Title | ||
---|---|---|
Dual REPS: A Generalization of Relative Entropy Policy Search Exploiting Bad Experiences. |
Abstract | ||
---|---|---|
Policy search (PS) algorithms are widely used for their simplicity and effectiveness in finding solutions for robotic problems. However, most current PS algorithms derive policies by statistically fitting the data from the best experiments only. This means that experiments yielding a poor performance are usually discarded or given too little influence on the policy update. In this paper, we propos... |
Year | DOI | Venue |
---|---|---|
2017 | 10.1109/TRO.2017.2679202 | IEEE Transactions on Robotics |
Keywords | Field | DocType |
Clustering algorithms,Robots,Optimization,Gaussian distribution,Entropy,Learning (artificial intelligence),Probability distribution | Convergence (routing),Control theory,Computer science,Duality (optimization),Probability distribution,Cluster analysis,Maxima,Optimization problem,Kullback–Leibler divergence,Reinforcement learning | Journal |
Volume | Issue | ISSN |
33 | 4 | 1552-3098 |
Citations | PageRank | References |
0 | 0.34 | 10 |
Authors | ||
2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Adria Colome | 1 | 30 | 5.89 |
Carme Torras | 2 | 1155 | 115.66 |