Showing results 21 to 23 of 23
  Inferring bounds on the performance of a control policy from a sample of trajectoriesFonteneau, Raphaël  ; ; Wehenkel, Louis et alin Proceedings of the IEEE International Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL-09) (2009) We propose an approach for inferring bounds on the finite-horizon return of a control policy from an off-policy sample of trajectories collecting state transitions, rewards, and control actions. In this ... [more ▼] We propose an approach for inferring bounds on the finite-horizon return of a control policy from an off-policy sample of trajectories collecting state transitions, rewards, and control actions. In this paper, the dynamics, control policy, and reward function are supposed to be deterministic and Lipschitz continuous. Under these assumptions, a polynomial algorithm, in terms of the sample size and length of the optimization horizon, is derived to compute these bounds, and their tightness is characterized in terms of the sample density. [less ▲] Detailed reference viewed: 35 (10 ULg)Modelling the influence of activation-induced apoptosis of CD4+ and CD8+ T-cells on the immune system response of a HIV-infected patient; Belmudes, Florence ; Fonteneau, Raphaël et alin IET Systems Biology (2008), 2(2), 94-102 On the basis of the human immunodeficiency virus (HIV) infection dynamics model proposed by Adams, the authors propose an extended model that aims at incorporating the influence of activation-induced ... [more ▼] On the basis of the human immunodeficiency virus (HIV) infection dynamics model proposed by Adams, the authors propose an extended model that aims at incorporating the influence of activation-induced apoptosis of CD4+ and CD8+ T-cells on the immune system response of HIV-infected patients. Through this model, the authors study the influence of this phenomenon on the time evolution of specific cell populations such as plasma concentrations of HIV copies, or blood concentrations of CD4+ and CD8+ T-cells. In particular, this study shows that depending on its intensity, the apoptosis phenomenon can either favour or mitigate the long-term evolution of the HIV infection. [less ▲] Detailed reference viewed: 54 (10 ULg)Variable selection for dynamic treatment regimes: a reinforcement learning approachFonteneau, Raphaël ; Wehenkel, Louis ; Ernst, Damien Conference (2008) Dynamic treatment regimes (DTRs) can be inferred from data collected through some randomized clinical trials by using reinforcement learning algorithms. During these clinical trials, a large set of ... [more ▼] Dynamic treatment regimes (DTRs) can be inferred from data collected through some randomized clinical trials by using reinforcement learning algorithms. During these clinical trials, a large set of clinical indicators are usually monitored. However, it is often more convenient for clinicians to have DTRs which are only defined on a small set of indicators rather than on the original full set. To address this problem, we analyse the approximation architecture of the state-action value functions computed by the fitted Q iteration algorithm - a RL algorithm - using tree-based regressors in order to identify a small subset of relevant ones. The RL algorithm is then rerun by considering only as state variables these most relevant indicators to have DTRs defined on a small set of indicators. The approach is validated on benchmark problems inspired from the classical ‘car on the hill’ problem and the results obtained are positive. [less ▲] Detailed reference viewed: 41 (5 ULg)
|
||
