Local Updates, Global Learning (LUGL): Playing Games with non-incremental Learners
The dominance of Neural Networks (NNs) in RL is partially due to their incremental learning capability, which naturally suits the online, non-stationary nature of self-play training. However, gradient-boosted trees like LightGBM are widely recognised as the state of the art for tabular data in supervised learning, ofte...
David Milec, Spyridon Samothrakis, Michael Fairbank et al.
· IEEE Transactions on Games · 0 citations