paper-with-me

홈 › Papers

Improving Deep Policy Gradients with Value Function Search

2023-02-20 · Enrico Marchesini, Christopher Amato

Deep Policy Gradient (PG) algorithms employ value networks to drive the learning of parameterized policies and reduce the variance of the gradient estimates. However, value function approximation gets stuck in local optima and struggles to fit the actual return, limiting the variance reduction efficacy and leading policies to sub-optimal performance. This paper focuses on improving value approximation and analyzing the effects on Deep PG primitives such as value prediction, variance reduction, and correlation of gradient estimates with the true gradient. To this end, we introduce a Value Function Search that employs a population of perturbed value networks to search for a better approximation. Our framework does not require additional environment interactions, gradient computations, or ensembles, providing a computationally inexpensive approach to enhance the supervised learning task on which value networks train. Crucially, we show that improving Deep PG primitives results in improved sample efficiency and policies with higher returns using common continuous control benchmark domains.

📄 PDF Abstract BibTeX arXiv:2302.10145

Code (0)

등록된 구현이 없습니다.

Tasks

continuous-controlContinuous ControlValue prediction

Similar Papers 제목 키워드 기반

Equivalence of stochastic and deterministic policy gradients

2025-05-29 · Emo Todorov

Policy gradients in continuous control have been derived for both stochastic and deterministic policies. Here we study the relationship between the two. In a widely-used family of MDPs involving Gaussian control noise an…

continuous-controlContinuous ControlPolicy Gradient Methods

Almost Sure Convergence of Networked Policy Gradient over Time-Varying Networks in Markov Potential Games

2024-10-26 · Sarper Aydin, Ceyhun Eksin

We propose networked policy gradient play for solving Markov potential games including continuous action and state spaces. In the decentralized algorithm, agents sample their actions from parametrized and differentiable …

Relative Entropy Pathwise Policy Optimization

2025-07-15 · Claas Voelcker, Axel Brunnbauer, Marcel Hussing, Michal Nauman 외

Score-function policy gradients have delivered strong results in game-playing, robotics and language-model fine-tuning. Yet its high-variance often undermines training stability. On the other hand, pathwise policy gradie…

GPU

Particle Value Functions

2017-03-16 · Chris J. Maddison, Dieterich Lawson, George Tucker, Nicolas Heess 외

The policy gradients of the expected return objective can react slowly to rare rewards. Yet, in some cases agents may wish to emphasize the low or high returns regardless of their probability. Borrowing from the economic…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)

Gradient Informed Proximal Policy Optimization

2023-12-14 · NeurIPS 2023 11 · Sanghyun Son, Laura Yu Zheng, Ryan Sullivan, Yi-Ling Qiao 외

We introduce a novel policy learning method that integrates analytical gradients from differentiable environments with the Proximal Policy Optimization (PPO) algorithm. To incorporate analytical gradients into the PPO fr…