Re:Introduction to Reinforcement Learning (2015)
by suref on Sunday December 27, 2020 @12:49PM
(#25552747)
While RL is about the problem it's also about the solution. Problems/Environments are formulated in a way where methods can be applied easily (i.e. Markov decision process) and thus the solutions are directly connected to the way the problem is formulated.
Deep learning is used for function approximation and is not in contrast with evolutionary computation. You can train a neutral network policy (mapping states to actions) with an evolutionary algorithm, but most of the success has come from methods that utilize the internal structure of the problem as mentioned earlier and evolutionary algorithms do not, which is what makes these optimization strategies both weak and powerful.
Re:Introduction to Reinforcement Learning (2015)
by dgb23 on Sunday December 27, 2020 @11:21AM
(#25552023)
That makes sense thank you! It's easy to conflate the concept/problem with the tool as an outsider.
Re:Introduction to Reinforcement Learning (2015)
by computerphage on Sunday December 27, 2020 @11:34AM
(#25552120)
And it doesn't help that popular sources are perfectly happy to just call things AI or RL and leave it at that. The popular discourse around AI sometimes sounds like "How do computers work? Programming. How does google work? Programming. How do games work? Programming." Like, they're not wrong, just too vague to be useful.
RL is an optimization domain. It's the name of the problem, not the solution. You can straightforwardly use evolutionary algorithms on RL problems. However, a lot of the recent success in RL has come from using deep learning to try to solve various RL problems, not from trying evolutionary computation.