mugoh
  • Member for 1 year, 4 months
  • Last seen this week
0 answers
1 votes
16 views
Are there guiding principles as to which activation functions suit a given RL algorithm?
0 answers
1 votes
20 views
What's mutual exclusivity in meta-learning?
1 answers
1 votes
51 views
Why are shallow networks so prevalent in RL?
0 answers
1 votes
127 views
What adapts an algorithm to continuous or to discrete action spaces?
2 answers
2 votes
180 views
1 bookmarks
When should one prefer using Total Variational Divergence over KL divergence in RL
1 answers
2 votes
162 views
What are proxy reward functions?
1 answers
2 votes
68 views
Are linear approximators better suited to some tasks compared to complex neural net functions?
1 answers
1 votes
82 views
Can entire neural networks be composed of only activation functions?
0 answers
1 votes
34 views
2 bookmarks
How do non-local neural networks relate to attention and self-attention?