Log In Sign Up

Momentum-Based Policy Gradient Methods

by   Feihu Huang, et al.

In the paper, we propose a class of efficient momentum-based policy gradient methods for the model-free reinforcement learning, which use adaptive learning rates and do not require any large batches. Specifically, we propose a fast important-sampling momentum-based policy gradient (IS-MBPG) method based on a new momentum-based variance reduced technique and the importance sampling technique. We also propose a fast Hessian-aided momentum-based policy gradient (HA-MBPG) method based on the momentum-based variance reduced technique and the Hessian-aided technique. Moreover, we prove that both the IS-MBPG and HA-MBPG methods reach the best known sample complexity of O(ϵ^-3) for finding an ϵ-stationary point of the non-concave performance function, which only require one trajectory at each iteration. In particular, we present a non-adaptive version of IS-MBPG method, i.e., IS-MBPG*, which also reaches the best known sample complexity of O(ϵ^-3) without any large batches. In the experiments, we apply four benchmark tasks to demonstrate the effectiveness of our algorithms.


Bregman Gradient Policy Optimization

In this paper, we design a novel Bregman gradient policy optimization fr...

MDPGT: Momentum-based Decentralized Policy Gradient Tracking

We propose a novel policy gradient method for multi-agent reinforcement ...

An Improved Convergence Analysis of Stochastic Variance-Reduced Policy Gradient

We revisit the stochastic variance-reduced policy gradient (SVRPG) metho...

Adaptive Momentum-Based Policy Gradient with Second-Order Information

The variance reduced gradient estimators for policy gradient methods has...

Stochastic Recursive Momentum for Policy Gradient Methods

In this paper, we propose a novel algorithm named STOchastic Recursive M...

On the Global Convergence of Momentum-based Policy Gradient

Policy gradient (PG) methods are popular and efficient for large-scale r...

BiAdam: Fast Adaptive Bilevel Optimization Methods

Bilevel optimization recently has attracted increased interest in machin...