Evolutionary Algorithms for Reinforcement Learning

Moriarty, David E.; Schultz, Alan C.; Grefenstette, John J.

doi:10.1613/jair.613

Cited by 252 publications

(144 citation statements)

References 43 publications

Supporting

Mentioning

143

Contrasting

Unclassified

Order By: Relevance

“…The probability of successful strategies is increased. (see also (Moriarty and Schultz, 1999) • Genetic algorithm: Genetic algorithms are orientated on the concept of evolution. The available strategy space is broken down into strategies consisting of small segments (genes), e. g. the volume bid into the market.…”

Section: Models With Focus On Agent Decisions and Learningmentioning

confidence: 99%

Agent-based Simulation of Electricity Markets -A Literature Review-

Sensfuß

Ragwitz

Genoese

et al. 2007

Energy Studies Review

View full text Add to dashboard Cite

Standard-Nutzungsbedingungen:Die Dokumente auf EconStor dürfen zu eigenen wissenschaftlichen Zwecken und zum Privatgebrauch gespeichert und kopiert werden.Sie dürfen die Dokumente nicht für öffentliche oder kommerzielle Zwecke vervielfältigen, öffentlich ausstellen, öffentlich zugänglich machen, vertreiben oder anderweitig nutzen.Sofern die Verfasser die Dokumente unter Open-Content-Lizenzen (insbesondere CC-Lizenzen) zur Verfügung gestellt haben sollten, gelten abweichend von diesen Nutzungsbedingungen die in der dort genannten Lizenz gewährten Nutzungsrechte. Terms of use: Documents in EconStor may AbstractLiberalisation, climate policy and promotion of renewable energy are challenges to players of the electricity sector in many countries. Policy makers have to consider issues like market power, bounded rationality of players and the appearance of fluctuating energy sources in order to provide adequate legislation. Furthermore the interactions between markets and environmental policy instruments become an issue of increasing importance. A promising approach for the scientific analysis of these developments is the field of agent-based simulation. The goal of this article is to provide an overview of the current work applying this methodology to the analysis of electricity markets.

show abstract

Section: Models With Focus On Agent Decisions and Learningmentioning

confidence: 99%

Agent-based Simulation of Electricity Markets -A Literature Review-

Sensfuß

Ragwitz

Genoese

et al. 2007

Energy Studies Review

View full text Add to dashboard Cite

show abstract

“…There are many studies combined evolutionary algorithms and RL [9,10]. Although the approaches differ from our proposed technique, we see several studies in which GP and RL are combined [7,8].…”

Section: Related Workmentioning

confidence: 99%

Integration of Genetic Programming and Reinforcement Learning for Real Robots

Kamio

Mitsuhashi

Iba

2003

Genetic and Evolutionary Computation — GECCO 2003

View full text Add to dashboard Cite

Abstract.We propose an integrated technique of genetic programming (GP) and reinforcement learning (RL) that allows a real robot to execute real-time learning. Our technique does not need a precise simulator because learning is done with a real robot. Moreover, our technique makes it possible to learn optimal actions in real robots. We show the result of an experiment with a real robot AIBO and represents the result which proves proposed technique performs better than traditional Q-learning method.

show abstract

“…Examples can be found in [37] and [18], where later work also considered optimization of the network structure [47], or using recurrent neural networks to better cope with hidden states [19]. A recent comparison of these methods can also be found in [51] and [26].…”

Section: Direct Policy Searchmentioning

confidence: 99%

“…However, a major issue in DPS is that the final performance strongly depends on the choice of an appropriate policy representation. Common policy representations include linear parametrizations [22], neural networks [37,47,19] or radial basis functions [6,14] and typically have hyper-parameters that require tuning (e.g. the number of hidden neurons).…”

Section: Introductionmentioning

confidence: 99%

Optimized look‐ahead tree policies: a bridge between look‐ahead tree policies and direct policy search

Jung

Wehenkel

Ernst

et al. 2013

Adaptive Control & Signal

View full text Add to dashboard Cite

Direct policy search (DPS) and look-ahead tree (LT) policies are two widely used classes of techniques to produce high performance policies for sequential decision-making problems. To make DPS approaches work well, one crucial issue is to select an appropriate space of parameterized policies with respect to the targeted problem. A fundamental issue in LT approaches is that, to take good decisions, such policies must develop very large look-ahead trees which may require excessive online computational resources. In this paper, we propose a new hybrid policy learning scheme that lies at the intersection of DPS and LT, in which the policy is an algorithm that develops a small look-ahead tree in a directed way, guided by a node scoring function that is learned through DPS. The LT-based representation is shown to be a versatile way of representing policies in a DPS scheme, while at the same time, DPS enables to significantly reduce the size of the look-ahead trees that are required to take high-quality decisions.We experimentally compare our method with two other state-of-the-art DPS techniques and four common LT policies on four benchmark domains and show that it combines the advantages of the two techniques from which it originates. In particular, we show that our method: (1) produces overall better performing policies than both pure DPS and pure LT policies, (2) requires a substantially smaller number of policy evaluations than other DPS techniques, (3) is easy to tune and (4) results in policies that are quite robust with respect to perturbations of the initial conditions.

show abstract

Evolutionary Algorithms for Reinforcement Learning

Cited by 252 publications

References 43 publications

Agent-based Simulation of Electricity Markets -A Literature Review-

Agent-based Simulation of Electricity Markets -A Literature Review-

Integration of Genetic Programming and Reinforcement Learning for Real Robots

Optimized look‐ahead tree policies: a bridge between look‐ahead tree policies and direct policy search

Contact Info

Product

Resources

About