scientific article; zbMATH DE number 6982305

MaRDI QIDQ4558153zbMATH OpenFDO

Authors Riad Akrour, A. Abdolmaleki, Hany Abdulsamad, Jan Peters, Gerhard Neumann

Publication date 21 November 2018

Full work available at URL https://arxiv.org/abs/1606.09197, http://jmlr.csail.mit.edu/papers/v19/17-329.html

zbMATH Keywords

reinforcement learningroboticstrajectory optimizationpolicy optimization

Mathematics Subject Classification ID

Statistical aspects of information-theoretic topics (62B10) Learning and adaptive systems in artificial intelligence (68T05) Markov and semi-Markov decision processes (90C40)

Recommendations

• Using trajectory data to improve Bayesian optimization for reinforcement learning
• An incremental off-policy search in a model-free Markov decision process using a single sample path
• A stochastic trust-region framework for policy optimization
• Policy gradient in continuous time
• On the policy improvement algorithm in continuous time
• Safe policy iteration: a monotonically improving approximate policy iteration approach

Cites work

• scientific article; zbMATH DE number 1095138 (Why is no real title available?)
• scientific article; zbMATH DE number 6982305 (Why is no real title available?)
• A generalized path integral control approach to reinforcement learning
• Algorithms for reinforcement learning.
• Hierarchical relative entropy policy search
• Model-based contextual policy search for data-efficient generalization of robot skills
• Policy gradient in Lipschitz Markov decision processes

Cited in

(7)

• TD-regularized actor-critic methods
• Experiments with Tractable Feedback in Robotic Planning Under Uncertainty: Insights over a Wide Range of Noise Regimes
• Expected policy gradients for reinforcement learning
• scientific article; zbMATH DE number 7307467 (Why is no real title available?)
• scientific article; zbMATH DE number 6982305 (Why is no real title available?)
• Optimistic reinforcement learning by forward Kullback-Leibler divergence optimization
• Compatible natural gradient policy search

Describes a project that uses

Uses Software

• GitHub
• PILCO
• Baselines

This page was built for publication:

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4558153)