Computer Science
Slow Convergence
100%
Gradient Method
100%
Navigation Task
100%
Stochastic Policy
100%
Reinforcement Learning-Based Method
100%
Variance Reduction
100%
Experimental Result
100%
Continuous Control
100%
Bounded Interval
100%
Reduction Property
100%
Keyphrases
Action Space
100%
Family of Estimators
100%
Bounded Actions
100%
Policy Gradient
100%
Action Policy
33%
Real-time Strategy Games
33%
Popular
11%
Variance Reduction
11%
Complex Domain
11%
Policy-based
11%
Navigation Task
11%
Parametrized
11%
Discrete Set
11%
Continuous Control
11%
Gradient Estimator
11%
Slow Convergence
11%
Policy Gradient Method
11%
Robotic Control
11%
Reduction Property
11%
Directional Control
11%
Continuous Parameters
11%
Reinforcement Learning Algorithm
11%
Variance-reduced Method
11%
Unbounded Support
11%
Stochastic Policy Gradient
11%
Unified Analysis
11%
Mathematics
Variance
100%
Marginals
100%
Action Space
100%
Variance Reduction
25%
Discrete Set
25%
Stochastics
25%
Bounded Interval
25%
Reduction Property
25%