Reinforcement Learning

Back to List
method ID: reinforcementlearning

Outgoing Relationships

Relationship Target Entity Type Actions
identifies Faithful Rationales otherentity View
combinesWith Training Data Selection method View
combinesWith Information State Approach method View
inspiredBy Adversarial Attacks task View
measures Semantic Adequacy metric View
proposes Generalizable Policies otherentity View
formulatedAs Markov Decision Process method View
guides Visual Question Generation task View
learns Control Policy otherentity View
learns Dialogue Strategies method View