142 search results - page 8 / 29 » An Experimental Comparison of Symbolic and Connectionist Lea... |
JAIR
2008
13 years 9 months ago
2008
Several multiagent reinforcement learning (MARL) algorithms have been proposed to optimize agents' decisions. Due to the complexity of the problem, the majority of the previo...
KDD
2009
ACM
14 years 1 months ago
2009
ACM
Learning from data streams is a research area of increasing importance. Nowadays, several stream learning algorithms have been developed. Most of them learn decision models that c...
GECCO
2006
Springer
14 years 19 days ago
2006
Springer
Both genetic algorithms (GAs) and temporal difference (TD) methods have proven effective at solving reinforcement learning (RL) problems. However, since few rigorous empirical com...
ISCI
2008
13 years 9 months ago
2008
In this paper we propose a new probability update rule and sampling procedure for population-based incremental learning. These proposed methods are based on the concept of opposit...
WIA
2004
Springer
14 years 2 months ago
2004
Springer
In this paper we propose a new data structure, called shared automata, for representing deterministic finite automata (DFA). Shared automata admit a strong canonical form for DFA ...