Policy Gradient Methods

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.

Source: Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation

Papers


Paper Code Results Date Stars

Tasks


Task Papers Share
Imitation Learning 1 20.00%
OpenAI Gym 1 20.00%
Atari Games 1 20.00%
Continuous Control 1 20.00%
reinforcement Learning 1 20.00%

Categories