Selective Neural Network Ensembles in Reinforcement Learning
نویسندگان
چکیده
Ensemble models can achieve more accurate predictions than single learners. Selective ensembles further improve the predictions by selecting an informative subset of the full ensemble. We consider reinforcement learning ensembles, where the members are neural networks. In this context we study a new algorithm for ensemble subset selection in reinforcement learning scenarios. The aim of the proposed learning strategy is to minimize the Bellman errors of the collected states. In the empirical evaluation, two benchmark applications with large state spaces have been considered, namely SZ-Tetris and generalized maze. Here, our selective ensemble algorithm significantly outperforms other approaches.
منابع مشابه
Reinforcement Learning in Neural Networks: A Survey
In recent years, researches on reinforcement learning (RL) have focused on bridging the gap between adaptive optimal control and bio-inspired learning techniques. Neural network reinforcement learning (NNRL) is among the most popular algorithms in the RL framework. The advantage of using neural networks enables the RL to search for optimal policies more efficiently in several real-life applicat...
متن کاملReinforcement Learning in Neural Networks: A Survey
In recent years, researches on reinforcement learning (RL) have focused on bridging the gap between adaptive optimal control and bio-inspired learning techniques. Neural network reinforcement learning (NNRL) is among the most popular algorithms in the RL framework. The advantage of using neural networks enables the RL to search for optimal policies more efficiently in several real-life applicat...
متن کاملEnsemble Usage for More Reliable Policy Identification in Reinforcement Learning
Reinforcement learning (RL) methods employing powerful function approximators like neural networks have become an interesting approach for optimal control. Since they learn a policy from observations, they are also applicable when no analytical description of the system is available. Although impressive results have been reported, their handling in practice is still hard, as they can fail at re...
متن کاملEnsemble of GA based Selective Neural Network Ensembles
Neural network ensemble is a learning paradigm where several neural networks are jointly used to solve a problem. In this paper, e-GASEN, a twolayer neural network ensemble architecture is proposed, in which the base learners of the final ensemble are also ensembles. Experimental results show that e-GASEN generalizes better than a popular ensemble method. The reason why e-GASEN works is also di...
متن کاملAn Unsupervised Learning Method for an Attacker Agent in Robot Soccer Competitions Based on the Kohonen Neural Network
RoboCup competition as a great test-bed, has turned to a worldwide popular domains in recent years. The main object of such competitions is to deal with complex behavior of systems whichconsist of multiple autonomous agents. The rich experience of human soccer player can be used as a valuable reference for a robot soccer player. However, because of the differences between real and simulated soc...
متن کامل