Olivier Teytaud

artificial intelligence games evolutionary algorithms game of go power systems uct monte-carlo tree search mcts black-box optimization upper confidence tree optimization partial observation open source parallel optimization noisy optimization deep networks energy management minesweeper intelligence artificielle direct policy search derivative free optimization computational complexity simulation-based optimization monte carlo tree search undecidability fully parallel optimization energy transition exp3 unit commitment killall-go quasi-random numbers nash equilibria comparison-based optimization bandits parallelism svn tao team multiobjective optimization computer games zermelo algorithm alpha-beta concurrent version systems linux openoffice energy provocative statements bias variance phantom games exact solving partially observable game weights complexity bounds active learning batch active learning partially observable games endgames phantom-go kriegspiel blind games memory in games intelligencia artificial juego del go debugging development rules programming very short introduction to direct policy search evolutionary algorithm bias and variance emna self-adaptation cumulative step-size adaptation bilevel problems multistage problems functional programming france machine learning applications decidability global optimization multimodal optimization expensive optimization reweightings hydroelectricity reinforcement learning wald criterion uncertainty savage criterion bias correction bootstrap jackknife open data investments public continuous non-linear optimization apprentissage automatique vision artificielle réseaux neuronaux profonds evolution strategies uncertainties random search tuning hyperparameter search hyperparameter tuning numerical optimization particle swarm optimization differential evolution bayesian optimization game of havannah game of hex alpha-zero deep learning zero learning alphazero computer vision environment water monte carlo tree search;upper confidence trees operation research; introduction artificial intelligence; games monte-carlo tree seach; subgoal learning; macro-ac sequential decision making games; partial information; artificial intelligenc planning hidden information unstructured optimization simple regrets opening book generation go 7x7 shape game stochastic modelling random positions estimation of distribution algorithms complexity planning;power systems réseau éléctrique;centrales électriques électricité;centrales de production;réseau de t statistics;101 fuzzy control go;ai;portfolio;random seeds vc-dimension dynamic programming bandit ucb texp3 metagaming power systems;markov decision processes; optimizat power systems; optimization noisy optimization; simulation-based optimization model predictive control;stochastic dynamic progra computational intelligence automatic parallelization