logo Idiap Research Institute        
 [BibTeX] [Marc21]
A Survey on Policy Search Algorithms for Learning Robot Controllers in a Handful of Trials
Type of publication: Journal paper
Citation: Chatzilygeroudis_T-RO_2020
Publication status: Published
Journal: IEEE Trans. on Robotics
Volume: 32
Number: 2
Year: 2020
Month: April
Pages: 328-347
URL: https://ieeexplore.ieee.org/do...
DOI: 10.1109/TRO.2019.2958211
Abstract: Most policy search algorithms require thousands of training episodes to find an effective policy, which is often infeasible with a physical robot. This survey article focuses on the extreme other end of the spectrum: how can a robot adapt with only a handful of trials (a dozen) and a few minutes? By analogy with the word "big-data", we refer to this challenge as "micro-data reinforcement learning". We show that a first strategy is to leverage prior knowledge on the policy structure (e.g., dynamic movement primitives), on the policy parameters (e.g., demonstrations), or on the dynamics (e.g., simulators). A second strategy is to create data-driven surrogate models of the expected reward (e.g., Bayesian optimization) or the dynamical model (e.g., model-based policy search), so that the policy optimizer queries the model instead of the real system. Overall, all successful micro-data algorithms combine these two strategies by varying the kind of model and prior knowledge. The current scientific challenges essentially revolve around scaling up to complex robots (e.g., humanoids), designing generic priors, and optimizing the computing time.
Keywords: Bayesian optimization, learning from demonstration, policy search
Projects Idiap
Authors Chatzilygeroudis, K.
Vassiliades, A.
Stulp, F.
Calinon, Sylvain
Mouret, J. -B.
Added by: [UNK]
Total mark: 0
  • Chatzilygeroudis_T-RO_2020.pdf