"Behavior"的相关文档

Data-Efficient Policy Evaluation Through Behavior Policy Search

Data-EfﬁcientPolicyEvaluationThroughBehaviorPolicySearchJosiahP.Hanna1PhilipS.Thomas23PeterStone1ScottNiekum1AbstractMethodsthatevaluateπewhileselectingactionsaccordingtoπearetermedon-policy.Pre...

through Evaluation Policy Data-Efficient Behavior

2023-11-12 20:44:0716161.12 MB4

Learning Human Objectives by Evaluating Hypothetical Behavior

Data-Efficient Policy Evaluation Through Behavior Policy Search