High-Confidence Off-Policy (or Counterfactual) Variance Estimation

High-Confidence Off-Policy Evaluation

Many reinforcement learning algorithms use trajectories collected from the execution of one or more policies to propose a new policy. Because execution of a bad policy can be costly or dangerous, techniques for evaluating the performance of the new policy without requiring its execution have been of recent interest in industry. Such off-policy evaluation methods, which estimate the performance ...

High Confidence Policy Improvement

We present a batch reinforcement learning (RL) algorithm that provides probabilistic guarantees about the quality of each policy that it proposes, and which has no hyper-parameters that require expert tuning. The user may select any performance lower-bound, ρ−, and confidence level, δ, and our algorithm will ensure that the probability that it returns a policy with performance below ρ− is at mo...

Stochastic Variance Reduction for Policy Gradient Estimation

Recent advances in policy gradient methods and deep learning have demonstrated their applicability for complex reinforcement learning problems. However, the variance of the performance gradient estimates obtained from the simulation is often excessive, leading to poor sample efficiency. In this paper, we apply the stochastic variance reduced gradient descent (SVRG) technique [1] to model-free p...

Regularized Policy Gradients: Direct Variance Reduction in Policy Gradient Estimation

Policy gradient algorithms are widely used in reinforcement learning problems with continuous action spaces, which update the policy parameters along the steepest direction of the expected return. However, large variance of policy gradient estimation often causes instability of policy update. In this paper, we propose to suppress the variance of gradient estimation by directly employing the var...

Variance Estimation and Construction of Confidence Intervals for GEE Estimator