Proximal Policy Optimization Algorithms

最新推荐文章于 2023-06-15 12:41:00 发布

算法学习者

最新推荐文章于 2023-06-15 12:41:00 发布

阅读量3.5k

点赞数 1

分类专栏： DL RL

DL 同时被 2 个专栏收录

158 篇文章 3 订阅

订阅专栏

37 篇文章 10 订阅

订阅专栏

提出了一种新的策略梯度方法——近端策略优化(PPO)，该方法交替进行环境交互采样及使用随机梯度上升优化代理目标函数。PPO允许进行多次小批量更新，兼具TRPO的优点且更易于实现，实验证明其样本复杂度较低。

摘要由CSDN通过智能技术生成

Proximal Policy Optimization Algorithms

John Schulman, Filip Wolski, Prafulla Dhariwal, Alec Radford, Oleg Klimov

(Submitted on 20 Jul 2017)

We propose a new family of policy gradient methods for reinforcement learning, which alternate between sampling data through interaction with the environment, and optimizing a "surrogate" objective function using stochastic gradient ascent. Whereas standard policy gradient methods perform one gradient update per data sample, we propose a novel objective function that enables multiple epochs of minibatch updates. The new methods, which we call proximal policy optimization (PPO), have some of the benefits of trust region policy optimization (TRPO), but they are much simpler to implement, more general, and have better sample complexity (empirically). Our experiments test PPO on a collection of benchmark tasks, including simulated robotic locomotion and Atari game playing, and we show that PPO outperforms other online policy gradient methods, and overall strikes a favorable balance between sample complexity, simplicity, and wall-time.