McCallum, R. A. (1994b). Reduced Training Time for Reinforcement Learning with Hidden State.  Home/Search Document Details and Download
Summary Related Articles Check |
This paper is cited in the following contexts:
Deictic Codes for the Embodiment of Cognition - Ballard, Hayhoe, Pook, Rao (1995) (31 citations) (Correct)
....Deictic pointers provide a way of understanding this cost accounting. Identifying working memory items with pointers suggests that temporary memory should be minimized. It simplifies the credit assignment problem in cognitive programs as described in Section 2 [Whitehead and Ballard, 1991, McCallum, 1994, Pook and Ballard, 1994a] 4. The simplification of sensory motor routines. The use of deictic codes leads to functional models of vision wherein the representational products are only computed if they are vital to the current cognitive program. It is always a good idea to give the brain less to ....
McCallum, R. (1994). Reduced training time for reinforcement learning with hidden state. In Proc., 11th Int'l. Machine Learning Workshop (Robot Learning), New Brunswick, NJ.
Greedy Utile Suffix Memory for Reinforcement Learning with.. - Leonard Breslow (1996) (Correct)
No context found.
McCallum, R. A. (1994b). Reduced Training Time for Reinforcement Learning with Hidden State.
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