Keyphrases
Constraint Violation
100%
Efficient Model
100%
Linear Function Approximation
100%
Regret
75%
Feature Mapping
75%
UCB Algorithm
50%
Adaptation
25%
Reward Function
25%
Utility Function
25%
State Action
25%
State Space
25%
Large-scale Systems
25%
Action Function
25%
Linear Function
25%
Number of States
25%
Model-based Approach
25%
Number of Steps
25%
Cumulative Reward
25%
Uniform Concentration
25%
Softmax
25%
Constrained Markov Decision Process
25%
Sub-linear Regret
25%
Transitional Dynamics
25%
Reinforcement Learning Problems
25%
Constrained Reinforcement Learning
25%
Greedy Selection
25%
Transition Model
25%
Primal-dual Optimization
25%
Model-free Methods
25%
Computer Science
Constraint Violation
100%
Function Approximation
100%
Linear Function
100%
Feature Mapping
75%
Approximation (Algorithm)
25%
Learning Problem
25%
Utility Function
25%
Reinforcement Learning
25%
State Space
25%
Primal-Dual
25%
Markov Decision Process
25%
Transition Model
25%
Mathematics
Linear Function
100%
Tradeoff
33%
Total Number
33%
Main Result
33%
Markov Decision Process
33%
Utility Function
33%
Chemical Engineering
Reinforcement Learning
100%