Re:Why traditional reinforcement learning will probably not ...
by xamuel on Friday October 23, 2020 @12:44PM
(#24871345)
I make no attempt to disprove an entire field, rather to question an implicit assumption, namely that real number rewards are flexible enough to capture all relevant environments an AGI should be able to comprehend. Quite the opposite, I indicate ways reinforcement learning could be modified to get past the roadblock I point out with real numbers.
Since you mentioned higher dimensional representations for rewards, I want to remind that the sub-fields of Inverse RL and Model-based RL are concerned with reward representation and prediction by neural nets.
Also, it doesn't seem like a good idea to try to disprove an entire field with a purely theoretical (a-priori) argument. There should be at least some consideration given to the state of the art in the field.