97 search results - page 9 / 20 » Guiding Inference with Policy Search Reinforcement Learning |
ACL
2009
14 years 9 months ago
2009
In this paper, we present a reinforcement learning approach for mapping natural language instructions to sequences of executable actions. We assume access to a reward function tha...
106
click to vote
ICML
2001
IEEE
16 years 13 days ago
2001
IEEE
Direct policy search is a practical way to solve reinforcement learning problems involving continuous state and action spaces. The goal becomes finding policy parameters that maxi...
ICML
2006
IEEE
16 years 13 days ago
2006
IEEE
In the model-based policy search approach to reinforcement learning (RL), policies are found using a model (or "simulator") of the Markov decision process. However, for ...
ICML
2009
IEEE
16 years 13 days ago
2009
IEEE
In this paper we introduce the first algorithms for efficiently learning a simulation policy for Monte-Carlo search. Our main idea is to optimise the balance of a simulation polic...
89
Voted
ICML
2010
IEEE
15 years 21 days ago
2010
IEEE
We consider the problem of multi-task reinforcement learning where the learner is provided with a set of tasks, for which only a small number of samples can be generated for any g...