178 search results - page 27 / 36 » Probabilistic policy reuse in a reinforcement learning agent |
AAAI
1998
13 years 10 months ago
1998
Reinforcement learning is an effective technique for learning action policies in discrete stochastic environments, but its efficiency can decay exponentially with the size of the ...
AAAI
2010
13 years 10 months ago
2010
Recent advancements in model-based reinforcement learning have shown that the dynamics of many structured domains (e.g. DBNs) can be learned with tractable sample complexity, desp...
AAAI
2008
13 years 11 months ago
2008
Proactive assessment of computer-network vulnerability to unknown future attacks is an important but unsolved computer security problem where AI techniques have significant impact...
AAAI
2012
11 years 11 months ago
2012
Markov decision processes (MDPs) are an established framework for solving sequential decision-making problems under uncertainty. In this work, we propose a new method for batchmod...
GECCO
2004
Springer
14 years 2 months ago
2004
Springer
A new graph-based evolutionary algorithm named “Genetic Network Programming, GNP” has been proposed. GNP represents its solutions as directed graph structures, which can improv...