Diversity-based inference of finite automata
Journal of the ACM (JACM)
Continual learning in reinforcement environments
Continual learning in reinforcement environments
Introduction to Reinforcement Learning
Introduction to Reinforcement Learning
Reinforcement learning with selective perception and hidden state
Reinforcement learning with selective perception and hidden state
A planning algorithm for predictive state representations
IJCAI'03 Proceedings of the 18th international joint conference on Artificial intelligence
Proceedings of the 6th international joint conference on Autonomous agents and multiagent systems
SAB '08 Proceedings of the 10th international conference on Simulation of Adaptive Behavior: From Animals to Animats
Relational knowledge with predictive state representations
IJCAI'07 Proceedings of the 20th international joint conference on Artifical intelligence
Point-based planning for predictive state representations
Canadian AI'08 Proceedings of the Canadian Society for computational studies of intelligence, 21st conference on Advances in artificial intelligence
Temporal-difference networks for dynamical systems with continuous observations and actions
UAI '09 Proceedings of the Twenty-Fifth Conference on Uncertainty in Artificial Intelligence
Goal-Directed online learning of predictive models
EWRL'11 Proceedings of the 9th European conference on Recent Advances in Reinforcement Learning
Better generalization with forecasts
IJCAI'13 Proceedings of the Twenty-Third international joint conference on Artificial Intelligence
Hi-index | 0.00 |
The predictive representations hypothesis holds that particularly good generalization will result from representing the state of the world in terms of predictions about possible future experience. This hypothesis has been a central motivation behind recent research in, for example, PSRs and TD networks. In this paper we present the first explicit investigation of this hypothesis. We show in a reinforcement-learning example (a grid-world navigation task) that a predictive representation in tabular form can learn much faster than both the tabular explicit-state representation and a tabular history-based method.