Statements (11)
| Predicate | Object |
|---|---|
| gptkbp:instanceOf |
algorithm
|
| gptkbp:appliesTo |
policy gradient methods
|
| gptkbp:developedBy |
gptkb:Richard_S._Sutton
|
| https://www.w3.org/2000/01/rdf-schema#label |
REINFORCE
|
| gptkbp:improves |
policy evaluation
|
| gptkbp:is |
stochastic
model-free |
| gptkbp:isUsedFor |
continuous action spaces
|
| gptkbp:performance |
expected reward
|
| gptkbp:requires |
sample trajectories
|
| gptkbp:usedIn |
reinforcement learning
|