AAAI
2012
11 years 6 months ago
2012
We consider symbolic dynamic programming (SDP) for solving Markov Decision Processes (MDP) with factored state and action spaces, where both states and actions are described by se...
RAS
2010
13 years 2 months ago
2010
Policy Reuse is a reinforcement learning technique that efficiently learns a new policy by using past similar learned policies. The Policy Reuse learner improves its exploration b...
ORL
2006
13 years 4 months ago
2006
For undiscounted two-person zero-sum communicating stochastic games with finite state and action spaces, a solution procedure is proposed that exploits the communication property,...
AUTOMATICA
2007
13 years 4 months ago
2007
The sensor scheduling problem can be formulated as a controlled hidden Markov model and this paper solves the problem when the state, observation and action spaces are continuous....
NIPS
2007
13 years 5 months ago
2007
Learning in real-world domains often requires to deal with continuous state and action spaces. Although many solutions have been proposed to apply Reinforcement Learning algorithm...
NIPS
2008
13 years 5 months ago
2008
Recently, fitted Q-iteration (FQI) based methods have become more popular due to their increased sample efficiency, a more stable learning process and the higher quality of the re...
SIGECOM
2006
ACM
13 years 10 months ago
2006
ACM
While traditional mechanism design typically assumes isomorphism between the agents’ type- and action spaces, in many situations the agents face strict restrictions on their act...