algo
now
.net
new ·
18
pairs
atlas
problems
fields
listen
quant
AI
philosophy
algonow
/
algorithms
/
Dyna-Q
Dyna-Q
Pairings in the atlas
Model-based planning updates
standard
Sample-efficient RL
reinforcement-learning
Rivals: other methods for the same problems
AlphaZero
Dreamer
MuZero
Prioritized sweeping RL
World models
Where it sits
reinforcement-learning
·
Machine Learning & AI