Person
Tuomas Haarnoja
A researcher at UC Berkeley and primary originator of the Soft Actor-Critic (SAC) algorithm, with significant contributions to the field of maximum entropy reinforcement learning.
Timeline (last 90 days)
Sep 11
SAC (Soft Actor-Critic) was proposed by Tuomas Haarnoja et al. at UC Berkeley, introduces the maximum entropy reinforcement learning framework, and is an off-policy method
Unverified50%
Aug 27
SAC由Tuomas Haarnoja等人在2018年提出，是最大熵强化学习框架的代表算法，属于off-policy算法，样本效率高于PPO
Unverified50%