Measuring and Optimizing Behavioral Complexity for Evolutionary Reinforcement Learning
نویسندگان
چکیده
Model complexity is key concern to any artificial learning system due its critical impact on generalization. However, EC research has only focused phenotype structural complexity for static problems. For sequential decision tasks, phenotypes that are very similar in structure, can produce radically different behaviors, and the trade-off between fitness and complexity in this context is not clear. In this paper, behavioral complexity is measured explicitly using compression, and used as a separate objective to be optimized (not as an additional regularization term in a scalar fitness), in order to study this trade-off directly.
منابع مشابه
Evolving Childhood’s Length and Learning Parameters in an Intrinsically Motivated Reinforcement Learning Robot
The capacity of re-using previously acquired skills can greatly enhance robots’ learning speed and behavioral complexity. ‘Intrinsically Motivated Reinforcement Learning (IMRL)’ is a framework that exploits this idea and proposes to build agents capable of solving several specific tasks by assembling general-purpose building-block behaviors (‘skills’) previously acquired on the basis of ‘intrin...
متن کاملRelational Databases Query Optimization using Hybrid Evolutionary Algorithm
Optimizing the database queries is one of hard research problems. Exhaustive search techniques like dynamic programming is suitable for queries with a few relations, but by increasing the number of relations in query, much use of memory and processing is needed, and the use of these methods is not suitable, so we have to use random and evolutionary methods. The use of evolutionary methods, beca...
متن کاملModeling and Control of Discrete Event Dynamic Systems: a Simulator-based Reinforcement-learning Paradigm
A general reinforcement-learning approach for controlling discrete event systems is presented. A machine-repair example is formulated: (1) to describe and explain the DEVS formulation, and (2) to illustrate the general control method. Modified gradient learning methods and evolutionary programming methods are compared for the purpose of optimizing the controller. An on-line adaptation method is...
متن کاملOptimizing the AGC system of a three-unequal-area hydrothermal system based on evolutionary algorithms
This paper focuses on expanding and evaluating an automatic generation control (AGC) system of a hydrothermal system by modelling the appropriate generation rate constraints to operate practically in an economic manner. The hydro area is considered with an electric governor and the thermal area is modelled with a reheat turbine. Furthermore, the integral controllers and electri...
متن کاملMulticast Routing in Wireless Sensor Networks: A Distributed Reinforcement Learning Approach
Wireless Sensor Networks (WSNs) are consist of independent distributed sensors with storing, processing, sensing and communication capabilities to monitor physical or environmental conditions. There are number of challenges in WSNs because of limitation of battery power, communications, computation and storage space. In the recent years, computational intelligence approaches such as evolutionar...
متن کامل