1234 search results - page 20 / 247 » Multi-criteria Reinforcement Learning |
ICMLA
2004
15 years 1 months ago
2004
We present JoSTLe, an algorithm that performs value iteration on control problems with continuous actions, allowing this useful reinforcement learning technique to be applied to p...
102
click to vote
ICMLA
2010
14 years 9 months ago
2010
Abstract-- Policy Gradients with Parameter-based Exploration (PGPE) is a novel model-free reinforcement learning method that alleviates the problem of high-variance gradient estima...
IEAAIE
2001
Springer
15 years 4 months ago
2001
Springer
In this paper a combined use of reinforcement learning and simulated annealing is treated. Most of the simulated annealing methods suggest using heuristic temperature bounds as the...
ECML
2005
Springer
15 years 5 months ago
2005
Springer
Abstract. While direct, model-free reinforcement learning often performs better than model-based approaches in practice, only the latter have yet supported theoretical guarantees f...
ATAL
2006
Springer
15 years 3 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...