Suchergebnisse - "IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning"

Approximate real-time optimal control based on sparse Gaussian process models von Boedecker, Joschka, Springenberg, Jost Tobias, Wulfing, Jan, Riedmiller, Martin

“… In this paper we present a fully automated approach to (approximate) optimal control of non-linear systems. Our algorithm jointly learns a non-parametric model …”
Volltext

Protecting against evaluation overfitting in empirical reinforcement learning von Whiteson, S., Tanner, B., Taylor, M. E., Stone, P.

“… Empirical evaluations play an important role in machine learning. However, the usefulness of any evaluation depends on the empirical methodology employed …”
Volltext

Model-based multi-objective reinforcement learning von Wiering, Marco A., Withagen, Maikel, Drugan, Madalina M.

“… This paper describes a novel multi-objective reinforcement learning algorithm. The proposed algorithm first learns a model of the multi-objective sequential …”
Volltext

Reinforcement learning in the game of Othello: Learning against a fixed opponent and learning from self-play von van der Ree, Michiel, Wiering, Marco

“… This paper compares three strategies in using reinforcement learning algorithms to let an artificial agent learn to play the game of Othello. The three …”
Volltext

Pseudo-MDPs and factored linear action models von Hengshuai Yao, Szepesvari, Csaba, Pires, Bernardo Avila, Xinhua Zhang

“… In this paper we introduce the concept of pseudo-MDPs to develop abstractions. Pseudo-MDPs relax the requirement that the transition kernel has to be a …”
Volltext

Reinforcement learning algorithms for solving classification problems von Wiering, M. A., van Hasselt, H., Pietersma, Auke-Dirk, Schomaker, L.

“… We describe a new framework for applying reinforcement learning (RL) algorithms to solve classification tasks by letting an agent act on the inputs and learn …”
Volltext

A comparison of approximate dynamic programming techniques on benchmark energy storage problems: Does anything work? von Jiang, Daniel R., Pham, Thuy V., Powell, Warren B., Salas, Daniel F., Scott, Warren R.

“… As more renewable, yet volatile, forms of energy like solar and wind are being incorporated into the grid, the problem of finding optimal control policies for …”
Volltext

Data-driven partially observable dynamic processes using adaptive dynamic programming von Xiangnan Zhong, Zhen Ni, Yufei Tang, Haibo He

“… Adaptive dynamic programming (ADP) has been widely recognized as one of the "core methodologies" to achieve optimal control for intelligent systems in Markov …”
Volltext

Parametric value function approximation: A unified view von Geist, M., Pietquin, O.

“… Reinforcement learning (RL) is a machine learning answer to the optimal control problem. It consists of learning an optimal control policy through interactions …”
Volltext

Multi-objective reinforcement learning for AUV thruster failure recovery von Ahmadzadeh, Seyed Reza, Kormushev, Petar, Caldwell, Darwin G.

“… This paper investigates learning approaches for discovering fault-tolerant control policies to overcome thruster failures in Autonomous Underwater Vehicles …”
Volltext

Annealing-pareto multi-objective multi-armed bandit algorithm von Yahyaa, Saba Q., Drugan, Madalina M., Manderick, Bernard

“… In the stochastic multi-objective multi-armed bandit (or MOMAB), arms generate a vector of stochastic rewards, one per objective, instead of a single scalar …”
Volltext

Active learning for classification: An optimistic approach von Collet, Timothe, Pietquin, Olivier

“… In this paper, we propose to reformulate the active learning problem occurring in classification as a sequential decision making problem. We particularly focus …”
Volltext

Approximate reinforcement learning: An overview von Busoniu, L., Ernst, D., De Schutter, B., Babuska, R.

“… Reinforcement learning (RL) allows agents to learn how to optimally interact with complex environments. Fueled by recent advances in approximation-based …”
Volltext

Neural network-based adaptive optimal consensus control of leaderless networked mobile robots von Guzey, Haci Mehmet, Hao Xu, Jagannathan, S.

“… A novel neural network (NN)-based optimal adaptive consensus control scheme is introduced in this paper for networked mobile robots in the presence of unknown …”
Volltext

Using approximate dynamic programming for estimating the revenues of a hydrogen-based high-capacity storage device von Francois-Lavet, Vincent, Fonteneau, Raphael, Ernst, Damien

“… This paper proposes a methodology to estimate the maximum revenue that can be generated by a company that operates a high-capacity storage device to buy or …”
Volltext

Information-theoretic stochastic optimal control via incremental sampling-based algorithms von Arslan, Oktay, Theodorou, Evangelos A., Tsiotras, Panagiotis

“… This paper considers optimal control of dynamical systems which are represented by nonlinear stochastic differential equations. It is well-known that the …”
Volltext

Pareto Upper Confidence Bounds algorithms: An empirical study von Drugan, Madalina M., Nowe, Ann, Manderick, Bernard

“… Many real-world stochastic environments are inherently multi-objective environments with conflicting objectives. The multi-objective multi-armed bandits …”
Volltext

Exploring the relationship of reward and punishment in reinforcement learning von Lowe, Robert, Ziemke, Tom

“… We present a reinforcement learning algorithm based on Dyna-Sarsa that utilizes separate representations of reward and punishment when guiding state-action …”
Volltext

An analysis of optimistic, best-first search for minimax sequential decision making von Busoniu, Lucian, Munos, Remi, Pall, Elod

“… We consider problems in which a maximizer and a minimizer agent take actions in turn, such as games or optimal control with uncertainty modeled as an opponent …”
Volltext

Real-time tracking on adaptive critic design with uniformly ultimately bounded condition von Zhen Ni, Xiao Fang, Haibo He, Dongbin Zhao, Xin Xu

“… In this paper, we proposed a new nonlinear tracking controller based on heuristic dynamic programming (HDP) with the tracking filter. Specifically, we …”
Volltext