Publication Details

SELECT * FROM publications WHERE Record_Number=10233
Reference TypeJournal Article
Author(s)Peters, J.; Schaal, S.
TitleNatural actor critic
Journal/Conference/Book TitleNeurocomputing
Keywordsreinforcement learning, policy gradient, natural actor-critic, natural gradients
AbstractIn this paper, we suggest a novel reinforcement learning architecture, the Natural Actor-Critic. The actor updates are achieved using stochastic policy gradients em- ploying AmariÕs natural gradient approach, while the critic obtains both the natural policy gradient and additional parameters of a value function simultaneously by lin- ear regression. We show that actor improvements with natural policy gradients are particularly appealing as these are independent of coordinate frame of the chosen policy representation, and can be estimated more efficiently than regular policy gra- dients. The critic makes use of a special basis function parameterization motivated by the policy-gradient compatible function approximation. We show that several well-known reinforcement learning methods such as the original Actor-Critic and BradtkeÕs Linear Quadratic Q-Learning are in fact Natural Actor-Critic algorithms. Empirical evaluations illustrate the effectiveness of our techniques in comparison to previous methods, and also demonstrate their applicability for learning control on an anthropomorphic robot arm.
Short TitleNatural actor critic


zum Seitenanfang