Re:Towards deep symbolic reinforcement learning
by aub3bhat on Saturday October 15, 2016 @05:22PM
(#12715700)
It seems like a really interesting approach but it needs to be validated on a larger set of Atari games. Considering even a Linear learner outperforms DQN on several games such as Double Dunk. It's possible that the DQN underperforms because the game is more amenable to the symbolic representation used. [0]
[0] Figure 3 http://home.uchicago.edu/~arij/journalclub/papers/2015_Mnih_...