Kuvayev, L., Sutton, R.S.: Model-based reinforcement learning with an approximate, learned model. In: Proceedings of the ninth yale workshop on adaptive and learning systems, New Haven, CT (1996) 101-105 Home/Search Document Details and Download
Summary Related Articles Check |
This paper is cited in the following contexts:
Internal Models and Anticipations in Adaptive Learning.. - Butz, Sigaud, Gérard (2 citations) (Correct)
....forms an ungeneralized representation of its environment in tabular form but it is not necessarily restricted to such a representation. Interesting enhancements of Dyna have been undertaken optimizing the internal model based RL process [35, 40] or adopting the mechanism to a tile coding approach [30]. The introduction of Dyna was kept very general so that many of the subsequent mechanisms can be characterized as Dyna mechanisms as well. Di erences can be found in the learning mechanism of the predictive model, the sensory input provided, and the behavioral policy learning. 5.2 Schema ....
Kuvayev, L., Sutton, R.S.: Model-based reinforcement learning with an approximate, learned model. In: Proceedings of the ninth yale workshop on adaptive and learning systems, New Haven, CT (1996) 101-105
Spatial Memory Structures for Sensor-Guided Robot Navigation - Balakrishnan, Honavar (Correct)
.... learning, which only requires scalar feedback, has found use in learning policy or action functions (the right set of actions to perform in each sensory state) for robots [11, 8, 10] Availability of an internal model of the environment often simplifies the learning of action functions [11, 18]. Robots that have to navigate and manipulate objects in space can benefit from structures for acquiring and using internal models or spatial maps of their environments. Such models can be of great value in the identification and avoidance of obstacles, picking up specific objects and depositing ....
L. Kuvayev and R. Sutton. Model-based reinforcement learning with an approximate, learned model. In Proceedings of the Ninth Yale Workshop on Adaptive and Learning Systems, pages 101--105, New Haven, CT, 1996. Yale University.
Predicting Financial Markets with Neural Networks - Kuvayev (1996) Self-citation (Kuvayev) (Correct)
No context found.
Kuvayev, L., and Sutton, R.S. (1996), Model-based reinforcement learning with an approximate, learned model, submitted to Advances in Neural Information Processing Systems, 8. 8
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC