Bellemare
A reinforcement learning researcher and one of the pioneers of distributional reinforcement learning, who proposed the C51 algorithm.
Timeline (last 90 days)
Distributional reinforcement learning (DRL) learns the full distribution of returns rather than only their expectation, an idea first systematized by Bellemare et al. in the C51 algorithm.
The C51 algorithm, proposed by Bellemare et al. in 2017, is the first algorithm to successfully apply distributional reinforcement learning to Atari games; it approximates the return distribution with 51 fixed support points and updates the distribution through a projection step.
All Facts (2)
Distributional reinforcement learning (DRL) learns the full distribution of returns rather than only their expectation, an idea first systematized by Bellemare et al. in the C51 algorithm.
50%UnverifiedThe C51 algorithm, proposed by Bellemare et al. in 2017, is the first algorithm to successfully apply distributional reinforcement learning to Atari games; it approximates the return distribution with 51 fixed support points and updates the distribution through a projection step.
50%