Sciweavers

494 search results - page 16 / 99
» Evaluating a Reinforcement Learning Algorithm with a General...
Sort
View
ATAL
2009
Springer
14 years 2 months ago
Solving multiagent assignment Markov decision processes
We consider the setting of multiple collaborative agents trying to complete a set of tasks as assigned by a centralized controller. We propose a scalable method called“Assignmen...
Scott Proper, Prasad Tadepalli
AAAI
2007
13 years 10 months ago
RETALIATE: Learning Winning Policies in First-Person Shooter Games
In this paper we present RETALIATE, an online reinforcement learning algorithm for developing winning policies in team firstperson shooter games. RETALIATE has three crucial chara...
Megan Smith, Stephen Lee-Urban, Hector Muño...
ECAI
2008
Springer
13 years 9 months ago
Exploiting locality of interactions using a policy-gradient approach in multiagent learning
In this paper, we propose a policy gradient reinforcement learning algorithm to address transition-independent Dec-POMDPs. This approach aims at implicitly exploiting the locality...
Francisco S. Melo
GECCO
2007
Springer
293views Optimization» more  GECCO 2007»
14 years 1 months ago
Solving the artificial ant on the Santa Fe trail problem in 20, 696 fitness evaluations
In this paper, we provide an algorithm that systematically considers all small trees in the search space of genetic programming. These small trees are used to generate useful subr...
Steffen Christensen, Franz Oppacher
ICML
2005
IEEE
14 years 8 months ago
High speed obstacle avoidance using monocular vision and reinforcement learning
We consider the task of driving a remote control car at high speeds through unstructured outdoor environments. We present an approach in which supervised learning is first used to...
Jeff Michels, Ashutosh Saxena, Andrew Y. Ng