Variance-Reduced Off-Policy Memory-Efficient Policy Search

by   Daoming Lyu, et al.

Off-policy policy optimization is a challenging problem in reinforcement learning (RL). The algorithms designed for this problem often suffer from high variance in their estimators, which results in poor sample efficiency, and have issues with convergence. A few variance-reduced on-policy policy gradient algorithms have been recently proposed that use methods from stochastic optimization to reduce the variance of the gradient estimate in the REINFORCE algorithm. However, these algorithms are not designed for the off-policy setting and are memory-inefficient, since they need to collect and store a large “reference” batch of samples from time to time. To achieve variance-reduced off-policy-stable policy optimization, we propose an algorithm family that is memory-efficient, stochastically variance-reduced, and capable of learning from off-policy samples. Empirical studies validate the effectiveness of the proposed approaches.


page 1

page 2

page 3

page 4


On the Convergence and Sample Efficiency of Variance-Reduced Policy Gradient Method

Policy gradient gives rise to a rich class of reinforcement learning (RL...

Stable and Efficient Policy Evaluation

Policy evaluation algorithms are essential to reinforcement learning due...

Don't Forget Your Teacher: A Corrective Reinforcement Learning Framework

Although reinforcement learning (RL) can provide reliable solutions in m...

Stochastic Variance Reduction for Deep Q-learning

Recent advances in deep reinforcement learning have achieved human-level...

Local policy search with Bayesian optimization

Reinforcement learning (RL) aims to find an optimal policy by interactio...

SVRG for Policy Evaluation with Fewer Gradient Evaluations

Stochastic variance-reduced gradient (SVRG) is an optimization method or...

Reanalysis of Variance Reduced Temporal Difference Learning

Temporal difference (TD) learning is a popular algorithm for policy eval...