Self-Adaptive Rolling Horizon Evolutionary Algorithms for General Video Game Playing

Gaina, Raluca D.; Peŕez-Liebana, Diego; Lucas, Simon M.; Sironi, Chiara F.; Winands, Mark H. M.

doi:10.1109/cog47356.2020.9231587

Cited by 6 publications

(3 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…According to constraint conditions and copied dynamic equations, the MATLAB simulation software is used to analyze the ideal state of the tripartite game among the government, farmers and consumers [27][28]. To make a more intuitive understanding of the evolution process and results between the government, farmers and consumers in numerical experiments, we present experiments to simulate the evolution process when the initial proportions and related parameter changes.…”

Section: A Effect Of Different Initial Proportions On the Evolutionary Resultsmentioning

confidence: 99%

Research on the Evolutionary Decision-Making Behavior Among the Government, Farmers, and Consumers: Based on the Quality and Safety of Agricultural Products

et al. 2021

View full text Add to dashboard Cite

YUN TENG received a Ph.D. degree from the Harbin Engineering University, Harbin, China in 2016, where she is currently a professor and a Ph.D. supervisor. Her research interests include agricultural economics and management theory and method.XINLIN CHEN received the a bachelor's degree in engineering from Northeast Agricultural University in China in 2020. She is currently studying for a master's degree at Northeast Agricultural University in China. Her research mainly focuses on managed agricultural production, evolutionary games and data mining. ZHIGANG YU received a Ph.D. degree from JilinUniversity, Changchun, China in 2012, where he is currently a professor and a Ph.D. supervisor. His research interests include agricultural economics and management theory and methods.JINGBO WEI received the a bachelor's degree in engineering from Northeast Agricultural University in China in 2020. He is currently studying for a master's degree at Northeast Agricultural University in China. His research mainly focuses on managed agricultural production , evolutionary games and data mining.

show abstract

Section: A Effect Of Different Initial Proportions On the Evolutionary Resultsmentioning

confidence: 99%

Research on the Evolutionary Decision-Making Behavior Among the Government, Farmers, and Consumers: Based on the Quality and Safety of Agricultural Products

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Further extensive growth in this direction can be safely envisaged. (2) AutoMCTS-an enhancement of MCTS with self-adaptation mechanisms (Świechowski and Mańdziuk 2014;Gaina et al 2020), which rely on finding optimal hyperparameters or the most adequate policies for a given problem being solved. As discussed in Sect.…”

Section: Discussionmentioning

confidence: 99%

“…The online self-adaptation of MCTS (e.g.) has also its counterparts for RHEA as described by Gaina et al (2020).…”

Section: Rolling Horizon Evolutionary Algorithmmentioning

confidence: 99%

Monte Carlo Tree Search: a review of recent modifications and applications

Świechowski¹,

et al. 2022

View full text Add to dashboard Cite

Monte Carlo Tree Search (MCTS) is a powerful approach to designing game-playing bots or solving sequential decision problems. The method relies on intelligent tree search that balances exploration and exploitation. MCTS performs random sampling in the form of simulations and stores statistics of actions to make more educated choices in each subsequent iteration. The method has become a state-of-the-art technique for combinatorial games. However, in more complex games (e.g. those with a high branching factor or real-time ones) as well as in various practical domains (e.g. transportation, scheduling or security) an efficient MCTS application often requires its problem-dependent modification or integration with other techniques. Such domain-specific modifications and hybrid approaches are the main focus of this survey. The last major MCTS survey was published in 2012. Contributions that appeared since its release are of particular interest for this review.

show abstract

Warm-Start AlphaZero Self-play Search Enhancements

Wang

Preuß

Plaat

2020

Parallel Problem Solving From Nature – PPSN XVI

View full text Add to dashboard Cite

Recently, AlphaZero has achieved landmark results in deep reinforcement learning, by providing a single self-play architecture that learned three different games at super human level. AlphaZero is a large and complicated system with many parameters, and success requires much compute power and fine-tuning. Reproducing results in other games is a challenge, and many researchers are looking for ways to improve results while reducing computational demands. AlphaZero's design is purely based on self-play and makes no use of labeled expert data or domain specific enhancements; it is designed to learn from scratch. We propose a novel approach to deal with this cold-start problem by employing simple search enhancements at the beginning phase of self-play training, namely Rollout, Rapid Action Value Estimate (RAVE) and dynamically weighted combinations of these with the neural network, and Rolling Horizon Evolutionary Algorithms (RHEA). Our experiments indicate that most of these enhancements improve the performance of their baseline player in three different (small) board games, with especially RAVE based variants playing strongly.

show abstract

Self-Adaptive Rolling Horizon Evolutionary Algorithms for General Video Game Playing

Cited by 6 publications

References 16 publications

Research on the Evolutionary Decision-Making Behavior Among the Government, Farmers, and Consumers: Based on the Quality and Safety of Agricultural Products

Research on the Evolutionary Decision-Making Behavior Among the Government, Farmers, and Consumers: Based on the Quality and Safety of Agricultural Products

Monte Carlo Tree Search: a review of recent modifications and applications

Warm-Start AlphaZero Self-play Search Enhancements

Contact Info

Product

Resources

About