Exploring Parameter Space in Reinforcement Learning
نویسندگان
چکیده
منابع مشابه
Exploring parameter space in reinforcement learning
This paper discusses parameter-based exploration methods for reinforcement learning. Parameter-based methods perturb parameters of a general function approximator directly, rather than adding noise to the resulting actions. Parameter-based exploration unifies reinforcement learning and black-box optimization, and has several advantages over action perturbation. We review two recent parameter-ex...
متن کاملExploring Multi-action Relationship in Reinforcement Learning
In many real-world reinforcement learning problems, an agent needs to control multiple actions simultaneously. To learn under this circumstance, previously, each action was commonly treated independently with other. However, these multiple actions are rarely independent in applications, and it could be helpful to accelerate the learning if the underlying relationship among the actions is utiliz...
متن کاملExploring the Superimposed Oscillations Parameter Space
The space of parameters characterizing an inflationary primordial power spectrum with small superimposed oscillations is explored using Monte Carlo methods. The most interesting region corresponding to high frequency oscillations is included in the analysis. The oscillations originate from some new physics taking place at the beginning of the inflationary phase and characterized by the new ener...
متن کاملReinforcement Learning in Continuous Time and Space
This article presents a reinforcement learning framework for continuous-time dynamical systems without a priori discretization of time, state, and action. Based on the Hamilton-Jacobi-Bellman (HJB) equation for infinite-horizon, discounted reward problems, we derive algorithms for estimating value functions and improving policies with the use of function approximators. The process of value func...
متن کاملDeep Reinforcement Learning in Parameterized Action Space
Recent work has shown that deep neural networks are capable of approximating both value functions and policies in reinforcement learning domains featuring continuous state and action spaces. However, to the best of our knowledge no previous work has succeeded at using deep neural networks in structured (parameterized) continuous action spaces. To fill this gap, this paper focuses on learning wi...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Paladyn, Journal of Behavioral Robotics
سال: 2010
ISSN: 2081-4836
DOI: 10.2478/s13230-010-0002-4