Learning Values Across Many Orders Of Magnitude
neural information processing systems(2016)
摘要
Most learning algorithms are not invariant to the scale of the signal that is being approximated. We propose to adaptively normalize the targets used in the learning updates. This is important in value-based reinforcement learning, where the magnitude of appropriate value approximations can change over time when we update the policy of behavior. Our main motivation is prior work on learning to play Atari games, where the rewards were clipped to a predetermined range. This clipping facilitates learning across many different games with a single learning algorithm, but a clipped reward function can result in qualitatively different behavior. Using adaptive normalization we can remove this domain-specific heuristic without diminishing overall performance.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络