Trust Region Policy Optimization

GPTKB entity

Predicate	Object
gptkbp:instanceOf	reinforcement learning algorithm
gptkbp:abbreviation	gptkb:TRPO
gptkbp:author	John Schulman, Sergey Levine, Philipp Moritz, Michael Jordan, Pieter Abbeel
gptkbp:category	deep reinforcement learning
gptkbp:citation	gptkb:Trust_Region_Policy_Optimization high
gptkbp:contrastsWith	gptkb:Proximal_Policy_Optimization vanilla policy gradient
gptkbp:field	gptkb:artificial_intelligence gptkb:machine_learning gptkb:reinforcement_learning
gptkbp:goal	improve policy optimization stability
https://www.w3.org/2000/01/rdf-schema#label	Trust Region Policy Optimization
gptkbp:inspiredBy	natural policy gradient
gptkbp:introduced	gptkb:John_Schulman
gptkbp:introducedIn	2015
gptkbp:objective	maximize expected reward
gptkbp:openSource	gptkb:OpenAI_Baselines gptkb:Stable_Baselines rllab
gptkbp:optimizationConstraint	KL-divergence constraint
gptkbp:publishedIn	arXiv preprint arXiv:1502.05477
gptkbp:relatedTo	gptkb:Deep_Deterministic_Policy_Gradient gptkb:Proximal_Policy_Optimization Actor-Critic methods
gptkbp:type	policy gradient method
gptkbp:updateRule	constrained optimization
gptkbp:usedFor	robotics games continuous control tasks
gptkbp:uses	trust region methods
gptkbp:bfsParent	gptkb:TRPO gptkb:Trust_Region_Policy_Optimization_(TRPO)
gptkbp:bfsLayer	7