
2018
Ruiz Euler H.C., Rebelo Marques J.P , Kappen H.J.
Nonlinear deconvolution by sampling biophysically plausible hemodynamic models.
arxiv,
2018
Ruiz Euler H.C., Kappen H.J.
Effective connectivity from single trial fmri data by sampling biologically plausible models.
arxiv,
2018
Thijssen S.A., Kappen H.J.
Consistent adaptive multiple importance sampling and controlled diffusions.
arxiv,
2018
Thalmeier D., Gómez V., Kappen H.J.
Action selection in growing state spaces:
control of network structure growth.
Journal of Physics A,
vol. 50,
pp. 1-21,
2017
Ruiz H.C., Kappen H.J.
Particle smoothing for hidden diffusion processes: adaptive path integral smoother.
IEEE Transactions on Signal Processing,
vol. 65,
pp. 3391-3203,
2017
McGuire, K.N., Croon G. de, Tuyls K., Kappen H.J.
Efficient optical flow and stereo vision for an autonomous pocket drone..
IEEE transactions on Automatic Control,
vol. 2,
pp. 1070-1076,
2017
Nauta J., Thalmeier D., Kappen H.J.
About path integrals, trust regions and feynman diagrams.
Master Thesis,
2017
Thalmeier D., Gómez V., Kappen H.J.
Optimal control of network structure growth.
NIPS workshop on Advances in Approximate Bayesian Inference,
2016
Ruiz Euler, Kappen H.J.
Smoothing estimates of diffusion processes.
NIPS workshop on Advances in Approximate Bayesian Inference,
2016
Gómez V., Thijssen S.A., Symington A., Hailes Stephen, Kappen H.J.
Real-time stochastic optimal control for multi-agent quadrotor swarm.
RSS Workshop R4Sim2015 Rome,
2015
Kappen H.J., Ruiz H.C., Christian H.
Adaptive importance sampling for control and inference.
Journal of Statistical Physics,
2015
Thalmeier D., Uhlmann M., Memmesheimer R., Kappen H.J.
Learning universal computations with spikes.
UNKNOWN,
2015
Matsubara T., Gómez V., Kappen H.J.
Latent kullback leibler control for continuous-state systems using probabilistic graphical models.
Proceedings UAI,
vol. 30 th,
pp. 1-10,
2014
Gheshlaghi Azar M., Munos R., Ghavamzadaeh M., Kappen H.J.
Speedy q-learning: a computationally efficient reinforcement learning algorithm with a near optimal rate of convergence.
Journal of Machine Learning Research,
2013
Kappen H.J.
Comment: causal entropic forces.
Technical Report,
pp. http://arxiv.org/abs/1312.4185,
2013
Thijssen S.A., Kappen H.J.
Stochastic path integral control.
International Journal of Control,
2013
Llera A., Gómez V., Kappen H.J.
Adaptive classification on brain computer interfaces using reinforcement signals.
Neural Computation,
vol. 24,
no. 11,
pp. 2900-2923,
2012
Gheshlaghi Azar M.
On the theory of reinforcement learning methods, convergence analysis and sample complexity..
PhD Thesis,
pp. 1-143,
2012
Tramper J.J., Broek J.L. van den, Wiegerinck W.A.J.J., Kappen H.J., Gielen C.C.A.M.
Stochastic optimal control predicts human motor behavior in time-constrained
sensorimotor tasks.
Biological Cybernetics,
pp. xx,
2011
Broek J.L. van den, Wiegerinck W.A.J.J., Kappen H.J.
Stochastic optimal control of state constrained systems.
International Journal of Control,
vol. 84,
no. 3,
pp. 597-615,
2011
Gheshlaghi Azar M., Kappen H.J.
Dynamic policy programming with kl-divergence minimization.
NIPS Workshop on Probabilistic Approaches for Stochastic Optimal Control and Robotics,
2009