39 search results - page 2 / 8 » Learning Probabilistic Relational Planning Rules |
ICMLA
2009
13 years 2 months ago
2009
Languages that combine predicate logic with probabilities are needed to succinctly represent knowledge in many real-world domains. We consider a formalism based on universally qua...
JAIR
2007
13 years 4 months ago
2007
In this article, we work towards the goal of developing agents that can learn to act in complex worlds. We develop a a new probabilistic planning rule representation to compactly ...
AIPS
2007
13 years 6 months ago
2007
In sequential decision-making problems formulated as Markov decision processes, state-value function approximation using domain features is a critical technique for scaling up the...
ATAL
2006
Springer
13 years 8 months ago
2006
Springer
RVRL (Rule Value Reinforcement Learning) is a new algorithm which extends an existing learning framework that models the environment of a situated agent using a probabilistic rule...
AGENTS
1998
Springer
13 years 8 months ago
1998
Springer
Physical domains are notoriously hard to model completely and correctly, especially to capture the dynamics of the environment. Moreover, since environments change, it is even mor...