265 search results - page 16 / 53 » Not Everything We Know We Learned |
76
Voted
JUCS
2007
14 years 9 months ago
2007
Abstract: Classification-based reinforcement learning (RL) methods have recently been proposed as an alternative to the traditional value-function based methods. These methods use...
69
Voted
DAGSTUHL
2003
14 years 11 months ago
2003
In this paper, we try to demonstrate the capability of a very simple architecture to learn to recognize and reproduce facial expressions without the innate capability to recognize ...
DIGRA
2005
Springer
15 years 3 months ago
2005
Springer
An examination of the contributions that can be made by the field of non-mechanistic cybernetics (as elaborated by Gregory Bateson and Anthony Wilden) to a theory of videogames th...
NIPS
1996
14 years 11 months ago
1996
Predictions oflifetimesofdynamicallyallocated objects can be used to improve time and space e ciency of dynamic memory management in computer programs. Barrett and Zorn 1993] used...
109
click to vote
COLT
2010
Springer
14 years 7 months ago
2010
Springer
Bandit convex optimization is a special case of online convex optimization with partial information. In this setting, a player attempts to minimize a sequence of adversarially gen...