688 search results - page 52 / 138 » Using reinforcement learning to adapt an imitation task |
ICMLA
2010
13 years 5 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...
ECAI
2000
Springer
14 years 6 days ago
2000
Springer
This paper investigates the problem of improving the performance of general state-of-the-art robot control systems by autonomously adapting them to specific tasks and environments...
ICML
2009
IEEE
14 years 8 months ago
2009
IEEE
Reinforcement Learning methods for controlling stochastic processes typically assume a small and discrete action space. While continuous action spaces are quite common in real-wor...
HIS
2004
13 years 9 months ago
2004
Case-based reasoning (CBR) is a knowledge-based problem-solving technique, which is based on reuse of previous experiences. In this paper we propose a new model for static task as...
CEC
2009
IEEE
14 years 2 months ago
2009
IEEE
Abstract— A combination of backpropagation and neuroevolution is used to train a neural network visual controller for agents in the Quake II environment. The agents must learn to...