Step Size Adaptation in Evolution Strategies using Reinforcement Learning
نویسندگان
چکیده
AbstractWe discuss the implementation of a learning algorithm for determining adaptation parameters in evolution strategies. As an initial test case, we consider the application of reinforcement learning for determining the relationship between success rates and the adaptation of step sizes in the (1+1)-evolution strategy. The results from the new adaptive scheme when applied to several test functions are compared with those obtained from the (1+1)-evolution strategy with a priori selected parameters. Our results indicate that assigning good reward measures seems to be crucial to the performance of the combined strategy.
منابع مشابه
Evolutionary reinforcement learning of artificial neural networks
In this article we describe EANT2, Evolutionary Acquisition of Neural Topologies, Version 2, a method that creates neural networks by evolutionary reinforcement learning. The structure of the networks is developed using mutation operators, starting from a minimal structure. Their parameters are optimised using CMA-ES, Covariance Matrix Adaptation Evolution Strategy, a derandomised variant of ev...
متن کاملSimilarities and differences between policy gradient methods and evolution strategies
Natural policy gradient methods and the covariance matrix adaptation evolution strategy, two variable metric methods proposed for solving reinforcement learning tasks, are contrasted to point out their conceptual similarities and differences. Experiments on the cart pole benchmark are conducted as a first attempt to compare their performance.
متن کاملInductive Learning of Mutation Step-Size in Evolutionary Parameter Optimization
The problem of setting the mutation step-size for real-coded evolutionary algorithms has received diierent answers: exogenous rules like the 1=5 rule, or endogenous factor like the self-adaptation of the step-size in the Gaussian mutation of modern Evolution Strategies. On the other hand, in the bitstring framework, the control of both crossover and mutation by means of Inductive Leaning has pr...
متن کاملGenetic Encoding of Agent Behavioral Strategy
The general framework tackled in this paper is the automatic generation of intelligent collective behaviors using genetic programming and reinforcement learning. We define a behavior-based system relying on automatic design process using artificial evolution to synthesize high level behaviors for autonomous agents. Behavioral strategies are described by tree-based structures, and manipulated by...
متن کاملStep-Size Adaptation Based on Non-Local Use Selection Information
The performance of Evolution Strategies (ESs) depends on a suitable choice of internal strategy control parameters. Apart from a fixed setting, ESs facilitate an adjustment of such parameters within a self-adaptation process. For stepsize control in particular, various adaptation concepts were evolved early in the development of ESs. These algorithms mostly work very efficiently as long as the ...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2001