Methods › Reinforcement Learning › Policy Gradient Methods › ACTKR
ACTKR
Introduced by Yuhuai Wu et al. in Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
ACKTR, or Actor Critic with Kronecker-factored Trust Region, is an actor-critic method for reinforcement learning that applies trust region optimization using a recently proposed Kronecker-factored approximation to the curvature. The method extends the framework of natural policy gradient and optimizes both the actor and the critic using Kronecker-factored approximate curvature (K-FAC) with trust region.
Papers archive 2025-07-28
2 shown of 2, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.
-
myGym: Modular Toolkit for Visuomotor Robotic Tasks 21 Dec 2020 · 0 repositories · arXiv:2012.11643
-
Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation 17 Aug 2017 · 8 repositories · arXiv:1708.05144Syntology ran 1 of 1 samples · 0 unverified
Tasks archive 2025-07-28
10 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
Usage over time archive 2025-07-28
Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).
Categories archive 2025-07-28
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections