.png){kind=icon}
.png){kind=icon}
Return
Parameter-exploring policy gradients
.png){kind=icon}
OA
AI
DOI：10.1016/j.neunet.2009.12.004.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
We present a model-free reinforcement learning method for partially observable Markov decision problems. Our method estimates a likelihood gradient by sampling directly in parameter space, which leads to lower variance gradient estimates than obtained by regular policy gradient methods. We show that for several complex control tasks, including robust standing with a humanoid robot, this method outperforms well-known algorithms from the fields of standard policy gradients, finite difference methods and population based heuristics. We also show that the improvement is largest when the parameter samples are drawn symmetrically. Lastly we analyse the importance of the individual components of our method by incrementally incorporating them into the other algorithms, and measuring the gain in performance after each step. (C) 2009 Elsevier Ltd. All rights reserved.
Keywords:
Policy gradients
Stochastic optimisation
Reinforcement learning
Robotics
Control
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
6.3
Papers:
7.8K
Citations:
3.0W