Policy Gradient Methods

NoisyNet-A3C

Introduced by Fortunato et al. in Noisy Networks for Exploration

NoisyNet-A3C is a modification of A3C that utilises noisy linear layers for exploration instead of $\epsilon$-greedy exploration as in the original DQN formulation.

Source: Noisy Networks for Exploration

Papers


Paper Code Results Date Stars

Tasks


Task Papers Share
Atari Games 1 33.33%
Efficient Exploration 1 33.33%
reinforcement Learning 1 33.33%

Categories