The Beta Policy for Continuous Control Reinforcement Learning

نویسندگان

  • Po-Wei Chou
  • Sebastian Scherer
  • Kris Kitani
  • Daniel Maturana
  • Guan-Horng Liu
  • Ming Hsiao
  • Yen-Chi Chen
  • Wen Sun
چکیده

Recently, reinforcement learning with deep neural networks has achieved great success in challenging continuous control problems such as 3D locomotion and robotic manipulation. However, in real-world control problems, the actions one can take are bounded by physical constraints, which introduces a bias when the standard Gaussian distribution is used as the stochastic policy. In this work, we propose to use the Beta distribution as an alternative and analyze the bias and variance of the policy gradients of both policies. We show that the Beta policy is bias-free and provides significantly faster convergence and higher scores over the Gaussian policy when both are used with trust region policy optimization (TRPO) and actor critic with experience replay (ACER), the state-of-the-art onand off-policy stochastic methods respectively, on OpenAI Gym’s and MuJoCo’s continuous control environments.

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Improving Stochastic Policy Gradients in Continuous Control with Deep Reinforcement Learning using the Beta Distribution

Recently, reinforcement learning with deep neural networks has achieved great success in challenging continuous control problems such as 3D locomotion and robotic manipulation. However, in real-world control problems, the actions one can take are bounded by physical constraints, which introduces a bias when the standard Gaussian distribution is used as the stochastic policy. In this work, we pr...

متن کامل

Reproducibility of Benchmarked Deep Reinforcement Learning Tasks for Continuous Control

Policy gradient methods in reinforcement learning have become increasingly prevalent for state-of-the-art performance in continuous control tasks. Novel methods typically benchmark against a few key algorithms such as deep deterministic policy gradients and trust region policy optimization. As such, it is important to present and use consistent baselines experiments. However, this can be diffic...

متن کامل

Comparing Deep Reinforcement Learning and Evolutionary Methods in Continuous Control

Reinforcement learning and evolutionary strategy are two major approaches in addressing complicated control problems. Both have strong biological basis and there have been recently many advanced techniques in both domains. In this paper, we present a thorough comparison between the state of the art techniques in both domains in complex continuous control tasks. We also formulate the parallelize...

متن کامل

Operation Scheduling of MGs Based on Deep Reinforcement Learning Algorithm

: In this paper, the operation scheduling of Microgrids (MGs), including Distributed Energy Resources (DERs) and Energy Storage Systems (ESSs), is proposed using a Deep Reinforcement Learning (DRL) based approach. Due to the dynamic characteristic of the problem, it firstly is formulated as a Markov Decision Process (MDP). Next, Deep Deterministic Policy Gradient (DDPG) algorithm is presented t...

متن کامل

Deep Reinforcement Learning for Robotic Manipulation - The state of the art

The focus of this work is to enumerate the various approaches and algorithms that center around application of reinforcement learning in robotic manipulation tasks. Earlier methods utilized specialized policy representations and human demonstrations to constrict the policy. Such methods worked well with continuous state and policy space of robots but failed to come up with generalized policies....

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2017