An Improved Convergence Analysis Of Stochastic Variance-reduced Policy Gradient

Abstract

We revisit the stochastic variance-reduced policy gradient (SVRPG) method proposed by Papini et al. (2018) for reinforcement learning. We provide an improved convergence analysis of SVRPG and show that it can find an \(\epsilon\)-approximate stationary point of the performance function within \(O(1/\epsilon^\{5/3\})\) trajectories. This sample complexity improves upon the best known result \(O(1/\epsilon^2)\) by a factor of \(O(1/\epsilon^\{1/3\})\). At the core of our analysis is (i) a tighter upper bound for the variance of importance sampling weights, where we prove that the variance can be controlled by the parameter distance between different policies; and (ii) a fine-grained analysis of the epoch length and batch size parameters such that we can significantly reduce the number of trajectories required in each iteration of SVRPG. We also empirically demonstrate the effectiveness of our theoretical claims of batch sizes on reinforcement learning benchmark tasks.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyxu2019an

Related papers

• Sample Efficient Policy Gradient Methods With Recursive Variance Reduction (2019)0.00
• On The Convergence And Sample Efficiency Of Variance-reduced Policy Gradient Method (2021)0.00
• Stochastic Variance Reduction For Policy Gradient Estimation (2017)0.00
• Oracle Complexity Reduction For Model-free LQR: A Stochastic Variance-reduced Policy Gradient Approach (2023)2.26
• Efficiently Escaping Saddle Points For Policy Optimization (2023)0.00
• Variance Reduction Based Partial Trajectory Reuse To Accelerate Policy Gradient Optimization (2022)0.00
• PAGE-PG: A Simple And Loopless Variance-reduced Policy Gradient Method With Probabilistic Gradient Estimation (2022)0.00
• Policy Optimization With Stochastic Mirror Descent (2019)7.50